CHNSpec Technology （Zhejiang）Co.,Ltd

I.Introduction: Color Consistency In the modern cosmetics and personal care industry, color is not merely a product's visual coating; it is a direct statement of brand credibility and product excellence. From liquid foundations that demand precise skin-tone blending, to lipsticks requiring vivid color payoff, to eyeshadows and pressed powders reliant on smooth color dispersion, consumers are extraordinarily discerning when it comes to shade accuracy. Visual shade discrepancies between production batches—or between in-store tester samples and delivered retail products—inevitably trigger severe commercial consequences: Elevated Customer Complaints & Return Rates: Consumers suspect counterfeit, expired, or reformulated products. Erosion of Brand Equity: Premium beauty brands cannot sustain high market positioning without rigorous color uniformity across global distribution channels. Costly Production Scraps: Detecting shade misalignment after filling or pressing results in significant waste of raw materials and labor hours. To eliminate these risks, cosmetics manufacturers (OEMs, ODMs, and brand owners) require a standardized, quantified, and high-precision Color Quality Control (QC) system. II.Practical Challenges in Cosmetic Color Measurement Cosmetic formulations span diverse states—liquids, pastes, pressed powders, and semi-solids—frequently incorporating pearls, mica, and optical modifiers. These characteristics complicate optical color measurement: 1. Liquid Foundations & Concealers Wet-to-Dry Color Shifts: Liquid formulations frequently undergo oxidation or moisture evaporation during film formation on the skin, altering their visual tone. Quality control must evaluate dry-film state colors against established digital standards. Multiphase Scattering: Foundations are complex emulsions containing titanium dioxide, iron oxides (red, yellow, black), and organic pigments. Light scatters extensively within the emulsion matrix, demanding standardized optical illumination geometry. 2. Lipsticks, Lip Balms & Glosses High Gloss Interference: Formulated with high pigment concentrations and waxes, lipstick surfaces exhibit strong specular reflection. Colorimeters must isolate specular reflections from diffuse reflectance to capture genuine color density. Micro-Area Curved Geometry: Slanted lipstick tips feature small, non-planar surfaces that standard large-aperture colorimeters cannot seal cleanly. 3. Pressed Powders, Blushes & Loose Powders Compaction Density Variance: Variations in pressing pressure alter particle packing density, directly influencing light reflection and perceived shade intensity. Metamerism & Effect Pigments: Eyeshadows containing mica pearls show different color behaviors under varying light sources (e.g., D65 daylight vs. F2 store lighting). III.Selection of Optical Configuration for Cosmetic Color Measurement Optical Geometry: D/8° Integrating Sphere and SCI/SCE ModesCHNSpec colorimeters and spectrophotometers utilize the D/8°(diffuse illumination, 8° viewing angle) integrating sphere design compliant with CIE No.15 and ISO 7724/1 standards: SCI (Specular Component Included): Measures total reflected light, including specular glare. SCI eliminates surface gloss or texture variances, revealing the true pigmentation of the formula. This mode is optimal for R&D formulation matching and evaluating raw pigment density. SCE (Specular Component Excluded): Blocks specular glare, matching human visual perception of glossy surfaces. SCE is essential for inspecting finished lipsticks, glosses, and shiny cosmetic packaging. IV.CHNSpec Colorimeter Solutions for Cosmetic Quality Control CHNSpec Technology supplies a full hierarchy of color measuring equipment, ranging from portable colorimeters to benchtop spectrophotometers. 1. Handheld Spectrophotometers & ColorMeter Series (DS-700 / DS-200 / ColorMeter) For fast floor checks, incoming raw material inspections, and portable QA, handheld colorimeters offer necessary mobility and speed. Repeatability: Models like the DS-200 and DS-700 series achieve short-term repeatability of ΔE*ab ≤ 0.02  ~ 0.03, ensuring consistent measurements across shifts. Versatile Measurement Apertures: 8mm / 11mm Apertures: Ideal for compact powder pans, loose powder samples, and drawdown cards. 3mm / 4mm/ 6mm Micro Apertures: Designed for small, contoured surfaces such as slanted lipstick tips, narrow lip gloss sticks, and small eyeshadow pans. Smart App & Cloud Integration: CHNSpec ColorMeter instruments connect via Bluetooth to iOS/Android devices, enabling instant shade matching, digital color library lookups, and automated Pass/Fail decisions on the factory floor. 2. High-Precision Benchtop Spectrophotometers (CS-820N / DS-820 Series)For central R&D laboratories, master shade library development, and raw material formulation, benchtop spectrophotometers provide analytical precision: Ultra-High Repeatability and Inter-Instrument Agreement: Repeatability ΔE*ab ≤ 0.02, with inter-instrument agreement controlled within ΔE*ab ≤ 0.15 ~ 0.25, ensuring seamless data compatibility across different factories and laboratories worldwide. Spectral Range (360nm - 780nm): Full visible and near-UV spectrum analysis identifies metameric pairs under multi-light source conditions. Dual Reflection & Transmission Modes: Reflection Mode: Accommodates solid lipsticks, opaque cream foundations, and pressed powders using dedicated powder holders and cuvettes.   Transmission Mode: Measures clear or translucent liquid formulations (shampoos, serums, transparent lip tints) for light transmittance and color coordinates. UV Inclusion / Exclusion Filters: Formulations with UV filters or optical brighteners require controlled UV illumination. CHNSpec benchtop models include adjustable UV filters to measure true color with or without UV excitation. V.Conclusion Against the background of globalization and quality upgrading in the cosmetics industry, traditional visual color inspection has gradually revealed its limitations when facing the refined demands of the modern beauty supply chain. Adopting objective, digital colorimeter equipment not only helps enterprises determine shade numbers more precisely during R&D, but also establishes an effective quality control defense line on the production end.

In modern industrial manufacturing, color consistency directly determines brand value and quality control. Whether in automotive coatings, plastic masterbatches, fine chemicals, or food processing, the colorimeter / spectrophotometer is an indispensable precision tool in the quality control laboratory.However, many procurement managers frequently face a common dilemma: "Our test materials are highly diverse—some are liquids, some are powders, and others are irregular solids. What kind of colorimeter architecture should we choose to ensure precise and repeatable measurement data?"The physical form of the test material (liquid, powder, solid) directly dictates how light reflects, transmits, and scatters across or through its surface. Choosing the wrong colorimeter or incorrect fixtures leads to severely distorted color data. This comprehensive guide will analyze how to properly select a colorimeter based on your material's state and introduce the solutions provided by CHNSpec Technology. I.Color Measurement for Liquid Materials: The Art of Transmission and Refraction 1.Technical Challenges in Liquid Color MeasurementLiquid materials—such as beverages, edible oils, petrochemicals, pharmaceuticals, and solvents—are fluid, vary in transparency, and allow light to penetrate easily. For fully transparent or translucent liquids, light passes directly through the sample. Standard reflection-based colorimeters cannot capture enough reflected light to generate accurate CIE Lab values. Furthermore, the fluidity and volatility of liquids require instruments with exceptional anti-contamination designs. 2.Core Selection FactorsOptical Geometry: The instrument must support D/0 (Diffuse illumination, 0-degree viewing) transmission measurement mode.Accessory Support: High-quality cuvettes or quartz glass test fixtures are mandatory to maintain a fixed liquid sample thickness.Industry Indices: The device should support liquid-specific color indices such as APHA/Hazen (Pt-Co), Gardner, and Saybolt. 3.CHNSpec Recommended Models: CS-821N / CS-820P Benchtop SpectrophotometersFor liquid measurement, benchtop models provide unparalleled optical stability.CHNSpec CS-821N / CS-820P: These high-end benchtop spectrophotometers feature an integrated architecture supporting both Reflection D/8 and Transmission D/0 geometries. Their spacious transmission chambers (located on the side or top) easily accommodate various specifications of quartz cuvettes. They not only precisely measure CIE Lab color differences but also directly output crucial liquid color indices. II.Color Measurement for Powder Materials: Overcoming Scattering and Texture Challenges1.Technical Challenges in Powder Color MeasurementPowder materials (such as flour, titanium dioxide, pigments, cosmetic powders, and cement) possess surfaces formed by countless microscopic particles. When the light from a colorimeter hits a powder surface, severe multi-angle diffuse scattering occurs. If the compactness of the powder packing varies, or if the grain sizes are uneven, the colorimeter will yield vastly different data even when measuring the exact same sample. 2.Core Selection FactorsMeasurement Aperture: A colorimeter with a Large Aperture is highly recommended. A larger measurement area effectively averages out the surface irregularities of the powder, providing stable and repeatable data.Specialized Test Cell / Powder Press: To ensure a completely flat measurement surface, the powder should be loaded into a dedicated powder test cell or compressed into a stable "color cake" using a powder press.Illumination Structure: A D/8 (diffuse illumination, 8-degree viewing) spectrophotometer is preferred, as it effectively eliminates measurement errors caused by tiny shadows on granular surfaces. 3.CHNSpec Recommended Models: DS-807 Large-Aperture SpectrophotometerCHNSpec DS-807: Engineered specifically for granules and powders, it boasts an ultra-large 50mm measurement aperture. This vast aperture easily handles powder surface inconsistencies, delivering highly repeatable data without requiring overly strict compression techniques. III.Color Measurement for Solid Materials: Adapting to Texture, Shape, and Gloss Variations1.Technical Challenges in Solid Color MeasurementSolid materials represent the widest range of applications and the most complex physical variations:Regular & Flat Solids: Plastic sheets, metal plates, and paper are the easiest to measure directly.Irregular & Small Solids: Plastic pellets, textile yarns, and tiny electronic components.High-Gloss & Textured Solids: Automotive coatings, leather, and 3D-printed parts.Surface gloss and texture heavily distort how the human eye perceives color. Therefore, a colorimeter must be capable of separating SCI (Specular Component Included) and SCE (Specular Component Excluded) data. 2.Core Selection FactorsOptical Geometry: The D/8 (SCI/SCE) structure is the universal standard for solid color checking. SCI mode evaluates the true color formulation (ignoring gloss effects), while SCE mode evaluates the color exactly as the human eye sees it (influenced by gloss). For pure coatings or printed matter, a 45/0 geometry may be chosen to align closely with human visual observation habits.Multi-Aperture Switching: To measure solids of different dimensions, the colorimeter should ideally recognize and switch between various aperture sizes (e.g., 8mm, 4mm, 3mm) automatically.Camera Targeting: For measuring specific micro-zones on solid parts, a built-in camera viewport is essential for perfect alignment. 3.CHNSpec Recommended Models: DS-700D Portable ColorimetersCHNSpec DS-700D: As a flagship model among CHNSpec’s portable spectrophotometers, it supports simultaneous SCI/SCE measurement and delivers exceptional inter-instrument agreement alongside outstanding repeatability. Equipped with an intelligent automatic aperture recognition function, it flexibly caters to diverse color detection needs, ranging from large-area plastic sheets to microscopic solid components. IV.ConclusionBy precisely matching the physical characteristics of materials with the technical parameters of colorimeters, enterprises can effectively minimize common measurement errors. Leveraging its comprehensive product line and numerous patented technologies, CHNSpec Technology provides customers with full-scenario color management solutions covering liquids, powders, and solids. For different material forms, CHNSpec offers tailored colorimeters to help your color quality control seamlessly align with international standards.

In the fiercely competitive global Fast-Moving Consumer Goods (FMCG) market, food packaging is far more than just a container to protect the product—it is the brand's silent spokesperson. Imagine a consumer standing in front of a supermarket shelf, looking at the same Coca-Cola or Lay's potato chips, only to notice that different batches of the packaging have obvious color variations, such as "red shifting to purple" or "yellow shifting to green." What would they think? For the vast majority of consumers, their first reaction would be: "Is this a counterfeit?" or "Has this product expired?" This is the harsh reality of brand color consistency. For food brands, color deviations in packaging print can directly damage brand trust. However, food packaging materials are extremely complex. From flexible plastic packaging and aluminum foil to paperboard cartons and corrugated boxes, different substrates, ink batches, and printing processes (such as flexography, gravure, and digital printing) all contribute to color variations. How can this pain point be resolved? The answer lies in abandoning naked-eye evaluation in favor of digital color management. And the core tools of this digital management are colorimeters and spectrophotometers. I.The 4 Major Obstacles to Color Control in Food Packaging PrintingBefore jumping into the solution, we must understand why controlling color in food packaging is notoriously difficult: 1.Substrate Diversity: Food packaging utilizes a wide range of materials including laminated films, metallic foils, kraft paper, and plastics. Each material has distinct reflectance, absorption, and base colors. The same ink printed on different substrates will look drastically different to the naked eye. 2.Ink and Coating Variations: Even inks from the same manufacturer can exhibit minor variances between batches. Furthermore, water-based inks commonly used in food packaging are highly sensitive; slight adjustments in viscosity and pH will shift the final color. 3.Complexity of Printing Processes: Factors like the high speed of rotogravure printing, anilox roller wear in flexography, water-ink balance in offset printing, and the subsequent lamination process all introduce unpredictable color drift. 4.Metamerism & Human Error: Visual inspection is highly subjective. It is easily influenced by ambient lighting, operator fatigue, and the phenomenon of metamerism—where two colors match under one light source (e.g., D65 daylight) but look completely different under another (e.g., store fluorescent light). II.Digital Color Management: Understanding ΔE (Color Difference)To completely eliminate subjective errors, the printing and packaging industry relies on the CIE Lab color space and the ΔE color difference formula: In modern food packaging supply chains, global brands enforce strict tolerances on their print vendors: ΔE < 1.0: Perceptible only to highly trained eyes or instruments. This is the premium standard required by top-tier international brands. 1.0 ≤ ΔE < 2.0: Noticeable to experienced QA inspectors; typically accepted as the commercial passing standard for food packaging. ΔE  ≥  2.0: Easily spotted by average consumers on retail shelves. This represents an unacceptable deviation that often leads to rejected shipments and high financial losses. Without quantitative measurement by precision instruments, press operators cannot make data-driven, real-time adjustments during production runs. III.CHNSPEC Color Solutions for Food Packaging & Recommended Models1. The Production QC & Portable Champion: CHNSPEC DS-700D SpectrophotometerFor quality control teams who need to frequently move between the printing floor, ink-mixing room, and the QA laboratory, the DS-700D is the undisputed king of performance and value. Core Advantages: It boasts an exceptional inter-instrument agreement (ΔE*ab ≤ 0.2) and high repeatability (≤ 0.02). This ensures that data measured on a DS-700D in one facility perfectly aligns with a unit used at another site across the globe. Packaging-Specific Performance: It supports simultaneous SCI (Specular Component Included) and SCE (Specular Component Excluded) measurements. Whether you are measuring highly reflective laminated plastic snack bags or matte cardboard boxes, it accurately captures the true color profile. Smart Connectivity: By connecting seamlessly to mobile apps and PC color management software, data is synced to the cloud in real-time, making it an ideal tool for global food brands to monitor overseas contract manufacturers. 2. The Ink and Dot Control Expert: CHNSPEC EX Series Printing Spectrodensitometer (EX PRO/MAX)If your facility focuses heavily on commercial offset, corrugated box printing, or rotogravure flexible packaging, you need more than just color difference data—为 you need to know ink film thickness and dot behavior. The CHNSPEC EX Series is purpose-built for the printing shop. Core Advantages: Seamlessly integrates high-precision spectrophotometric color measurement with advanced printing densitometry. Essential Print Control Features: It measures critical printing parameters such as Dot Gain (Tonal Value Increase), Trapping, Print Contrast, and Ink Density. Featuring a dual-positioning system (physical alignment + built-in camera viewfinder), operators can effortlessly target and measure tiny color bars on the edge of the packaging. Best Applied To: Paper food boxes, liquid milk cartons, and large corrugated outer shipping cases. ConclusionIn the world of food packaging, color equals sales, and color equals brand safety. Implementing CHNSPEC's high-precision colorimeters and spectrophotometers allows packaging printers to shift from reactive guesswork to proactive, data-driven quality control. Not only does this drastically minimize waste, reduce ink costs, and optimize substrate utilization.

Introduction: In the plastics and injection molding industry, color consistency is not just an aesthetic parameter—it is a direct reflection of a brand's quality and credibility. When faced with multi-batch production, raw material variations, recycled material blending, and complex part assembly, how do molders achieve precise color control? I.The "Color Difference Nightmare" in Injection Molding During the actual production of plastic parts, batch-to-batch color variation is a common and challenging pain point. The factors driving color fluctuations are multifaceted: 1.Raw Material Fluctuations: Slight base color variations exist in different batches of plastic resins (e.g., PP, ABS, PC). Uneven dispersion or ratio mismatch of color masterbatches and pigments also leads to color shifts. 2.Process Parameter Drifts: Variations in barrel temperature, injection pressure, holding time, and mold temperature during injection molding can trigger thermal degradation or alter micro-surface crystallinity, changing the light reflection and gloss. 3.Use of Recycled Materials: To cut costs or comply with environmental mandates, molders often blend regrind materials. Repeated heating shears the polymers, causing yellowing and significantly complicating mixture control. 4.Surface Texture Effects: Due to differing diffuse reflection paths, the exact same color formula will look distinctly different on a glossy surface compared to a textured (matte/grain) surface to the human eye. II.Establishing a Standardized Color QC Workflow Relying solely on visual evaluation introduces major subjective bias (such as ambient lighting conditions, operator eye fatigue, and physiological differences). Integrating a high-precision spectrophotometer is the only way to achieve scientific, quantitative color management. A standard QC workflow includes: Step 1: Establish Digital StandardsMeasure the physical standard plaque provided by the customer using a spectrophotometer. Store its absolute scientific values—L*(lightness), a*(redness/greenness), b* (yellowness/blueness), and spectral reflectance curves—directly into the instrument. Step 2: Define Realistic Color TolerancesIn the plastics sector, ΔE*ab or the more human-eye-aligned ΔE*00 is typically used as the pass/fail index.High-Precision Assemblies (Automotive Interiors, 3C Electronics): ΔE*ab < 0.5.General Consumer Goods: ΔE*ab < 1.0. Step 3: IQC & FAI (Incoming & First Article Inspection)Perform rapid sampling on incoming masterbatches and raw pellets. Furthermore, the "First Article" produced at the start of each molding run must be checked to ensure process parameters have not drifted. Step 4: IPQC (In-Process Quality Control) Sample finished products periodically during production. Compare measurements against the saved digital standard. If the ΔE approaches the threshold, immediately adjust the molding temperature or feed ratio. III.Recommended CHNSpec Models & Key Applications 1. For Complex, Curved, or Mini Plastic Parts: CHNSpec DS-700D Spectrophotometer Key Strengths: Tool-free Multi-aperture Switching, Smart Auto-Calibration, High-Accuracy Dual-Path CMOS The Challenge: Molded parts often feature complex curves, narrow grooves, ribbing, or tiny clips. A single large aperture can cause light leakage, yielding faulty measurements. The CHNSpec DS-700D Solution: 3 Apertures in One Device: Comes standard with 11mm, 6mm, and a specialized 1mm X 3mm strip aperture for tiny parts. Switch apertures in seconds without any tools. Intelligent Auto-Calibration: Equipped with a premium Zirconia (ZrO₂) white tile calibration base. It self-calibrates automatically on the base, eliminating manual calibration errors and protecting the tile from scratches. SCI and SCE Compatibility: Supports both Specular Component Included (SCI) and Specular Component Excluded (SCE) modes. When mold wear alters a part's gloss, SCI mode isolates the gloss factor to measure the true pigment color difference, helping engineers pinpoint formulation errors. 2. For High-Flexibility Production Lines: CHNSpec DS-420 Spectrophotometer Key Strengths: Up to 10 Measurement Apertures, Camera Viewfinder, Outstanding ROI The Challenge: Contract injection molders handle diverse product types daily, requiring a flexible instrument that can measure everything from large flat panels to tiny buttons. The CHNSpec DS-420 Solution: 10 Apertures: Offers a vast selection of 10 different stable and agile apertures (ranging from 3mm to 11mm, making it the ultimate multi-purpose tool for OEM factories. Camera-Aided Positioning: Misalignment near part edges ruins measurement data. The DS-420's built-in camera allows real-time viewing of the exact measurement area on-screen, guaranteeing precise alignment. 3. For Transparent/Translucent Plastics & Films: CHNSpec CS-700 Color Haze Meter Key Strengths: All-in-One Measurement of Color, Haze, and Transmittance The Challenge: For optical parts like light guides, phone cases, light diffusers, and plastic packaging films, managing color is only half the battle. Transmittance (T%) and Haze must also be tightly controlled to ensure optimal optical properties. The CHNSpec CS-700 Solution: Fully compliant with ASTM D1003/D1044, ISO 13468, and other global standards. It delivers color metrics (Lab, Yellowness, Whiteness) alongside haze and light transmission in a single, ultra-fast test.

Forensics PrefaceTrace stains of beverages like coffee, juice, and alcohol are ubiquitous at crime scenes, making it extremely difficult to distinguish their types with the naked eye. Traditional detection methods mostly rely on sampling and chemical color-development processing, which can easily damage physical evidence and are detrimental to subsequent review. Nature published a study that constructed a complete analysis solution combining hyperspectral imaging, band selection, and deep learning. This solution conducted non-destructive identification experiments on nine categories of beverage stains, providing a new perspective for criminal investigation trace evidence detection. Integrating this study, CHNSpec discusses the landing value of hyperspectral technology in the forensic field. I. Existing Difficulties in Traditional Physical Evidence Detection1.Visual recognition has significant limitations. Coffee and tea, or whiskey and rum, are visually highly similar, making manual differentiation extremely difficult; 2.Chemical testing destroys the original form of the stains, preventing physical evidence from being repeatedly verified; 3.Ordinary spectrometer equipment can only perform single-point acquisition, rendering the detection of large-area traces time-consuming; 4.Interferences such as paper color differences and stain air-drying/oxidation hamper judgment, leaving a lack of standardized data support. Hyperspectral imaging relies on its advantages of non-contact, full-field acquisition of chemical spectral fingerprints to make up for the above deficiencies, becoming a practical optical tool for trace evidence analysis. II. Core Tasks Undertaken by Hyperspectral Cameras in the ExperimentThis study utilized a 400–1000 nm visible-to-near-infrared hyperspectral imaging device, equipped with 204 continuous spectral bands, to fully collect the 3D spectral data cube (2D spatial coordinates + 1D spectral curve) of various stains. The entire acquisition process is standardized and reproducible. 1.Multi-Scenario Standardized Spectral AcquisitionThe study simulated real crime scene conditions, uniformly controlling temperature, humidity, light source angle, and stain droplet volume to perform imaging on 9 categories of beverages (papaya juice, coffee, pomegranate juice, orange juice, tea, red wine, whiskey, rum, and brandy): Substrates covered white, pink, and brown absorbent paper towels, including both flat and folded forms; Acquisition was conducted at 6 time intervals from 0 to 5 hours to capture spectral changes caused by oxidation and evaporation; A 1.5×1.5 cm reflection-free ROI (Region of Interest) was designated for each stain, eliminating edge interference pixels to ensure data purity. Before shooting, white board reflection calibration and dark current calibration were completed to uniformly convert data into standardized reflectance curves. This eliminated numerical deviations caused by equipment and illumination, allowing horizontal comparisons of spectral differences among different samples. 2.Capturing Invisible Chemical Spectral CharacteristicsEvery imaging pixel generates an exclusive spectral curve, recording reflection values at different wavelengths to unlock chemical differences unrecognizable to the human eye: Red wine and pomegranate juice are rich in anthocyanins, resulting in lower reflection values in the 400–700 nm visible light range; Coffee and tea polyphenols exhibit exclusive absorption characteristics in the blue-green bands; The distinguishing signals for whiskey and rum are concentrated in the 750–900 nm near-infrared range. It is precisely the fine data from hundreds of continuous bands that differentiate two types of beverage stains that look highly identical to the eye. 3.Constructing a Complete Standardized Evidence DatasetThe equipment collected over 120,000 raw spectral samples. After cleaning noise and duplicate pixels, more than 110,000 valid spectral samples were formed, with each sample corresponding to 204-dimensional spectral features, serving as the original data foundation for subsequent band selection and deep learning training. Sufficient, multi-variable spectral samples support the algorithm in learning stable spectral patterns of stains under different substrates and air-drying durations, reducing recognition fluctuations caused by the environment. III. Supporting Algorithm Flow: Dimensionality Reduction + Multi-Model Comparison to Enhance Identification StabilityRaw hyperspectral data has a large number of bands, and redundancy exists between these bands. Direct modeling would increase the computational burden, so the study introduced a two-layer data optimization scheme. 1.ANOVA Band Selection to Retain Effective Discriminative BandsThe ANOVA F-test was employed to calculate the discriminative capacity of each band (inter-class variance / intra-class variance), ranking the 204 bands by their differentiation performance. Through 5-fold cross-validation testing of the recognition performance corresponding to different numbers of bands, 162 highly discriminative bands were ultimately selected for modeling, which reduced the scale of data computation while maintaining recognition performance. 2.Comparative Verification of Four Types of Deep Learning ModelsBased on the selected 162-dimensional spectral data, four mainstream network models—MLP, 1D-CNN, LSTM, and CNN-LSTM hybrid network—were trained with unified hyperparameters. Precision, recall, F1-score, and overall accuracy were uniformly adopted for evaluation: MLP (Multilayer Perceptron) fully connected network: Displayed stable performance in fitting global spectral features, outperforming other models in experimental classification;1D-CNN: Excelled at capturing local spectral variations in adjacent bands; LSTM: Suited for sequential feature learning of continuous spectral bands; CNN-LSTM hybrid structure: Integrated local and sequential features, but due to the influence of data volume, its recognition performance was inferior to single networks. Concurrently, paired t-tests and McNemar's tests verified that the performance differences between models possessed statistical significance, ruling out fluctuation interference caused by random sampling. 3.Spectral Patterns Corroborating the Causes of Identification ConfusionThe misclassification logic of the models can be intuitively seen from the spectral curves: the curves of coffee and tea overlap heavily in the 400–550 nm range, and whiskey and rum show only subtle differences in the near-infrared range. These two pairs of samples are prone to mutual misjudgment, which is consistent with the model's confusion matrix results, proving that spectral data can explain recognition errors and enhance the interpretability of identification results. IV. Core Application Value of Hyperspectral Imaging in Forensic Evidence1.Complete preservation of physical evidence: The entire process requires no reagents and involves no contact with stains. After detection, samples can be preserved for other identifications, conforming to judicial physical evidence specifications; 2.Enhanced investigation efficiency: A single imaging session collects the full spectrum of an entire stain area without the need for point-by-point sampling, making it suitable for rapid on-site screening; 3.Differentiation of visually similar traces: Hundreds of continuous bands capture subtle optical differences in organic matter and pigments, solving visual differentiation dilemmas; 4.Strong environmental adaptability: Experiments verified that the equipment can adapt to stains with different background colors, folds, and air-drying states, with future potential to expand to fabrics, credentials, skin, and other substrates; 5.Digital retention of data: Spectral values can be exported and archived, gradually building a trace spectral library to achieve intelligent sample comparison. Product Recommendation: FigSpecFS-23 Imaging Hyperspectral Camera Image Resolution: 1920*1920 Spectral Range: 400-1000nm Spectral Resolution (FWHM): 2.5nm Number of Spectral Channels: 1200 DisclaimerThis content is compiled and edited based on public academic literature under Nature (Literature Link: https://www.nature.com/articles/s41598-026-49928-8). It is intended solely for industry technical discussion and popular science learning, does not constitute any commercial commitment, and cannot serve as a basis for investment reference. The experimental data and conclusions listed in the text may be interfered with by multiple variables such as the test environment, sample individual differences, and model construction schemes. If applied in actual scenarios, relevant effects must be verified through independent testing combined with specific use cases.

In modern manufacturing, "color" is a critical metric that defines product quality and brand integrity. Whether in plastics, coatings, textiles, or printing, a slight color variation can lead to product rejection and significant financial losses. To quantify and manage color precisely, quality control (QC) teams worldwide rely on colorimeters or spectrophotometers. However, when you receive a data sheet showing L*, a*, b*, and ΔE values, do you know how to interpret them? This guide will demystify these color measurements to help you master color inspection. I.What is the CIE L*a*b* Color Space? The most widely used mathematical color model in global industry is the CIE  L*a*b* color space (commonly referred to as the Lab space), established by the International Commission on Illumination (CIE) in 1976. It is a 3D color space defined by three perpendicular axes:   1.L*(Lightness Axis): Represents how light or dark a color is. L*= 100 indicates pure white. L*= 0 indicates pure black. 2.a*Red-Green Axis): Represents the red/green chromaticity. Positive values (+a*) trend toward Red. Negative values (-a*) trend toward Green.   3.b* (Yellow-Blue Axis): Represents the yellow/blue chromaticity. Positive values (+b*) trend toward Yellow. Negative values (-b*) trend toward Blue. II.How to Read Δ(Delta) Values on a Colorimeter? In real-world quality control, we rarely look at absolute L*, a*, b* values in isolation. Instead, we compare a Sample against a target Standard. The differences are represented by the Greek letter Δ (Delta): 1.Interpreting +/- signs for ΔL*, Δa*, and Δb*: Metric Meaning of Positive (+) Value Meaning of Negative (-) Value ΔL* Brighter/Whiter (The sample is lighter than the standard) Darker/Blacker (The sample is darker than the standard) Δa* Redder (More red/less green) Greener (More green/less red) Δb* Yellower (More yellow/less blue) Greener (More green/less red) Practical Example: If your colorimeter shows:  ΔL*= +0.5, Δa* = -1.2, Δb* = +0.8. Interpretation: The sample color is slightly lighter, greener, and yellower than the standard target. III.What is ΔE (Total Color Difference)? ΔE represents the total color difference. It is calculated as the straight-line distance between the sample and the standard in the 3D CIE Lab color space using the Pythagorean theorem: ΔE compresses all deviations in lightness, red/green, and yellow/blue into a single, easy-to-understand number. Global buyers and suppliers typically establish a specific ΔE limit in their contracts as the Pass/Fail threshold. ΔE Range & Human Visual Perception: ΔE 

I. Introduction In the international food trade and consumer market, as the old saying goes, "color, aroma, and taste are all essential," among which "color" ranks first. The color of liquid foods (including clarified liquids, emulsion liquids, and viscous semi-solid sauces) is not only the external manifestation of their intrinsic quality and freshness, but also the primary sensory element affecting consumers' purchasing decisions. For example, the bright orange color of orange juice represents an abundance of vitamins, the pure white color of milk reflects the emulsification stability of fat and protein, and the reddish-brown color of soy sauce directly embodies the maturity of the fermentation process.   However, during the production and storage processes, liquid foods are highly prone to color drift due to thermal processing, oxidation reactions, enzymatic browning, light exposure, and microbial activities. If there is a visible color difference between different batches of products, consumers will often suspect product spoilage or formula instability, thereby causing irreversible damage to brand trust. Traditional methods that rely on human eyes for color comparison suffer from huge subjective errors. Against this backdrop, the application of high-precision, digital colorimeters (spectrophotometers) for quantified quality control has become an important trend for the modern liquid food industry to achieve standardized, globalized, and cross-regional production. II. Core Technical Difficulties and Color Measurement Modes in Liquid Food Color Measurement Unlike solid or powdered foods, liquid foods face diversified challenges in color measurement due to their unique physical and optical characteristics, which are mainly manifested in the following aspects:   1.Transmission Measurement of Transparent Liquids: Such as liquor, clarified fruit juice, edible oil, mineral water, etc. These samples possess light permeability, and their color depends mainly on the absorption characteristics of transmitted light. Measuring this type of liquid must adopt the Transmission Mode. Through a sample cell (cuvette) with a fixed optical path, the light penetrating the liquid enters the optical detector. This type of liquid usually focuses not only on the conventional  L* a* b* color space, but also relies heavily on specific industry color indexes, such as the Platinum-Cobalt index (APHA/Pt-Co) and Gardner index used for edible oils and resins, as well as the Saybolt color scale used for certain petroleum products.   2.Dual-Mode Measurement of Turbid and Emulsion Liquids: Such as milk, yogurt, turbid fruit juice, thick soup, etc. These liquids contain a large amount of protein microparticles, fat globules, or fruit pulp fibers inside, and strong scattering and absorption will occur after light enters. If only the transmission method is used, the light cannot penetrate; if only the reflection method is used, the optical features of the internal medium cannot be captured. Therefore, these foods often require colorimeters that accommodate the Dual Mode of transmission + reflection to comprehensively evaluate their surface color and overall turbidity.   3.Non-Contact and Professional Container Measurement of High-Viscosity Semi-Solid Liquids: Such as flavoring sauces (tomato sauce, salad dressing), honey, oyster sauce, etc. These samples do not flow easily and can very easily adhere to the measurement window, causing contamination of the optical lens, which makes cleaning extremely inconvenient and may even trigger cross-contamination of food. The key to solving this difficulty lies in using colorimeters equipped with specialized testing accessories (such as liquid sample cups of specific specifications), or adopting a non-contact measurement architecture, ensuring both hygienic safety and data accuracy. III. Adaptation Solutions of CHNSpec Colorimeters in Liquid Food Color Management 1.DS-812N Series / CS-810 Benchtop Liquid Spectrophotometric Colorimeter Aiming at high-transparency liquid foods such as mineral water, liquor, edible oil, and clarified syrup, CHNSpec has launched the DS-810N and CS-810 benchtop liquid-specific colorimeters.   Optical Performance: The instruments adopt the D/0 illumination geometry condition, with built-in high-sensitivity, UV-enhanced silicon photodiodes as receivers, significantly upgrading the measurement range of transmittance to 0~200%. This ensures that even when facing liquid samples whose colors are extremely close to transparent with only subtle differences, extremely weak optical fluctuations can still be captured.   Integrated Specialized Color Indexes: They can not only directly output precise L* a* b*and  ΔE*  data, but also perfectly integrate multiple parameters universal in international food and chemical trade, such as the Platinum-Cobalt index (APHA/Pt-Co), Gardner index, yellowness, absorbance, and concentration. By eliminating the subjective randomness of manual visual eye color comparison, they provide fully traceable digital evidence for international trade. 2.CS-821N Series Advanced Benchtop Spectrophotometer Colorimeter For complex turbid, emulsion, or dark liquid foods such as milk, soy milk, thick fruit juice, rice wine, and soy sauce, the CHNSpec CS-821N benchtop spectrophotometer is the ideal choice for the industry.   Dual-Optical Path Spectrum Analysis Technology: The CS-821N adopts a high-intensity pulsed xenon lamp as the light source, cooperating with dual-optical path spectrum analysis technology, which can monitor micro-fluctuations of the light source in real time and perform automatic compensation, guaranteeing extremely high measurement repeatability (the standard deviation of spectral reflectance is within 0.08%).   Full Compatibility of Reflection + Transmission: The instrument supports the D/8 (diffused illumination geometry, 8-degree viewing) reflection mode and D/0 transmission mode, easily mastering color determination from solids and powders to various complex liquids. When measuring milk, its optical architecture can accurately distinguish the faint whiteness and yellowness differences caused by different fat contents (whole fat, low fat, skimmed) or the addition of high-calcium components; when facing soy sauce or petrochemical liquids, it can also provide color data with an extremely high signal-to-noise ratio. IV. Quality Control Process Application of Colorimeters in Liquid Food Production In actual international and local liquid food supply chains, the digital color management of CHNSpec colorimeters runs through three core links:   1.Fine Screening of Raw Materials Entering the Factory: Raw materials entering the factory, such as fruit juice puree, fresh milk, and crude vegetable oil, have base colors that are heavily influenced by origin and season. Using a colorimeter to determine their initial color data can provide a foundation for subsequent formula fine-tuning, preventing color fluctuations of raw materials from causing inconsistency in the final finished product.   2.Optimization of Processing Technology Parameters: In liquid food processes such as ultra-high temperature sterilization (UHT), evaporative concentration, and fermentation (such as soy sauce and beer brewing), excessive heating will lead to the Maillard reaction (browning), thereby deepening the product color. By periodically drawing online samples and measuring them with CHNSpec colorimeters, the heating temperature, pressure, and time can be dynamically adjusted to ensure that the process is maintained in the optimal golden zone.   3.Finished Product Out-of-Factory and Shelf-Life Consistency Assurance: When products are sold to different supermarkets and shelves around the world, a visually uniform color can tremendously establish a high-end, rigorous brand image. Colorimeters can also be used for simulated shelf-life testing, monitoring the impact of light and temperature on the color of food inside liquid packaging, and providing objective quantified data for the improvement of light-shielding and oxygen-barrier properties of packaging materials. V. Conclusion Today, with increasingly strict international food trade access and consumers' more and more demanding requirements for quality, traditional eye color evaluation can no longer meet the needs of the high-end food manufacturing industry in foreign trade. The colorimeter converts abstract, person-dependent visual sensory experiences into universal digital assets of international standards.   The multiple models of precision spectrophotometric colorimeters provided by CHNSpec, including the DS-812N series, CS-810, and CS-821N series, by virtue of their dual-optical path analysis technology, ultra-wide transmission range, and deeply integrated multi-industry specialized color indexes, have constructed a scientific, rigorous, and traceable modern color quality control system for liquid food enterprises. Introducing high-precision colorimeters can not only effectively control the defective rate and save raw materials, but also significantly enhance the core competitiveness of brands in the international market, making every bottle opening a perfect feast of vision and taste.

In the leaf quality evaluation system, oil content is one of the important indicators to measure the quality of flue-cured tobacco. Traditionally, oil content evaluation mainly relies on the empirical judgment of professionals, which has problems such as strong subjectivity and relatively low efficiency. In recent years, hyperspectral imaging technology, due to its characteristics of combining graphs and spectra, has demonstrated application potential in the field of agricultural product quality detection. Taking a study on flue-cured tobacco oil content detection as an example, this paper introduces the practical application effect of visible-near-infrared hyperspectral technology in this scenario. Research Background and Experimental DesignThe study selected 634 flue-cured tobacco leaf samples from 22 tobacco-growing provinces (autonomous regions) across the country, covering upper, middle, and lower parts. The research team used the FigSpec series hyperspectral imaging system from CHNSpec (including FigSpec-23 and FigSpec-25 cameras) to synchronously collect the spectral information of tobacco leaves in the wavelength ranges of 400-1000nm and 900-1700nm. During the collection process, by fixing the light source angle and camera distance, illumination uniformity was ensured, and the average value after collecting spectral data twice for each sample was used as the original input. The oil content score was independently evaluated on a 10-point scale by an appearance quality evaluation team consisting of 20 people. The samples were divided into a calibration set (443 samples) and a validation set (191 samples) at a ratio of 7:3. The distribution characteristics of oil content scores in the two sets of samples were consistent with the overall population, providing a reliable foundation for subsequent model construction. Spectral Preprocessing and Correlation AnalysisThe original spectral data contains noise and scattering interference, requiring preprocessing to enhance effective signals. The study compared five single preprocessing methods, including moving average smoothing (MA), multiplicative scatter correction (MSC), standard normal variate (SNV), first derivative (D1), and standardization (SS), as well as their combination strategies. The analysis results showed that MSC and SNV preprocessing could effectively improve the correlation between spectral reflectance and oil content scores. In the wavelength range of 928.36-1177.03nm, the correlation coefficient increased from 0.076-0.124 of the original spectrum to 0.331-0.640. D1 preprocessing, by strengthening the local variation features of the spectral curves, made the number of strongly correlated bands (|r|≥0.4) exceed 100. These results indicate that reasonable preprocessing strategies help to improve the predictive capacity of subsequent models. Model Construction and Performance EvaluationThe study used two algorithms, partial least squares regression (PLSR) and support vector regression (SVR), to construct quantitative prediction models for oil content scores. The PLSR model based on the full visible-near-infrared band had validation set RPD values between 1.642 and 1.775 under most preprocessing conditions, among which the validation set R² reached 0.683 and the RMSE was 0.346 after MA preprocessing. The SVR model had a validation set R² of 0.653 and an RMSE of 0.362 under the D1+SS combination preprocessing. To merge the advantages of both models, the study introduced a weighted average fusion strategy. The fusion model based on the full visible-near-infrared band (PLSR under MA preprocessing and SVR under D1+SS preprocessing) saw its validation set R² increase to 0.721, RMSE drop to 0.324, and RPD reach 1.894, showing a better prediction effect than any single model. Characteristic Band Selection and Model OptimizationHyperspectral data contains hundreds of bands, presenting data redundancy problems. The study adopted the successive projections algorithm (SPA) for characteristic band selection. The results showed that after MA preprocessing, the PLSR model constructed with 95 characteristic bands selected by SPA had a validation set R² of 0.685 and an RMSE of 0.345; after D1+SS preprocessing, the SVR model constructed with 56 characteristic bands selected by SPA had a validation set R² of 0.666 and an RMSE of 0.355. The number of characteristic bands was significantly reduced from 428 in the full band, drastically lowering the data dimensionality. The fusion model of PLSR and SVR based on SPA selection further improved the prediction accuracy, with the validation set R² reaching 0.724, RMSE at 0.323, and RPD at 1.904. This result indicates that characteristic band selection maintains model validity while reducing data redundancy. Application OutlookThis study demonstrates the feasibility of visible-near-infrared hyperspectral technology in the non-destructive detection of flue-cured tobacco oil content. Compared with traditional manual evaluation methods, hyperspectral technology has potential advantages of objectivity, non-destructiveness, and speed, which can provide reference bases for the development of automatic tobacco leaf grading equipment and the construction of intelligent quality control systems. The FigSpec series hyperspectral imaging system from CHNSpec undertook the core data collection task in this study, verifying its applicability in agricultural material quality detection scenarios.