CHNSpec Technology (Zhejiang)Co.,Ltd chnspec@colorspec.cn 86--13732210605
As an important cash crop, pumpkin seed vitality is directly related to the emergence rate, seedling growth potential and final yield after sowing. The traditional methods of seed vitality detection, such as germination test, are time-consuming and laborious, and can not meet the needs of rapid and large-scale seed quality detection in modern agriculture. Hyperspectral imaging technology combines the advantages of spectroscopy and imaging, and can obtain the spectral information and spatial information of samples at the same time, which shows great potential in the field of seed viability nondestructive testing.
一、Preparation of experimental materials
Divide the pumpkin seeds into 4 groups of 100 seeds and place them in a nylon mesh bag, as shown in Figure 3-2. Put a group of pumpkin seeds in the dryer every other day. The specific procedure is as follows: take out 3 groups of samples, put the first group of samples in the dryer, put the second group of samples in the dryer 24 hours later, put the third group of samples in the dryer 24 hours later, and take out all the samples with aging time of 1 to 3 days respectively after 3 days (the first group is the samples with aging time of 3 days). Group 2 is for samples aged for 2 days, and Group 3 is for samples aged for 1 day). The remaining 1 of the 4 groups was not subjected to aging treatment and was placed at room temperature for 3 days during the aging group experiment.
二、Hyperspectral data acquisition
Seeds with different aging days were collected by a color spectrum hyperspectral camera, and hyperspectral images of 400-1000nm were taken for all samples. After the spectral data were extracted, a total of 400 spectral curves were obtained, as shown in the figure.
Observe the growth every day, and pour the right amount of water to ensure the water needed for germination. The germination was recorded once on the third and fifth days respectively. The following is the pre-germination test diagram of pumpkin seeds.
According to the vitality level of each seed, the average spectral data of each seed was classified, and the overall spectral curve of each grade was shown in the figure below.
三、Spectral data processing
The original hyperspectral image is susceptible to noise and uneven illumination. Median filter is adopted to remove salt and pepper noise, and the illumination difference is eliminated based on the reflectivity correction of the standard whiteboard. The region of interest (ROI) is extracted from the corrected image, focusing on the seed embryo and endosperm to ensure the accuracy of subsequent feature extraction. Dimensionality reduction methods such as principal component analysis (PCA) are used to compress data initially, retain key information and reduce computation.
四、Conclusion and Prospect
In this study, a pumpkin seed vitality detection model based on hyperspectral imaging technology was successfully constructed to realize rapid, non-destructive and high-precision vitality identification, and provide an efficient technical solution for the quality control of pumpkin seed industry. Follow-up research can be extended to more crop seeds, and multi-modal data (such as fluorescence spectrum, thermal imaging, etc.) can be integrated to further improve the detection accuracy in complex environments. Combined with Internet of Things technology, an online monitoring system for seed vitality can be built to help real-time control and accurate screening of seed quality in smart agriculture.