News Release

Non-destructive method developed for detecting internal cracks in rice seeds

Peer-Reviewed Publication

Hefei Institutes of Physical Science, Chinese Academy of Sciences

Non-Destructive Method Developed for Detecting Internal Cracks in Rice Seeds


A seed with internal cracks as detected by near-infrared spectroscopy

view more 

Credit: WANG Liusan

Recently, a team led by Prof. WANG Rujing and WANG Liusan from the Hefei Institutes of Physical Science of the Chinese Academy of Sciences, developed a method to detect internal cracks in rice seeds using near-infrared spectroscopy.

"Cracks can affect the germination rate of seeds," said Wang Liusan, "Our study can help select high-quality seeds with non-destructive method."

The research results were published in Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy.

In agricultural production, the quality of rice seeds is directly related to the yield and quality of crops. However, cracks inside rice seeds are often difficult to identify with the naked eye, which poses a challenge for evaluating the quality of rice seeds.

In this study, researchers developed a non-destructive method for detecting internal cracks in rice seeds using near infrared spectroscopy. They applied machine learning classification algorithms, combined with spectral preprocessing methods to establish models. The performance of the models was compared to obtain the optimal model.

The results indicate that the combination of partial least squares discrimination and the original spectral data model is the most effective. While the best support vector machine model performed poorly, it still outperformed the random forest and k-nearest neighbor models. Analysis of wavelength importance revealed that the key variables for detecting internal cracks in rice seeds are related to amylose content.

The application of this technology not only improves the efficiency and accuracy of rice seed quality assessment, but also provides new technological means for seed quality control in agricultural production, according to the team.

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.