Liu Fan, Wang Fang, Zhang Zaiqi, Cao Liang, Wu Jinran, Wang You-Gan
Hunan Provincial Key Laboratory of Dong Medicine, Hunan University of Medicine, Huaihua, China.
Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education and Hunan Key Laboratory for Computation and Simulation in Science and Engineering, Xiangtan University, Xiangtan, China.
Front Genet. 2025 Jan 15;15:1518205. doi: 10.3389/fgene.2024.1518205. eCollection 2024.
Due to its favorable traits-such as lower lignin content, higher oil concentration, and increased protein levels-the genetic improvement of yellow-seeded rapeseed has attracted more attention than other rapeseed color variations. Traditionally, yellow-seeded rapeseed has been identified visually, but the complex variability in the seed coat color of has made manual identification challenging and often inaccurate. Another method, using the RGB color system, is frequently employed but is sensitive to photographic conditions, including lighting and camera settings.
We present four data-driven models to identify yellow-seeded using hyperspectral features combined with simple yet intelligent techniques. One model employs partial least squares regression (PLSR) to predict the R, G, and B color channels, effectively distinguishing yellow-seeded varieties from others according to globally accepted yellow-seed classification protocols. Another model uses logistic regression (Logit-R) to produce a probability-based assessment of yellow-seeded status. Additionally, we implement two intelligent models, random forest and support vector classifier to evaluate features selected through lasso-penalized logistic regression.
Our findings indicate significant recognition accuracies of 96.55% and 98% for the PLSR and Logit-R models, respectively, aligning closely with the accuracy of previous methods. This approach represents a meaningful advancement in identifying yellow-seeded rapeseed, with high recognition accuracy demonstrating the practical applicability of these models.
由于其具有诸如较低木质素含量、较高油浓度和增加的蛋白质水平等有利特性，黄籽油菜籽的遗传改良比其他油菜籽颜色变异更受关注。传统上，黄籽油菜籽是通过目视识别的，但种皮颜色的复杂变异性使得人工识别具有挑战性且往往不准确。另一种方法，即使用RGB颜色系统，经常被采用，但对包括光照和相机设置在内的拍摄条件敏感。
我们提出了四种数据驱动模型，利用高光谱特征结合简单而智能的技术来识别黄籽油菜籽。一种模型采用偏最小二乘回归（PLSR）来预测R、G和B颜色通道，根据全球公认的黄籽分类协议有效地将黄籽品种与其他品种区分开来。另一种模型使用逻辑回归（Logit-R）来对黄籽状态进行基于概率的评估。此外，我们还实现了两种智能模型，随机森林和支持向量分类器，以评估通过套索惩罚逻辑回归选择的特征。
我们的研究结果表明，PLSR和Logit-R模型的识别准确率分别达到了96.55%和98%，与先前方法的准确率密切相关。这种方法在识别黄籽油菜籽方面代表了一项有意义的进步。高识别准确率证明了这些模型的实际适用性。
