Rapid construction method for a precision pork color scoring model based on standard color board images

文献类型： 外文期刊

第一作者： Xiao, Dongsheng

作者： Xiao, Dongsheng;Gu, Jiabing;Li, Yongkang;Zhao, Sanqin;Liu, Yutao;Chao, Zhe;Yang, Wen;Men, Zi;Zha, Chengwan;Wu, Wangjun

作者机构：

期刊名称：NPJ SCIENCE OF FOOD （ 影响因子：7.8； 五年影响因子：7.0 ）

ISSN：

年卷期： 2025 年 9 卷 1 期

页码：

收录情况： SCI

摘要： This study addresses the challenges of large sample size dependency and sample imbalance in traditional pork color scoring models. We propose a rapid method for constructing an accurate color scoring model using six standard color board images and compare its performance with traditional models based on 525 real pork samples from seven pig herds. The results show that the classification accuracy of the CS_1 models, after intercept calibration with mixed herd images, is comparable to traditional models. Specifically, accuracies for CS_1_L, CS_1_La*, and CS_1_Lab models within a +/- 0.50 scale are 91.43%, 95.62%, and 94.10%, respectively. Calibration using individual herd images significantly improves accuracy, with CS_1_L, CS_1_La*, and CS_1_Lab* models achieving accuracies of 93.75%, 95.90%, and 96.10%, respectively. This method offers advantages such as small sample sizes and rapid intercept calibration, providing a new approach for objective pork color assessment.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序