Luo Junli, Lu Kai, Chen Yonggang, Zhang Boping
College of Information Engineering, Xuchang University, Xuchang, Henan, China; Xuchang Key Laboratory of Virtual Reality Technology, Xuchang, Henan, China.
College of Information Engineering, Xuchang University, Xuchang, Henan, China; Xuchang Key Laboratory of Virtual Reality Technology, Xuchang, Henan, China.
Micron. 2021 Apr;143:103023. doi: 10.1016/j.micron.2021.103023. Epub 2021 Jan 27.
Distinguishing cashmere and sheep wool fibers is a challenge. In this study, we propose a residual net-based method for the identification of cashmere and sheep wool fibers. First, optical microscopic images of six different types of cashmere and sheep wool fibers were collected, and then the sample images were data-augmented. Several classic convolutional neural network (CNN) models were trained and tested with the sample images. The comparison showed that the proposed residual net model with 18 weight layers had the highest accuracy, with an overall accuracy above 97.1 % on the test set; the highest accuracy on the Australian merino wool and Mongolian brown cashmere, both above 98 %; and the lowest accuracy on the Chinese white cashmere, above 95 %. The trained model exhibited a fast detection speed, processing 6000 sample images in less than 20 s.
区分羊绒纤维和羊毛纤维是一项挑战。在本研究中，我们提出了一种基于残差网络的方法来识别羊绒纤维和羊毛纤维。首先，收集了六种不同类型的羊绒纤维和羊毛纤维的光学显微镜图像，然后对样本图像进行数据增强。使用样本图像对几种经典的卷积神经网络（CNN）模型进行了训练和测试。比较结果表明，所提出的具有18个权重层的残差网络模型具有最高的准确率，在测试集上的总体准确率高于97.1%；对澳大利亚美利奴羊毛和蒙古棕色羊绒的准确率最高，均高于98%；对中国白绒的准确率最低，高于95%。训练后的模型检测速度快，在不到20秒的时间内处理了6000张样本图像。
