A Novel VBM Framework of Fiber Recognition Based on Image Segmentation and DCNN

Manual approaches of fiber recognition are often time-consuming, laborious, and subjective. In this paper, a novel vision-based measurement (VBM) framework of fiber recognition based on image segmentation and deep convolutional neural networks (DCNNs) is proposed. The proposed segmentation method can be applied to the segmentation of overlapping and adhering translucent fibers and has better segmentation performance. At the same time, the segmentation method provides a large number of single-fiber training samples and test samples for DCNN and provides a basis for multifiber map recognition using voting strategies. Finally, four frequently used kinds of fibers, i.e., cotton, camel hair, viscose, and yak cashmere, are selected for experiments. In order to decrease the chance of overfitting, the data augmentation methods are utilized to enlarge the data sets formed by the segmented single-fiber images. In the experimental phase, performance differences are evaluated between the four network architectures, namely, AlexNet, cashmere and wool classification-Net, VGG-Net-16, and GoogLeNet. The GoogLeNet's single-fiber classification accuracy rate reaches 96.6%, and the average accuracy rate of multifiber identification strategy reaches 99.5%. The results show that the proposed VBM framework of fiber recognition is effective.