FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets

Fabric is a planar material composed of textile fibers. Textile fibers are generated from many natural sources; including plants, animals, minerals, and even, it can be synthetic. A particular fabric may contain different types that pass through complex production process. Fiber identification usually carried out chemical tests microscopic tests. However, these testing processes complicated as well time-consuming. We propose FabricNet, pioneering approach for the image-based fiber recognition system, which have revolutionary impact individual to industrial The FabricNet recognize large scale by only utilizing surface image fabric. system constructed using distinct category class-based ensemble convolutional neural network (CNN) architecture. experiment conducted on recognizing 50 This includes significantly number unique than previous research endeavors best our knowledge. with popular CNN architectures include Inception, ResNet, VGG, MobileNet, DenseNet, Xception. Finally, experimental results demonstrate outperforms state-of-the-art reaching an accuracy 84% F1-score 90%.