Classification of foreign fibers using deep learning and its implementation on embedded system

Dexiang Deng,Wei Wei,Chen Zhang,Lin Zeng,Wenxuan Shi

doi:10.1177/1729881419867600

Abstract

In recent years, the foreign fibers in cotton lint significantly affect the quality of the final cotton textile products. It remains a challenging task to accurately distinguish foreign fibers from cotton. This article proposes an embedded system based on field programmable gate array (FPGA) + digital signal processor (DSP) to recognize and remove foreign fibers mixed in cotton. With substantial tests of this system, we collect massive samples of foreign fibers and fake foreign fibers. Based on these samples, a convolution neural network mode is developed to validate the classification of the suspected targets from the detection subsystem, to improve the detection reliability. After training several model architectures, we find a model with the best balance between performance and computation. The high success rate (up to 96% in the validation set) demonstrates the effectiveness of the model. Moreover, the computation time (5 ms on a single image based on an eight-core DSP) indicates the efficiency of the detection, which ensures the real-time application of the system.

Highlights

The foreign fibers include hair, ropes, plastic film, polypropylene twines, and so on which can seriously affect the quality of the final cotton textile products
A single personal computer (PC) was used for the entire process of training and testing the foreign fiber classification model described in this article
We develop a foreign fiber sorting system based on digital signal processor (DSP) and field programmable gate array (FPGA)

Summary

Introduction

The foreign fibers include hair, ropes, plastic film, polypropylene twines, and so on which can seriously affect the quality of the final cotton textile products. How to accurately identify and eliminate the foreign fibers mixed in raw cotton is one of the most concerned focuses in the textile industry. Based on the optical detection principle, computer vision techniques have the advantages of low cost, fine consistency, superior speed, good objectiveness, and high accuracy.[1,2] The working environment of the foreign fiber machine is usually high temperature, high humidity, and high dust, which means that very rigorous industrial standards are required for the foreign fiber machine, such as low power consumption and high reliability. The detection of different fibers requires real-time and stable work, so the calculation time of each

Methods

Results

Conclusion