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

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

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) + digit...

Full description

Bibliographic Details
Main Authors: Wei Wei, Dexiang Deng, Lin Zeng, Chen Zhang, Wenxuan Shi
Format: Article
Language:English
Published: SAGE Publishing 2019-08-01
Series:International Journal of Advanced Robotic Systems
Online Access:https://doi.org/10.1177/1729881419867600
id doaj-2226641e0af94d2db5633af37697d9e5
record_format Article
spelling doaj-2226641e0af94d2db5633af37697d9e52020-11-25T03:52:31ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88142019-08-011610.1177/1729881419867600Classification of foreign fibers using deep learning and its implementation on embedded systemWei Wei0Dexiang Deng1Lin Zeng2Chen Zhang3Wenxuan Shi4 School of Electronic Information, Wuhan University, Wuhan, China School of Electronic Information, Wuhan University, Wuhan, China School of Electronic Information, Wuhan University, Wuhan, China School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan, China School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaIn 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.https://doi.org/10.1177/1729881419867600
collection DOAJ
language English
format Article
sources DOAJ
author Wei Wei
Dexiang Deng
Lin Zeng
Chen Zhang
Wenxuan Shi
spellingShingle Wei Wei
Dexiang Deng
Lin Zeng
Chen Zhang
Wenxuan Shi
Classification of foreign fibers using deep learning and its implementation on embedded system
International Journal of Advanced Robotic Systems
author_facet Wei Wei
Dexiang Deng
Lin Zeng
Chen Zhang
Wenxuan Shi
author_sort Wei Wei
title Classification of foreign fibers using deep learning and its implementation on embedded system
title_short Classification of foreign fibers using deep learning and its implementation on embedded system
title_full Classification of foreign fibers using deep learning and its implementation on embedded system
title_fullStr Classification of foreign fibers using deep learning and its implementation on embedded system
title_full_unstemmed Classification of foreign fibers using deep learning and its implementation on embedded system
title_sort classification of foreign fibers using deep learning and its implementation on embedded system
publisher SAGE Publishing
series International Journal of Advanced Robotic Systems
issn 1729-8814
publishDate 2019-08-01
description 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.
url https://doi.org/10.1177/1729881419867600
work_keys_str_mv AT weiwei classificationofforeignfibersusingdeeplearninganditsimplementationonembeddedsystem
AT dexiangdeng classificationofforeignfibersusingdeeplearninganditsimplementationonembeddedsystem
AT linzeng classificationofforeignfibersusingdeeplearninganditsimplementationonembeddedsystem
AT chenzhang classificationofforeignfibersusingdeeplearninganditsimplementationonembeddedsystem
AT wenxuanshi classificationofforeignfibersusingdeeplearninganditsimplementationonembeddedsystem
_version_ 1724482511274246144

Similar Items