Lightweight Single Shot Multi-Box Detector: A fabric defect detection algorithm incorporating parallel dilated convolution and dual channel attention

计算机科学 卷积(计算机科学) 探测器 算法 卷积神经网络 频道(广播) 特征(语言学) 特征提取 人工智能 噪音(视频) 模式识别(心理学) 人工神经网络 图像(数学) 电信 语言学 哲学 计算机网络
作者
Shuhan Liu,Limin Huang,Yingbao Zhao,Xiaojing Wu
出处
期刊:Textile Research Journal [SAGE Publishing]
卷期号:94 (1-2): 209-224 被引量:9
标识
DOI:10.1177/00405175231202817
摘要

For the textile industry, fabric defect detection is an important part of production. In order to make the automatic fabric defect detection system used in production sites, this article proposes a lightweight algorithm Lightweight Single Shot Multi-Box Detector (LW-SSD) to address the issues of low detection accuracy, high computational complexity, and difficulty in deploying on hardware devices with limited computing power in fabric defect detection. Firstly, MobileNetv3 is introduced as the backbone network to reduce the number of model parameters. Secondly, in the feature fusion module, down-sampling stacking is used to fuse the feature maps processed by maximum pooling and regular 3 × 3 convolution, respectively, to enhance the generalization and small target feature extraction capability of the network. Then, the dilated convolution is incorporated into the Inceptionv3 to form a multi-branch parallel dilated convolution module, which can expand the receptive field of the feature layer and enhance the extraction of the target information. Finally, a dual-channel attention module is added, which adds the maximum pooling operation based on the efficient channel attention for deep convolutional neural networks (ECA) channel attention mechanism to highlight defect features and suppress background noise features. The experiments show that the accuracy of the system is improved while maintaining the faster detection speed. Among them, the LW-SSD algorithm has an accuracy improvement of 10.03% on the self-made dataset, a reduction of 58% in the number of model parameters compared to the Single Shot Multi-Box Detector (SSD) algorithm, and the detection speed reaches 48 frames per second.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
大个应助勤恳的夏之采纳,获得10
刚刚
欣慰薯片完成签到,获得积分10
刚刚
一如果一完成签到,获得积分10
1秒前
1秒前
北城发布了新的文献求助10
2秒前
练习时长两年半应助全齐采纳,获得10
2秒前
爱宝乐宝福宝应助高梦雪采纳,获得20
2秒前
2秒前
4秒前
4秒前
4秒前
plasma发布了新的文献求助10
5秒前
领导范儿应助澡雪采纳,获得10
5秒前
NexusExplorer应助万晓博采纳,获得10
5秒前
6秒前
归尘发布了新的文献求助30
6秒前
6秒前
干冷安发布了新的文献求助10
7秒前
8秒前
9秒前
9秒前
Barney发布了新的文献求助10
9秒前
10秒前
10秒前
mx发布了新的文献求助10
10秒前
123发布了新的文献求助10
12秒前
lyc45491314发布了新的文献求助20
12秒前
700w完成签到 ,获得积分0
12秒前
量子星尘发布了新的文献求助10
12秒前
13秒前
汉堡包应助无奈的老姆采纳,获得10
16秒前
gu发布了新的文献求助10
16秒前
情怀应助WJ采纳,获得10
17秒前
隐形曼青应助fuje采纳,获得10
17秒前
Cech发布了新的文献求助10
17秒前
dong应助冬冬采纳,获得10
17秒前
充电宝应助震动的又槐采纳,获得10
17秒前
FashionBoy应助mx采纳,获得10
18秒前
18秒前
18秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Effective Learning and Mental Wellbeing 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3975836
求助须知:如何正确求助?哪些是违规求助? 3520174
关于积分的说明 11201364
捐赠科研通 3256576
什么是DOI,文献DOI怎么找? 1798362
邀请新用户注册赠送积分活动 877539
科研通“疑难数据库(出版商)”最低求助积分说明 806426