«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

期数:

2025年02期

页码:

9-15

栏目:

媒体计算

出版日期:

2025-02-10

文章信息/Info

Title:

Fabric Defect Detection Algorithm Based on Adaptive Spatial Feature Fusion

文章编号:

1673-629X(2025)02-0009-07

作者:

吴梦微1; 毋涛2; 崔青1

1. 西安工程大学 计算机科学学院,陕西 西安 710048;

2. 西安工程大学 计算机科学学院 纺织服装智能信息服务研究所,陕西 西安 710048

Author(s):

WU Meng-wei1; WU Tao2; CUI Qing1

1. School of Computer Science,Xi’an Polytechnic University,Xi’an 710048,China;

2. Textile and Apparel Intelligent Information Service Research Institute,School of Computer Science,Xi’an Polytechnic University,Xi’an 710048,China

关键词:

织物疵点检测; YOLOv7; 自适应空间; 注意力机制; 特征融合

Keywords:

fabric defect detection; YOLOv7; adaptive space; attention mechanism; feature fusion

分类号:

TP391.41;TS101.9

DOI:

10.20165/j.cnki.ISSN1673-629X.2024.0318

摘要:

对于织物疵点检测通常耗时、背景复杂、疵点种类多样且依赖人工操作的问题,提出了一种基于改进 YOLOv7 算法的轻量级检测方法。 首先,增加了一个检测头 Swin-Transformer,增强模型捕获和识别小目标特征的能力;其次,在主干特征提取阶段加入卷积注意力融合的注意力机制 ACmix,使得模型可以自动学习并集中注意力在与小目标相关的区域或特征上,增加对重要特征信息的捕捉;采用自适应空间特征融合的方式,增强了多尺度特征融合能力;最后,使用 Wasstertein 距离优化损失函数,降低了模型对小目标的敏感度。 通过对构建的含有 6 种疵点的面料数据集进行测试可以看出,模型 ASFF-YOLOv7 的检测精度 mAP 达到 94% 、帧率达到 50. 92 帧/ s,与其他 8 种算法相比,ASFF-YOLOv7 的综合性能最优。

Abstract:

To address the issues commonly associated with fabric defect detection, such as time - consuming processes, complex backgrounds,diverse types of defects, and reliance on manual operations, we propose a lightweight detection method based on an improved YOLOv7 algorithm. Initially,a detection head,Swin -Transformer,is added to enhance the model’s ability to capture and recognize features of small objects. Subsequently,a convolutional attention fusion mechanism,ACmix,is integrated during the backbone feature extraction phase, enabling the model to autonomously learn and focus on areas or features related to small objects, thereby enhancing the capture of crucial feature information. Adaptive spatial feature fusion is employed to bolster multi - scale feature integration. Finally,the Wasserstein distance is used to optimize loss function and reduce the sensitivity to small objects. Testing on a constructed fabric dataset containing six types of defects demonstrates that the ASFF-YOLOv7 achieves the highest detection accuracy and the fastest speed next to YOLOv7 in the dataset. Compared to the original algorithm,the proposed method achieves an accuracy rate of 94% and a frame rate of 50. 92 frames per second.

常用功能

更新日期/Last Update: 2025-02-10