CM-YOLO: A Multimodal PCB Defect Detection Method Based on Cross-Modal Feature Fusion

By integrating information from RGB images and depth images, the feature perception capability of a defect detection algorithm can be enhanced, making it more robust and reliable in detecting subtle defects on printed circuit boards. On this basis, inspired by the concept of differential amplificati...

Full description

Saved in:
Bibliographic Details
Main Authors: Haowen Lan, Jiaxiang Luo, Hualiang Zhang, Xu Yan
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/13/4108
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849320897171685376
author Haowen Lan
Jiaxiang Luo
Hualiang Zhang
Xu Yan
author_facet Haowen Lan
Jiaxiang Luo
Hualiang Zhang
Xu Yan
author_sort Haowen Lan
collection DOAJ
description By integrating information from RGB images and depth images, the feature perception capability of a defect detection algorithm can be enhanced, making it more robust and reliable in detecting subtle defects on printed circuit boards. On this basis, inspired by the concept of differential amplification, we propose a novel and general weighted feature fusion method within the YOLO11 dual-stream detection network framework, which we name CM-YOLO. Based on the differential amplification approach, we introduce a Differential Amplification Weighted Fusion (DAWF) module, which separates multimodal features into common-mode and differential-mode features to preserve and enhance modality-specific characteristics. Then, the SE-Weighted Fusion module is used to fuse the common-mode and differential-mode features.In addition, we introduce a Cross-Attention Spatial and Channel (CASC) module into the detection network to enhance feature extraction capability. Extensive experiments show that the proposed CM-YOLO method achieves a mean Average Precision (mAP) of 0.969, demonstrating the accuracy and effectiveness of CM-YOLO.
format Article
id doaj-art-df439953abdb4f1a8ffbd26a389ada7d
institution Kabale University
issn 1424-8220
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-df439953abdb4f1a8ffbd26a389ada7d2025-08-20T03:49:55ZengMDPI AGSensors1424-82202025-06-012513410810.3390/s25134108CM-YOLO: A Multimodal PCB Defect Detection Method Based on Cross-Modal Feature FusionHaowen Lan0Jiaxiang Luo1Hualiang Zhang2Xu Yan3School of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, ChinaSchool of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, ChinaSchool of Software Engineering, South China University of Technology, Guangzhou 510640, ChinaSchool of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, ChinaBy integrating information from RGB images and depth images, the feature perception capability of a defect detection algorithm can be enhanced, making it more robust and reliable in detecting subtle defects on printed circuit boards. On this basis, inspired by the concept of differential amplification, we propose a novel and general weighted feature fusion method within the YOLO11 dual-stream detection network framework, which we name CM-YOLO. Based on the differential amplification approach, we introduce a Differential Amplification Weighted Fusion (DAWF) module, which separates multimodal features into common-mode and differential-mode features to preserve and enhance modality-specific characteristics. Then, the SE-Weighted Fusion module is used to fuse the common-mode and differential-mode features.In addition, we introduce a Cross-Attention Spatial and Channel (CASC) module into the detection network to enhance feature extraction capability. Extensive experiments show that the proposed CM-YOLO method achieves a mean Average Precision (mAP) of 0.969, demonstrating the accuracy and effectiveness of CM-YOLO.https://www.mdpi.com/1424-8220/25/13/4108PCB defect detectionmultimodalfeature fusion
spellingShingle Haowen Lan
Jiaxiang Luo
Hualiang Zhang
Xu Yan
CM-YOLO: A Multimodal PCB Defect Detection Method Based on Cross-Modal Feature Fusion
Sensors
PCB defect detection
multimodal
feature fusion
title CM-YOLO: A Multimodal PCB Defect Detection Method Based on Cross-Modal Feature Fusion
title_full CM-YOLO: A Multimodal PCB Defect Detection Method Based on Cross-Modal Feature Fusion
title_fullStr CM-YOLO: A Multimodal PCB Defect Detection Method Based on Cross-Modal Feature Fusion
title_full_unstemmed CM-YOLO: A Multimodal PCB Defect Detection Method Based on Cross-Modal Feature Fusion
title_short CM-YOLO: A Multimodal PCB Defect Detection Method Based on Cross-Modal Feature Fusion
title_sort cm yolo a multimodal pcb defect detection method based on cross modal feature fusion
topic PCB defect detection
multimodal
feature fusion
url https://www.mdpi.com/1424-8220/25/13/4108
work_keys_str_mv AT haowenlan cmyoloamultimodalpcbdefectdetectionmethodbasedoncrossmodalfeaturefusion
AT jiaxiangluo cmyoloamultimodalpcbdefectdetectionmethodbasedoncrossmodalfeaturefusion
AT hualiangzhang cmyoloamultimodalpcbdefectdetectionmethodbasedoncrossmodalfeaturefusion
AT xuyan cmyoloamultimodalpcbdefectdetectionmethodbasedoncrossmodalfeaturefusion