1
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Detection of surface defect on flexible printed circuit via guided box improvement in GA-Faster-RCNN network

      research-article
      1 , 1 , 1 , 2 , 3 , * ,
      PLOS ONE
      Public Library of Science

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Industrial defect detection is a critical aspect of production. Traditional industrial inspection algorithms often face challenges with low detection accuracy. In recent years, the adoption of deep learning algorithms, particularly Convolutional Neural Networks (CNNs), has shown remarkable success in the field of computer vision. Our research primarily focused on developing a defect detection algorithm for the surface of Flexible Printed Circuit (FPC) boards. To address the challenges of detecting small objects and objects with extreme aspect ratios in FPC defect detection for surface, we proposed a guided box improvement approach based on the GA-Faster-RCNN network. This approach involves refining bounding box predictions to enhance the precision and efficiency of defect detection in Faster-RCNN network. Through experiments, we verified that our designed GA-Faster-RCNN network achieved an impressive accuracy rate of 91.1%, representing an 8.5% improvement in detection accuracy compared to the baseline model.

          Related collections

          Most cited references15

          • Record: found
          • Abstract: found
          • Article: not found

          Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

          State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features-using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model [3], our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.
            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found
            Is Open Access

            Detection of PCB Surface Defects With Improved Faster-RCNN and Feature Pyramid Network

              Bookmark
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              Directly Printed Embedded Metal Mesh for Flexible Transparent Electrode via Liquid Substrate Electric‐Field‐Driven Jet

              Flexible transparent electrodes (FTEs) with embedded metal meshes play an indispensable role in many optoelectronic devices due to their excellent mechanical stability and environmental adaptability. However, low‐cost, simple, efficient, and environmental friendly integrated manufacturing of high‐performance embedded metal meshes remains a huge challenge. Here, a facile and novel fabrication method is proposed for FTEs with an embedded metal mesh via liquid substrateelectric‐field‐driven microscale 3D printing process. This direct printing strategy avoids tedious processes and offers low‐cost and high‐volume production, enabling the fabrication of high‐resolution, high‐aspect ratio embedded metal meshes without sacrificing transparency. The final manufactured FTEs with 80 mm × 80 mm embedded metal mesh offers excellent optoelectronic performance with a sheet resistance ( R s ) of 6 Ω sq −1 and a transmittance ( T ) of 85.79%. The embedded metal structure still has excellent mechanical stability and good environmental suitability under different harsh working conditions. The practical feasibility of the FTEs is successfully demonstrated with a thermally driven 4D printing structure and a resistive transparent strain sensor. This method can be used to manufacture large areas with facile, high‐efficiency, low‐cost, and high‐performance FTEs. A facile fabrication method for flexible transaprent electrodes (FTEs) with embedded metal mesh is proposed by using liquid substrate electric‐field‐driven (LS‐EFD) microscale 3D printing process. The fabricated FTEs exhibit excellent photoelectric properties, remarkable mechanical stability and environmental adaptability. The practical feasibility of the FTEs is successfully demonstrated with a thermal‐driven 4D printing structure and a resistive transparent strain sensor.
                Bookmark

                Author and article information

                Contributors
                Role: Funding acquisitionRole: MethodologyRole: Project administrationRole: SupervisionRole: Writing – original draftRole: Writing – review & editing
                Role: MethodologyRole: ValidationRole: VisualizationRole: Writing – original draftRole: Writing – review & editing
                Role: Data curationRole: MethodologyRole: SoftwareRole: Validation
                Role: MethodologyRole: Project administrationRole: SupervisionRole: Writing – review & editing
                Role: Editor
                Journal
                PLoS One
                PLoS One
                plos
                PLOS ONE
                Public Library of Science (San Francisco, CA USA )
                1932-6203
                2023
                5 December 2023
                : 18
                : 12
                : e0295400
                Affiliations
                [1 ] College of Big Data and Internet, Shenzhen Technology University, Shenzhen, Guang Dong, China
                [2 ] School of Electronics and Communication Engineering, Shenzhen Polytechnic University, Shenzhen, Guang Dong, China
                [3 ] School of Integrated Circuits, Shenzhen Polytechnic University, Shenzhen, Guang Dong, China
                VIT-AP Campus, INDIA
                Author notes

                Competing Interests: The authors have declared that no competing interests exist.

                Author information
                https://orcid.org/0000-0003-3188-9060
                https://orcid.org/0009-0007-1882-1527
                https://orcid.org/0009-0006-2813-8118
                Article
                PONE-D-23-23019
                10.1371/journal.pone.0295400
                10697535
                38051736
                c9e7a32a-fea3-4f14-acff-2d0e9a1efd24
                © 2023 Shen et al

                This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

                History
                : 25 July 2023
                : 21 November 2023
                Page count
                Figures: 8, Tables: 3, Pages: 12
                Funding
                Funded by: funder-id http://dx.doi.org/10.13039/501100001809, National Natural Science Foundation of China;
                Award ID: 41501370
                Award Recipient :
                Funded by: funder-id http://dx.doi.org/10.13039/501100001809, National Natural Science Foundation of China;
                Award ID: 62176165
                Award Recipient :
                Funded by: Shenzhen Technology University
                Award ID: 2021010802014
                Award Recipient :
                This research is supported by National Natural Science Foundation of China(Grant No. 41501370 and 62176165),the 5th College-enterprise Cooperation Project of Shenzhen Technology University (Grant No.2021010802014). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
                Categories
                Research Article
                Physical Sciences
                Mathematics
                Applied Mathematics
                Algorithms
                Machine Learning Algorithms
                Research and Analysis Methods
                Simulation and Modeling
                Algorithms
                Machine Learning Algorithms
                Computer and Information Sciences
                Artificial Intelligence
                Machine Learning
                Machine Learning Algorithms
                Computer and Information Sciences
                Network Analysis
                Computer and Information Sciences
                Neural Networks
                Biology and Life Sciences
                Neuroscience
                Neural Networks
                Engineering and Technology
                Signal Processing
                Image Processing
                Computer and Information Sciences
                Artificial Intelligence
                Machine Learning
                Deep Learning
                Physical Sciences
                Mathematics
                Probability Theory
                Probability Distribution
                Research and Analysis Methods
                Imaging Techniques
                Research and Analysis Methods
                Mathematical and Statistical Techniques
                Mathematical Functions
                Convolution
                Custom metadata
                Data and code cannot be shared publicly because of confidentiality agreement. Data and code are available from the MPWAY Technology Co., Ltd (contact via Mr. Zhou, zhlinxi205@ 123456163.com ) for researchers who meet the criteria for access to confidential data if they are permitted.

                Uncategorized
                Uncategorized

                Comments

                Comment on this article