A Feature Prefusion and Mask-Guided Network for Camera Decoration Defect Detection
- 30 October 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-10
Abstract
Camera decoration is an important part of smartphone. To achieve fully automated production, a dependable, efficient, and automatic method is required for camera decoration surface defect detection. This paper presents a detection scheme based on computer vision to improve the efficiency of screening defective products. Since there is no available dataset for method designing in camera decoration field, we establish a camera decoration defect dataset CD3 including 9417 samples with four types of defects. To increase sample size and alleviate category imbalance of CD3, we provide a dataset enhancing framework including a defect copy method and a background reuse method to generate an enhanced dataset CD3_En containing 39649 samples. Besides, a feature fusion and mask-guided network FMN including a feature pre-fusion (FPF) module and a multi-stage fusion (MSF) module is proposed to screen the defective products. The FPF is constructed by receptive field blocks (RFBs) and information diffusions (IDs), and it can achieve data volume reduction and context enhancement after being embedded between the BoneNet and Neck. The MSF is used as the Neck to realizes a two-step feature fusion for predicting the bounding boxes of defects and their masks. The experimental results on CD3_En dataset demonstrate the superiority of the proposed method compared to other eleven classic object detection methods.Keywords
Funding Information
- National Natural Science Foundation of China (U23B2063, 62076256)
- Key Research and Development Plan Program of Hunan Province (2023GK2021)
- in part by the Scientific Research Project of Hunan Provincial Education Department (23A0011)
- Higher Education Discipline Innovation Project (B18059)
This publication has 38 references indexed in Scilit:
- PCB defects target detection combining multi-scale and attention mechanismEngineering Applications of Artificial Intelligence, 2023
- Improved faster R-CNN for fabric defect detection based on Gabor filter with Genetic Algorithm optimizationComputers in Industry, 2022
- Nitrogen‐Doping‐Regulated Electromagnetic Wave Absorption Properties of Ultralight Three‐Dimensional Porous Reduced Graphene Oxide AerogelsAdvanced Electronic Materials, 2020
- Segmentation-based deep-learning approach for surface-defect detectionJournal of Intelligent Manufacturing, 2019
- Receptive Field Block Net for Accurate and Fast Object Detection2018
- Modeling Visual Context Is Key to Augmenting Object Detection Datasets2018
- Medical Image Synthesis for Data Augmentation and Anonymization Using Generative Adversarial Networks2018
- A Surface Defect Detection Method Based on Positive Samples2018
- SSD: Single Shot MultiBox Detector2016
- A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defectsApplied Surface Science, 2013