An Appearance Defect Detection Method for Cigarettes Based on C-CenterNet

2022-07-12

Electronics

AI Summary

To address the poor adaptability, low localization accuracy, and insufficient classification performance in detecting surface defects (e.g., dents, deformations, stains) on automated cigarette production lines, this paper proposes C-CenterNet—a novel end-to-end object detection framework. Our method innovatively integrates the Convolutional Block Attention Module (CBAM), deformable convolutions, and the ACON adaptive activation function into the CenterNet architecture, leveraging a ResNet50 backbone with Feature Pyramid Network (FPN) to enhance robust center-point localization and attribute regression for multi-scale, fine-grained defects. Evaluated on a real-world industrial dataset, C-CenterNet achieves a mean Average Precision (mAP) of 95.01%, outperforming the baseline CenterNet by 6.14 percentage points. The model maintains high detection accuracy while satisfying real-time inference requirements, making it suitable for practical deployment in industrial environments.

Technology Category

• Computer Vision: Object Detection & Categorization
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Due to the poor adaptability of traditional methods in the cigarette detection task on the automatic cigarette production line, it is difficult to accurately identify whether a cigarette has defects and the types of defects; thus, a cigarette appearance defect detection method based on C-CenterNet is proposed. This detector uses keypoint estimation to locate center points and regresses all other defect properties. Firstly, Resnet50 is used as the backbone feature extraction network, and the convolutional block attention mechanism (CBAM) is introduced to enhance the network’s ability to extract effective features and reduce the interference of non-target information. At the same time, the feature pyramid network is used to enhance the feature extraction of each layer. Then, deformable convolution is used to replace part of the common convolution to enhance the learning ability of different shape defects. Finally, the activation function ACON (ActivateOrNot) is used instead of the ReLU activation function, and the activation operation of some neurons is adaptively selected to improve the detection accuracy of the network. The experimental results are mainly acquired via the mean Average Precision (mAP). The experimental results show that the mAP of the C-CenterNet model applied in the cigarette appearance defect detection task is 95.01%. Compared with the original CenterNet model, the model’s success rate is increased by 6.14%, so it can meet the requirements of precision and adaptability in cigarette detection tasks on the automatic cigarette production line.

Problem

• Detects cigarette appearance defects accurately
• Improves defect type identification precision
• Enhances adaptability in automatic production lines

Innovation

• C-CenterNet for defect detection
• CBAM enhances feature extraction
• Deformable convolution improves accuracy