4.7 Article

Fusion of multi-light source illuminated images for effective defect inspection on highly reflective surfaces

期刊

出版社

ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD
DOI: 10.1016/j.ymssp.2022.109109

关键词

Surface inspection; Defect classification; Convolutional neural network; Image fusion; Multi-light source illumination

资金

  1. National Natural Science Foundation of China [52105526, 52075485]
  2. National Key Research and Development Program of China [2020YFB1711400]

向作者/读者索取更多资源

This paper proposes a multi-light source illumination/acquisition system and a multi-stream CNN model for high-accuracy surface defect classification on highly reflective metal. By fusing features extracted from multi-light source illuminated images, more accurate recognition results can be generated. In addition, the authors also propose individual stream deep supervision and channel attention-based feature re-calibration techniques.
It is observed that a human inspector can obtain better visual observations of surface defects via changing the lighting/viewing directions from time to time. Accordingly, we first build a multi light source illumination/acquisition system to capture images of workpieces under individual lighting directions and then propose a multi-stream CNN model to process multi-light source illuminated images for high-accuracy surface defect classification on highly reflective metal. Moreover, we present two effective techniques including individual stream deep supervision and channel attention (CA) based feature re-calibration to generate and select the most discriminative features on multi-light source illuminated images for the subsequent defect classification task. Comparative evaluation results demonstrate that our proposed method is capable of generating more accurate recognition results via the fusion of complementary features extracted on images illuminated by multi-light sources. Furthermore, our proposed light-weight CNN model can process more than 20 input frames per second on a single NVIDIA Quadro P6000 GPU (24G RAM) and is faster than a human inspector. Source codes and the newly constructed multi-light source illuminated dataset will be accessible to the public.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据