.png){kind=icon}
.png){kind=icon}
Return
An Adaptive Image Segmentation Network for Surface Defect Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2022.3230426.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Surface defect detection plays an essential role in industry, and it is challenging due to the following problems: 1) the similarity between defect and nondefect texture is very high, which eventually leads to recognition or classification errors and 2) the size of defects is tiny, which are much more difficult to be detected than larger ones. To address such problems, this article proposes an adaptive image segmentation network (AIS-Net) for pixelwise segmentation of surface defects. It con-sists of three main parts: multishuffle-block dilated convolution (MSDC), dual attention context guidance (DACG), and adaptive category prediction (ACP) modules, where MSDC is designed to merge the multiscale defect features for avoiding the loss of tiny defect feature caused by model depth, DACG is designed to capture more contextual information from the defect feature map for locating defect regions and obtaining clear segmenta-tion boundaries, and ACP is used to make classification and regression for predicting defect categories. Experimental results show that the proposed AIS-Net is superior to the state-of-the-art approaches on four actual surface defect datasets (NEU-DET: 98.38% +/- 0.03%, DAGM: 99.25% +/- 0.02%, Magnetic-tile: 98.73% +/- 0.13%, and MVTec: 99.72% +/- 0.02%).
Keywords:
Context information
deep learning
object detection
semantic segmentation
surface defect detection
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W