Increasing the Classification Achievement of Steel Surface Defects by Applying a Specific Deep Strategy and a New Image Processing Approach

Abstract

Defect detection is still challenging to apply in reality because the goal of the entire classification assignment is to identify the exact type and location of every problem in an image. Since defect detection is a task that includes location and categorization, it is difficult to take both accuracy factors into account when designing related solutions. Flaw detection deployment requires a unique detection dataset that is accurately annotated. Producing steel free of flaws is crucial, particularly in large production systems. Thus, in this study, we proposed a novel deep learning-based flaw detection system with an industrial focus on automated steel surface defect identification. To create processed images from raw steel surface images, a novel method was applied. A new deep learning model called the Parallel Attention–Residual CNN (PARC) model was constructed to extract deep features concurrently by training residual structures and attention. The Iterative Neighborhood Component Analysis (INCA) technique was chosen for distinguishing features to lower the computational cost. The classification assessed the SVM method using a convincing dataset (Severstal: Steel Defect Detection). The accuracy in both the binary and multi-class classification tests was above 90%. Moreover, using the same dataset, the suggested model was contrasted with pre-existing models.