Abstract
Convolutional neural network (CNN)-based approaches have recently led to major performance steps in visual recognition tasks. However, only a few industrial applications are described in the literature. In this paper, an object detection application for visual quality evaluation of X-ray scatter grids is described and evaluated. To detect the small defects on the 4K input images, a sliding window approach is chosen. A special characteristic of the selected approach is the aggregation of overlapping prediction results by applying a 2D scalar field. The final system is able to detect 90% of the relevant defects, taking a precision score of 25% into account. A practical examination of the effectiveness elaborates the potential of the approach, improving the detection results of the inspection process by over 13%.
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献