2021 •
A Novel Superpixels Image Segmentation Algorithm for PCBA Components
Authors:
Yan He, Xie Min, Zhao Qifeng
Abstract:
The visual location accuracy of assembly robot is affected directly by the accuracy of image segmentation. Most traditional algorithms couldn’t meet the industrial manufacture rhythm of Printed Circuit Board Assembly (PCBA) components. As a result, this paper proposed a novel superpixels image segmentation algorithm for PCBA components. Firstly, the salient feature was extracted by Histogram-based Contrast (HC) algorithm. Then, the salience map was extracted according to the Simple Non-Iterative Clustering (SNIC) superpixels segmentation algo (...)
The visual location accuracy of assembly robot is affected directly by the accuracy of image segmentation. Most traditional algorithms couldn’t meet the industrial manufacture rhythm of Printed Circuit Board Assembly (PCBA) components. As a result, this paper proposed a novel superpixels image segmentation algorithm for PCBA components. Firstly, the salient feature was extracted by Histogram-based Contrast (HC) algorithm. Then, the salience map was extracted according to the Simple Non-Iterative Clustering (SNIC) superpixels segmentation algorithm. A new method was proposed to obtain information entropy by creating a new superpixels image. Ultimately, the segmented image was obtained according to the information entropy. According to the experimental results, the F-measure, the MAE and the time were 0.7979, 0.040567 and 179.12851s respectively, showing that the proposed algorithm was better than the other six algorithms. (Read More)
2021 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC) ·
2021
Artificial intelligence |
Computer vision |
We have placed cookies on your device to help make this website and the services we offer better. By using this site, you agree to the use of cookies. Learn more