In recent years, learning based machine intelligence has aroused a lot of attention across science and engineering. Particularly in\nthe field of automatic industry inspection, the machine learning based vision inspection plays a more and more important role\nin defect identification and feature extraction. Through learning from image samples, many features of industry objects, such as\nshapes, positions, and orientations angles, can be obtained and then can be well utilized to determine whether there is defect\nor not. However, the robustness and the quickness are not easily achieved in such inspection way. In this work, for solar panel\nvision inspection, we present an extreme learning machine (ELM) and moving least square regression based approach to identify\nsolder joint defect and detect the panel position. Firstly, histogrampeaks distribution (HPD) and fractional calculus are applied for\nimage preprocessing. Then an ELM-based defective solder joints identification is discussed in detail. Finally, moving least square\nregression (MLSR) algorithm is introduced for solar panel position determination. Experimental results and comparisons show\nthat the proposed ELM and MLSR based inspection method is efficient not only in detection accuracy but also in processing speed.
Loading....