The Use of Intelligent Approaches to Improve the Quality of Coatings on Electronic Devices

In this paper, we present an object detection system with a set of weak classifiers and its application to plasma sprayed coatings. In order to improve performance of the classifier, we used combinations of halftone images and gradient images generated by the Sobel operator. Each weak classifier computes its feature value for a detection window. Three hundred positive and 300 negative snapshots were used to train the detector, while 200 positive and 200 negative images were used for its testing. At first a patch is convolved with one of 13 filters, including delta function, Gaussian derivatives, Laplacian, corner detectors and edge detectors. Then, one of 30 spatial templates applies to the filtered patch. This method was implemented in the MATLAB environment.