Recognition and Classification of Wire Bonding Joint via image Feature and SVM Model

Recognition and classification for wire bonding joint are important to quality assurance in semiconductor device manufacturing. In this paper, a precision recognition and classification system for bonding joint of ultrasonic heavy aluminum wire based on image feature and support vector machine (SVM) is presented. This system consists of feature extraction from images and classification model. In feature extraction, image processing algorithms including Canny edge extraction, histogram equalization, and image morphology closed operation are utilized to extract and locate a joint contour in a complicated background image. In the classification model, the principal component analysis (PCA) is employed to visualize, reconstruct, and reduce the images data dimension for less computation time. The SVM-based model is chosen as the classifier to identify and recognize joint types. The Gauss-radial basis function (RBF) kernel function is adopted in SVM, and its optimal parameters are determined by cross-validation. In the experiment, 588 bonding images are used to implement in this recognition and classification system. The results prove that the classification accuracy for wire bonding joint based on image feature, PCA, and SVM can achieve to 97.3%, and the computation time can be reduced significantly.