A novel label protuberant characters recognition method based on WPT and improved SVD

To recognize protuberant characters on the labels, a novel recognition method based on gray image using wavelet packet transform (WPT) and improved Singular Value Decomposition (SVD) is suggested. The images are decomposed by WPT, and then the singular values (SVs) feature and projection feature of approximation images obtained through the above process are combined to form a new eigenvector using weighting coefficient. And the comparisons of recognition experiments are carried out using Euclidean distance. This method not only makes full use of many excellent properties of the SVs feature, but also overcomes the shortcomings of missing useful information and many other problems caused by image binarization. Experiments confirm that the method could effectively improve the recognition rate of characters, and has much better robustness.