A Hybrid Approach for Image Classification Based on Sparse Coding and Wavelet Decomposition

As a powerful technique, sparse coding was adopted by several researchers in different approaches. Particularly in image processing, it has attracted a considerable attention. It can be widely used for representation, compression, denoising and separation of all type of signal. Recent works have confirmed that the use of a predefined dictionary is less efficient than a dictionary from training data. According to this idea, this paper proposes a new technique based on wavelet network to create a dictionary to ameliorate the representation and classification of image using sparse coding technique.