Persian Handwritten Numeral Recognition Using Complex Neural Network And Non-linear Feature Extraction

In this paper, we propose a new isolated handwritten numbers recognition by using of sparse structure representation. We introduce the sparse structure which is a over-complete dictionary and it is known with K-SVD algorithm. In this vocabulary, values adopted by initialized to the first layer of Complex Neural Network(CNN) and in the last, it learned for doing classification task. The distinction between proposed method with previous methods in addition to using of the CNN and K-SVD algorithm is non-linear feature extraction. It is noted which in the previous methods extracted linear feature. When using of each type linear and non-linear analysis, it is important that we distinguish between their application In reduce dimensional and special gregarious correct recognition of the features that doing basis on specific rules. Subspaces under high power will appears in the first usage, for notice to denoising and high data compression Without necessary that individuals were specifically. this is only condition which in describe the subspace to size of information in the data.