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 structurerepresentation. We introduce the sparse structure which is aover-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 ofthe CNN and K-SVD algorithm is non-linear feature extraction. It is noted which in the previous methods extracted linearfeature. When using of each type linear and non-linear analysis, it is important that we distinguish between their application Inreduce dimensional and special gregarious correct recognitionof the features that doing basis on specific rules. Subspaces under high power will appears in the first usage, for notice todenoising 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.

Keywords:

Non-linear features , Neural Networks , KSVD algorithm