Text detection algorithm on real scenes images and videos on the base of discrete cosine transform and convolutional neural network

In this work we present algorithms which are applied in such task as text recognition on images and video. Proposed algorithm is based on the combination of discrete cosine transform and convolutional neural networks. Description of the applying features of discrete cosine transform for text detection is provided. We list the main advantages and disadvantages of CNN and DCT combination. Also in this article we are going to consider methods of convolution neural networks for the task of text recognition.