Low-resolution character recognition with Compound Mutual Subspace Method

Abstract

In character recognition system using images captured by a mobile phone camera, it is difficult to correctly recognize blurred characters. Therefore, we aim at high accuracy character recognition by obtaining information from multiple frames of video. In this paper, we propose a character recognition method based on the Compound Mutual Subspace Method which absorbs the blur of low-resolution character and which is also superior to the identification of similar characters by generating an input subspace from multiple input images. In addition, we save the effort of collecting training data by estimating the degradation function from degraded images and make dictionary subspaces that reflects the characteristics of the camera.