Classification-Based Character Segmentation of Image

Abstract

In traditional way, the segmentation of image is conducted by simple technology of image processing, which cannot be operated automatically. In this paper, we present a kind of classification method to find the boundary area to segment character image. Referring to sample points and sample areas, the essential segmentation information is extracted. By merging different formats of image transformation, including rotation, erosion and dilation, more features are used to train and test the segmentation model. Parameter tuning is also proposed to optimize the model for promotion. By the means of cross validation, the basic training model and parameter tuning are integrated in iteration way. The comparison results show that the best precision and recall can up to 97.84% in precision and 94.09% in recall.