Recognitions of the printed English characters using Fractal Dimension.

Abstract<br /> In this research we presented approach for recognize printed English script, in the proposed approach, the technique can be divided into three major steps. The first step is digitization then do some pre-processing like segmentation to obtain the character image and resize it. Second, feature extraction, using Fractal Dimension. Finally, the K-Nearest-Neighbors is used for classification. This method was tested using 20 patterns for each English character. The sample images were divided into 15 training and 5 test images. Images in the test set did not appear in the training sets. This method performs extremely well with recognition rates 85.3%. This is a very good performance. All of this demonstrates that the new method is able to handle printed English character task efficiently. It is a promising technique for recognition printed English character.