Speeded Up Feature Extraction for CT Image Based on Integral Image Technique

초록

As a classic texture feature for image classification, the SGLDM is widely employed in medical image analysis. However, the complicated computation to extract texture features using SGLDM is an inherent problem of its application. Reducing the gray level of the image can partially solve this problem whereas significant texture information is lost. In this paper, we propose to apply the integral image technique so as to speed up the texture feature extraction. Experimental results show that the proposed method can extract identical features as the original algorithm whereas the extraction time of the proposed method is only 0.0822% of that of the original algorithm.