Effective Image Quality Inspection Based on Color and Texture Features

Abstract

As people’s interest in software increases, the number and types of newly developed applications increase day by day. Therefore, there are attempts to automatically check whether the newly developed interface of these programs works correctly through image processing instead of manually. In this paper, we describe a strategy to robustly detect execution error screens of applications through comparative analysis of key features from various kinds of image scenes. In the approach described in this study, we extract the main multiple features representing the image. Then, by comparing the difference of the extracted multiple features, it is effectively determined whether the image is the same normal image as the reference image or an error image similar to the target image but different from each other. Experimental results verify that the described algorithm accurately detects normal and faulty images by comparing the main multiple features from various types of images. For performance evaluation, we quantitatively compared the performance of the introduced dissimilar region extraction strategy with those of other conventional methods. The existing methods of extracting similarity between images based on one feature or histogram comparison mostly lack information to sufficiently express the entire image. Therefore, when similar areas between two images are extracted, many errors occurred due to incorrect matching. However, the proposed multiple feature-based method obtains richer information by extracting multiple features from the input image. In addition, because the matching is done based on this information, the accuracy is relatively high. The approach introduced in this study is expected to be effectively used in many practical applications related to image processing such as image retrieval, trademark comparison, video security, application quality inspection, etc.