IDENTIFYING COMPLEMENTARY CORNER DETECTORS FOR CORRECT IMAGE PIXELS CLASSIFICATION

Abstract

Classification of digital image content is mainly done by identifying low level imagefeatures such as corners and edges. The literature shows variety of algorithms for the identification ofcorner and non-corner pixels, important for objects’ identification and image segmentation. However,all of these algorithms produce different results for same data and therefore, suitable for limitedapplications. This paper proposes a hybrid solution of combining complementary corner detectionalgorithms to improve image pixels’ classification. This has been done by identifying the bestdetection algorithm for corner points with small and large angles and producing a hybrid algorithm bycombining the latter two. Results have shown that Harris detector combined with Global and LocalCurvature Points (GLC) improved the detection rate by 28% in synthetic images, but 50% in realimages whereas, the combination of Shi’s detection algorithm with GLC enhanced the detection rateby 25.9% in synthetic images and 123% in real images, showing a significant improvement.