Improving the Reliability of Object Recognition Based On Template Matching

Object recognition in computer vision is the task of finding a given object in an image or video sequence. During the last decades it has received increasing attention from the computer vision community for a variety of reasons, ranging from counting objects for industrial application to the development of practical biometric systems and interactive, emotion-aware and capable human–machine interfaces. There are variety of approaches for object recognition problem, depending on the type of object, the degree of freedom of the object and the target application. Template matching is the most advanced and intensively developed areas of computer vision and has been a classical approach to the problems of locating and recognizing of an object in the image. The object of this paper is to improve the reliability of object recognition by describing a modified method for template matching based on the Sum of Squared Differences (SSD) equation, that gives the highest margin between other template matching methods, the main advantage is that the high margin resulting from it can be considered as more safe to avoid wrongly detecting /recognizing an object.