A Target Recognition Algorithm Based on the Object’s Color and Size Features

Abstract

The problem being faced is that the current target recognition method based on color feature can’t filter objects that have the same color as the target object. In this paper, a new target recognition algorithm based on the object’s color and size is introduced. To achieve the goal of object recognition, the HSV color space conversion, the threshold method and seed growth method are used together to implement image segmentation. The size feature has been used to filter the image regions that have been extracted by image segmentation. The method is proved by experimentation to be effective in regular shape object recognition.