SPATIAL DECOMPOSITION FOR COIN IMAGE RECOGNITION

A novel approach for coin image recognition is presented. Measuring the similarity between full color coin images is the main goal of the paper. The procedure is based on edge extraction of the coin image. Effective features are driven and used for coin comparison. The features are based on spatial decomposition of pixels in the abstract image. The results extracted j?om the proposed method are compared with three other well-&own approaches. SigniJicant improvement in the Recall ratio using the proposed features is demonstrated.