A comparative study between Ridgelet PCA and PCA using different distance measure technique for 2D shape recognition and retrieval

In this paper, we have proposed a novel method for two-dimensional shape object recognition and retrieval. The proposed method is based on Ridgelet Principal Component Analysis (Ridgelet PCA). In our proposed approach we first use the ridgelet transform to extract line singularity features and point singularity features by applying the radon and wavelet transform respectively and then applying PCA to extract the effective features. For recognition and retrieval we have conducted a study by using seventeen different distance measure techniques. The training and testing process is conducted using leave-one-out strategy. The retrieval process is carried out by considering standard test ’bullseye’ score. The proposed method is tested on the collected standard dataset MPEG-7. Experimental results of Ridgelet PCA are compared with the existing PCA method, which show that our approach results are favorable compared to the reference methods, in terms of recognition and retrieval rate. keywords : 2D Object Recognition, Retrieval, Principal Component Analysis, Ridgelet Transform, Distance Measure Techniques.