Artwork painting identification method for panorama based on adaptive rectilinear projection and optimized ASIFT

In the paper, the authors present an artwork painting identification method for panorama based on adaptive rectilinear projection and optimized ASIFT (Affine Scale-Invariant Feature Transform). Firstly, the authors use the panorama dataset to train the artwork painting detection network to obtain the location information of artwork paintings. Secondly, the authors use the adaptive rectilinear projection to map the artwork painting into a square image with a fixed size. Then the authors use the image enhancement method to improve the image quality. Finally, the authors use the optimized ASIFT for features extraction and image matching. Several contrast experiments were conducted on the artwork paintings panorama dataset for artwork paintings identification. The results show that the proposed method can achieve 96% identification accuracy on average for the whole test artwork paintings panorama dataset. The proposed adaptive rectilinear based-method can improve at least 20% of the recognition accuracy. The proposed optimized ASIFT can improve at least 30% of the identification accuracy than SIFT. The authors also study other factors such as the size of the original artwork image, the image matching threshold, whether using image enhancement or not. The results show the size of the original artwork has little influence on the artwork identification in the panorama. The image matching threshold with 2.0 is better than 3.0. Furthermore, using the image enhancement method can improve about 2% of the identification accuracy.