Essential keypoints to enhance visual object recognition with saliency-based metrics

The authors propose a novel pre-processing phase that can be integrated into conventional methods to detect and recognize planar visual objects in printed materials with low computational cost and higher accuracy. A simple yet efficient visual saliency estimation technique based on regional contrast is developed to quickly filter out low informative regions in printed materials. By eliminating noisy or unimportant keypoint candidates, our proposed method not only reduces unnecessary computational cost of keypoint descriptors but also increases robustness and accuracy of visual object recognition. Our experimental results show that the whole visual object recognition process can be speeded up 46 times and the accuracy can increase up to 23%. These are desirable advantages for an augmented reality system, especially on mobile devices. Furthermore, this pre-processing stage is independent of the choice of features and matching model in a general process. Therefore it can be used to boost the performance of existing systems into real-time manner.