Robust Template Matching via Hierarchical Convolutional Features from a Shape Biased CNN
This work addresses template matching for computer vision applications, showing incremental improvements in robustness.
The paper tackles the problem of template matching in computer vision by enhancing a CNN's shape encoding to produce more distinguishable features, resulting in state-of-the-art performance on a standard benchmark and outperforming existing techniques on a new dataset.
Finding a template in a search image is an important task underlying many computer vision applications. Recent approaches perform template matching in a deep feature-space, produced by a convolutional neural network (CNN), which is found to provide more tolerance to changes in appearance. In this article we investigate if enhancing the CNN's encoding of shape information can produce more distinguishable features that improve the performance of template matching. This investigation results in a new template matching method that produces state-of-the-art results on a standard benchmark. To confirm these results we also create a new benchmark and show that the proposed method also outperforms existing techniques on this new dataset. Our code and dataset is available at: https://github.com/iminfine/Deep-DIM.