Texture Instance Similarity via Dense Correspondences

Published in IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Placid, NY, USA, 2016

Recommended citation: Tal Hassner, Gilad Saban and Lior Wolf. Texture Instance Similarity via Dense Correspondences. IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Placid, NY, USA, 2016.


Examples of texture instance recognition problems.Fingerprints (top left) are one example of the problem of distinguishing between textures from the same class using fine details. Male Zebra finches (top right) are identified by their female partners using the texture patterns on their chests. Chameleons change their textural patterns as a method of communication (bottom). Here, we present a method which is agnostic to the class of textures being compared, yet effective enough to obtain state-of-the-art performance on standard fingerprint recognition challenges.

Abstract

This paper concerns the task of evaluating the similarity of textures instances: Rather than discriminating between different texture classes, our goal is to identify when two images display the same texture instance. To address this problem, we propose an approach inspired by alignment based recognition theories. We offer a pixel-based method, employing a robust, dense correspondence estimation engine, applied to an efficient, novel representation, to match the pixels of two texture photos. We describe means for quantifying the quality of these matches, considering in particular the quality of the flow established between the two images. These quality measures are effectively combined into similarity scores by using standard linear SVM classifiers. By relying on a general, alignment based approach our method can be applied to different problem domains (different texture classes) with little modification. We demonstrate this by reporting state-of-the-art results on benchmarks for fingerprint recognition and two new benchmarks for texture-based animal identification.

Download paper here