Image Patch Matching Using Convolutional Descriptors with Euclidean Distance

TL;DR

This paper introduces a neural network-based image descriptor for patch matching that outperforms traditional methods like SIFT using Euclidean distance, with enhancements from preprocessing and spatial transformer networks.

Contribution

The authors develop a CNN-based descriptor that surpasses state-of-the-art L2 descriptors and demonstrate improvements with batch normalization, histogram equalization, and spatial transformer networks.

Findings

Outperforms SIFT and other L2-based descriptors.

Preprocessing techniques improve descriptor performance.

Spatial transformer networks enhance matching accuracy.

Abstract

In this work we propose a neural network based image descriptor suitable for image patch matching, which is an important task in many computer vision applications. Our approach is influenced by recent success of deep convolutional neural networks (CNNs) in object detection and classification tasks. We develop a model which maps the raw input patch to a low dimensional feature vector so that the distance between representations is small for similar patches and large otherwise. As a distance metric we utilize L2 norm, i.e. Euclidean distance, which is fast to evaluate and used in most popular hand-crafted descriptors, such as SIFT. According to the results, our approach outperforms state-of-the-art L2-based descriptors and can be considered as a direct replacement of SIFT. In addition, we conducted experiments with batch normalization and histogram equalization as a preprocessing method of the input data. The results confirm that these techniques further improve the performance of the proposed descriptor. Finally, we show promising preliminary results by appending our CNNs with recently proposed spatial transformer networks and provide a visualisation and interpretation of their impact.