Sparse Over-complete Patch Matching

by   Akila Pemasiri, et al.

Image patch matching, which is the process of identifying corresponding patches across images, has been used as a subroutine for many computer vision and image processing tasks. State -of-the-art patch matching techniques take image patches as input to a convolutional neural network to extract the patch features and evaluate their similarity. Our aim in this paper is to improve on the state of the art patch matching techniques by observing the fact that a sparse-overcomplete representation of an image posses statistical properties of natural visual scenes which can be exploited for patch matching. We propose a new paradigm which encodes image patch details by encoding the patch and subsequently using this sparse representation as input to a neural network to compare the patches. As sparse coding is based on a generative model of natural image patches, it can represent the patch in terms of the fundamental visual components from which it has been composed of, leading to similar sparse codes for patches which are built from similar components. Once the sparse coded features are extracted, we employ a fully-connected neural network, which captures the non-linear relationships between features, for comparison. We have evaluated our approach using the Liberty and Notredame subsets of the popular UBC patch dataset and set a new benchmark outperforming all state-of-the-art patch matching techniques for these datasets.


page 1

page 2

page 3

page 4


SimPatch: A Nearest Neighbor Similarity Match between Image Patches

Measuring the similarity between patches in images is a fundamental buil...

Patch Selection for Melanoma Classification

In medical image processing, the most important information is often loc...

Learned Multi-Patch Similarity

Estimating a depth map from multiple views of a scene is a fundamental t...

Feature Fusion for Robust Patch Matching With Compact Binary Descriptors

This work addresses the problem of learning compact yet discriminative p...

Sparse convolutional context-aware multiple instance learning for whole slide image classification

Whole slide microscopic slides display many cues about the underlying ti...

Research on Patch Attentive Neural Process

Attentive Neural Process (ANP) improves the fitting ability of Neural Pr...

Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding

Classifying single image patches is important in many different applicat...

Please sign up or login with your details

Forgot password? Click here to reset