The $\mathcal{E}$-Average Common Submatrix: Approximate Searching in a Restricted Neighborhood
Computer Vision and Pattern Recognition
2017-06-20 v1 Discrete Mathematics
Information Retrieval
Information Theory
math.IT
Abstract
This paper introduces a new (dis)similarity measure for 2D arrays, extending the Average Common Submatrix measure. This is accomplished by: (i) considering the frequency of matching patterns, (ii) restricting the pattern matching to a fixed-size neighborhood, and (iii) computing a distance-based approximate matching. This will achieve better performances with low execution time and larger information retrieval.
Cite
@article{arxiv.1706.06026,
title = {The $\mathcal{E}$-Average Common Submatrix: Approximate Searching in a Restricted Neighborhood},
author = {Alessia Amelio and Darko Brodić},
journal= {arXiv preprint arXiv:1706.06026},
year = {2017}
}
Comments
4 pages, 18th International Workshop on Combinatorial Image Analysis (IWCIA 2017), Short Communication