arrow
Return

LMR: Learning a Two-Class Classifier for Mismatch Removal

delete2019-08-01
delete187
PRE
AI
马佳义 cover
马佳义 (Jiayi Ma)
X
Xingyu Jiang
J
Junjun Jiang *
J
Ji Zhao
X
Xiaojie Guo
DOI:10.1109/TIP.2019.2906490delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
Feature matching, which refers to establishing reliable correspondence between two sets of features, is a critical prerequisite in a wide spectrum of vision-based tasks. Existing attempts typically involve the mismatch removal from a set of putative matches based on estimating the underlying image transformation. However, the transformation could vary with different data. Thus, a pre-defined transformation model is often demanded, which severely limits the applicability. From a novel perspective, this paper casts the mismatch removal into a two-class classification problem, learning a general classifier to determine the correctness of an arbitrary putative match, termed as Learning for Mismatch Removal (LMR). The classifier is trained based on a general match representation associated with each putative match through exploiting the consensus of local neighborhood structures based on a multiple K-nearest neighbors strategy. With only ten training image pairs involving about 8000 putative matches, the learned classifier can generate promising matching results in linearithmic time complexity on arbitrary testing data. The generality and robustness of our approach are verified under several representative supervised learning techniques as well as on different training and testing data. Extensive experiments on feature matching, visual homing, and near-duplicate image retrieval are conducted to reveal the superiority of our LMR over the state-of-the-art competitors.
Keywords:
Feature matching
supervised learning
classifier
outlier
mismatch removal
AI Summary

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.

Journal

IEEE Transactions on Image Processing cover
IEEE Transactions on Image Processing
IF:
13.7
Papers:
1.0W
Citations:
8.4W

Organization

H
harbin institute of technology
Scholars:
8.0W
Papers: 6.6W
Citations: 66
T
tianjin university
Scholars:
8.0W
Papers: 5.7W
Citations: 88
W
wuhan university
Scholars:
8.1W
Papers: 5.8W
Citations: 70
researcher View more organizations