Illumination invariant feature based on neighboring radiance ratio

2017 ◽  
Author(s):  
Xi Zhang ◽  
Xiaolin Wu
Keyword(s):  
Illumination Invariant ◽  
Invariant Feature ◽  
Feature Based

scholarly journals A New Illumination Invariant Feature Based on SIFT Descriptor in Color Space

2012 ◽  
Vol 41 ◽  
pp. 305-311 ◽  
Author(s):  
Reza Javanmard Alitappeh ◽  
Kossar Jeddi Saravi ◽  
Fariborz Mahmoudi
Keyword(s):  
Color Space ◽  
Illumination Invariant ◽  
Invariant Feature ◽  
Sift Descriptor ◽  
Feature Based

Illumination invariant feature-based motion estimation

2001 ◽  
Author(s):  
Dong Wang ◽  
Yue Lu ◽  
Zhi-Gang Wang ◽  
Wei Wang ◽  
Xiaoming Xu
Keyword(s):  
Motion Estimation ◽  
Illumination Invariant ◽  
Invariant Feature ◽  
Feature Based

Illumination-Invariant Feature Detection based on Shallow Hybrid Network Model

2021 ◽  
Author(s):  
Ruiping Wang ◽  
Meihang Zhang ◽  
Liangcai Zeng ◽  
Kelvin K.L. Wong
Keyword(s):  
Network Model ◽  
Feature Detection ◽  
Hybrid Network ◽  
Illumination Invariant ◽  
Invariant Feature

A biologically inspired scale-space for illumination invariant feature detection

2013 ◽  
Vol 24 (7) ◽  
pp. 074024 ◽  
Author(s):  
Vasillios Vonikakis ◽  
Dimitrios Chrysostomou ◽  
Rigas Kouskouridas ◽  
Antonios Gasteratos
Keyword(s):  
Feature Detection ◽  
Scale Space ◽  
Biologically Inspired ◽  
Illumination Invariant ◽  
Invariant Feature

scholarly journals Invariant-Feature Based Object Tracking Using Discrete Dynamic Swarm Optimization

ETRI Journal ◽  
2017 ◽  
Vol 39 (2) ◽  
pp. 151-162 ◽  
Author(s):  
Kyuchang Kang ◽  
Changseok Bae ◽  
Jinyoung Moon ◽  
Jongyoul Park ◽  
Yuk Ying Chung ◽  
...  
Keyword(s):  
Object Tracking ◽  
Swarm Optimization ◽  
Discrete Dynamic ◽  
Invariant Feature ◽  
Feature Based

scholarly journals Unsupervised Learning of Individuals and Categories from Images

2008 ◽  
Vol 20 (5) ◽  
pp. 1165-1178 ◽  
Author(s):  
Stephen Waydo ◽  
Christof Koch
Keyword(s):  
Sparse Representation ◽  
Unsupervised Learning ◽  
Temporal Lobe ◽  
Expectation Maximization ◽  
Medial Temporal Lobe ◽  
Natural Images ◽  
Unsupervised Method ◽  
Object Categories ◽  
Invariant Feature ◽  
Feature Based

Motivated by the existence of highly selective, sparsely firing cells observed in the human medial temporal lobe (MTL), we present an unsupervised method for learning and recognizing object categories from unlabeled images. In our model, a network of nonlinear neurons learns a sparse representation of its inputs through an unsupervised expectation-maximization process. We show that the application of this strategy to an invariant feature-based description of natural images leads to the development of units displaying sparse, invariant selectivity for particular individuals or image categories much like those observed in the MTL data.

Sign in / Sign up

Export Citation Format

Share Document