Locally Important Pattern Clustering Code for Pedestrian Classification
- Title
- Locally Important Pattern Clustering Code for Pedestrian Classification
- Author(s)
- Lim, Young Chul ; Kang, Minsung
- Issued Date
- 2015-08
- Citation
- IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, v.E98A, no.8, pp.1875 - 1878
- Type
- Article
- Author Keywords
- local binary pattern ; clustering code ; feature extraction ; pedestrian classification ; local ternary pattern
- Keywords
- Binary Patterns ; Clustering Code ; Codes (Symbols) ; Coding Scheme ; Feature Extraction ; Feature Vectors ; Local Binary Pattern ; Local Binary Patterns ; Local Patterns ; Local Ternary Pattern ; Local Ternary Patterns ; Pattern Clustering ; Pedestrian Classification
- ISSN
- 0916-8508
- Abstract
- In this letter, a local pattern coding scheme is proposed to reduce the dimensionality of feature vectors in the local ternary pattern. The proposed method encodes the ternary patterns into a binary pattern by clustering similar ternary patterns. The experimental results show that the proposed method outperforms the previous methods. Copyright © 2015 The Institute of Electronics, Information and Communication Engineers.
- Publisher
- Oxford University Press
- Related Researcher
-
-
Lim, Young Chul
- Research Interests
-
- Files in This Item:
-
There are no files associated with this item.
- Appears in Collections:
- Division of Automotive Technology 1. Journal Articles
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.