B-HMAX: A fast Binary Biologically Inspired Model for Object Recognition
Zhang Huazhen1; Lu Yanfeng2; Kang Taekoo3; Lim Myotaeg4
Source PublicationNeurocomputing
AbstractThe biologically inspired model, Hierarchical Model and X (HMAX), has excellent performance in object categorization. It consists of four layers of computational units based on the mechanisms of the visual cortex. However, the random patch selection method in HMAX often leads to mismatch due to the extraction of redundant information, and the computational cost of recognition is expensive because of the Euclidean distance calculations for similarity in the third layer, S2. To solve these limitations, we propose a fast binary-based HMAX model (B-HMAX). In the proposed method, we detect corner-based interest points after the second layer, C1, to extract few features with better distinctiveness, use binary strings to describe the image patches extracted around detected corners, then use the Hamming distance for matching between two patches in the third layer, S2, which is much faster than Euclidean distance calculations. The experimental results demonstrate that our proposed B-HMAX model can significantly reduce the total process time by almost 80% for an image, while keeping the accuracy performance competitive with the standard HMAX.
KeywordObject Recognition Classification Hmax Binary Descriptor
Indexed BySCI
Document Type期刊论文
Affiliation1.School of Mechatronics, Korea University
2.Institute of Automation, Chinese Academy of Sciences
3.Department of Information and Telecommunication Engineering, Sangmyung University
4.School of Electrical Engineering, Korea University
Recommended Citation
GB/T 7714
Zhang Huazhen,Lu Yanfeng,Kang Taekoo,et al. B-HMAX: A fast Binary Biologically Inspired Model for Object Recognition[J]. Neurocomputing,2016(218):242-250.
APA Zhang Huazhen,Lu Yanfeng,Kang Taekoo,&Lim Myotaeg.(2016).B-HMAX: A fast Binary Biologically Inspired Model for Object Recognition.Neurocomputing(218),242-250.
MLA Zhang Huazhen,et al."B-HMAX: A fast Binary Biologically Inspired Model for Object Recognition".Neurocomputing .218(2016):242-250.
Files in This Item: Download All
File Name/Size DocType Version Access License
B-HMAX A fast binary(2633KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang Huazhen]'s Articles
[Lu Yanfeng]'s Articles
[Kang Taekoo]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang Huazhen]'s Articles
[Lu Yanfeng]'s Articles
[Kang Taekoo]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang Huazhen]'s Articles
[Lu Yanfeng]'s Articles
[Kang Taekoo]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: B-HMAX A fast binary biologically inspired model for object recognition (2).pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.