Fast LBP Face Detection on Low-Power SIMD Architectures

This paper presents an embedded implementation of a face detection method based on boosted LBP features for Single Instruction Multiple Data (SIMD) architectures. The implementation exploits parallelism and data reuse in the detection algorithm and is integrated into CogniVue's Gen-1 APEX platf...

Full description

Saved in:
Bibliographic Details
Main Authors: Bilaniuk, Olexa, Fazl-Ersi, Ehsan, Laganiere, Robert, Xu, Christina, Laroche, Daniel, Moulder, Craig
Format: Conference Proceeding
Language:English
Subjects:
Algorithms
Design engineering
Energy use
Face
Face detection
Face recognition
Feature extraction
Field programmable gate arrays
Frames per second
LBP features
Pattern recognition
Platforms
SIMD architecture
Table lookup
Vectors
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents an embedded implementation of a face detection method based on boosted LBP features for Single Instruction Multiple Data (SIMD) architectures. The implementation exploits parallelism and data reuse in the detection algorithm and is integrated into CogniVue's Gen-1 APEX platform, which uses a SIMD design and is extremely energy efficient. The proposed embedded face detection system runs at 5 VGA frames per second, while providing similar accuracy to the PC version of the LBP face detection algorithm included in the OpenCV library.
ISSN:2160-7508
2160-7516
DOI:10.1109/CVPRW.2014.96