Face Recognition Using Local Binary Patterns Histograms (LBPH) on an FPGA-Based System on Chip (SoC)
Authors:
- Nikolaos StekasNSNikolaos Stekas
- Dirk Van Den HeuvelDHDirk Van Den Heuvel
- 1 May 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 300-304
Abstract
The need for facial recognition systems that are fast and accurate is continuously increasing. In this paper, a face recognition implementation on a System on Chip (SoC), integrated with an FPGA, is presented. This implementation utilizes Local Binary Patterns Histograms to extract features from test face images and Manhattan distance to retrieve the correct match from the system's face database. The SoC utilized is a Zynq-7030. The feature extraction and the distance computations, between the database, are implemented on the FPGA. The ARM processor of the SoC is responsible for receiving the input stream and presenting the output result, using the acquired distances. Real-time face recognition, with an execution time of 8.6 ms and accuracy of 79%, is achieved through this implementation.Keywords
This publication has 6 references indexed in Scilit:
- Unconstrained Facial Images: Database for Face Recognition Under Real-World Conditions2015
- Parallel Implementation of LBP Based Face Recognition on GPU Using OpenCL2012
- Local Binary Pattern histogram based Texton learning for texture classification2011
- Face Recognition with Local Binary Patterns, Spatial Pyramid Histograms and Naive Bayes Nearest Neighbor Classification2009
- Face Description with Local Binary Patterns: Application to Face RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- A comparative study of texture measures with classification based on featured distributionsPattern Recognition, 1996