Real-Time and Low-Memory Multi-Faces Detection System Design with Naive Bayes Classifier Implemented on FPGA

Kuan Yu Chou*, Yon Ping Chen

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

In recent years, face detection has been widely applied to a variety of fields, such as face recognition, image focusing, and surveillance systems. This study proposes a real-time multi-faces detection system based on naive Bayesian classifier using Field Programmable Gate Array (FPGA). The system includes three main parts, feature extraction, candidate face detection, and false elimination. First, downscale the image to the image pyramid and extract local binary image features from each downscaling image. With the bit-plane slicing for Local Binary Pattern (LBP) can save the memory consumption and speed up the computation. Then, adopt the naive Bayesian classifier to identify candidate faces. Finally use skin color filter and face overlapping elimination to remove false positives. The experimental results show that the accuracy rate is up to 96.14% in face detection, which demonstrates the proposed real-time multi-faces detection system is indeed effective and efficient.

Original languageEnglish
Article number8913595
Pages (from-to)4380-4389
Number of pages10
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume30
Issue number11
DOIs
StatePublished - Nov 2020

Keywords

  • bit-plane slicing for LBP
  • Face detection
  • field-programmable gate array (FPGA)
  • Naive Bayes classifier
  • skin color detection

Fingerprint Dive into the research topics of 'Real-Time and Low-Memory Multi-Faces Detection System Design with Naive Bayes Classifier Implemented on FPGA'. Together they form a unique fingerprint.

Cite this