FPGA Implementation of Multi-scale Face Detection Using HOG Features and SVM Classifier

Abstract In this paper an FPGA based embedded vision system for face detection is presented. The sliding detection window, HOG+SVM algorithm and multi-scale image processing were used and extensively described. The applied computation parallelizations allowed to obtain real-time processing of a 1280 × 720 @ 50Hz video stream. The presented module has been verified on the Zybo development board with Zynq SoC device from Xilinx. It can be used in a vast number of vision systems, including diver fatigue monitoring.

[1]  Stefanos Zafeiriou,et al.  A survey on face detection in the wild: Past, present and future , 2015, Comput. Vis. Image Underst..

[2]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[3]  Y. M. Mustafah,et al.  Skin region detector for real time face detection system , 2012, 2012 International Conference on Computer and Communication Engineering (ICCCE).

[4]  Wanqing Li,et al.  Human detection with contour-based local motion binary patterns , 2011, 2011 18th IEEE International Conference on Image Processing.

[5]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Nai-Jian Wang,et al.  A real-time multi-face detection system implemented on FPGA , 2012, 2012 International Symposium on Intelligent Signal Processing and Communications Systems.

[7]  Suraj Das,et al.  Modified architecture for real-time face detection using FPGA , 2012, 2012 Nirma University International Conference on Engineering (NUiCONE).

[8]  Marek Gorgon,et al.  Floating point HOG implementation for real-time multiple object detection , 2012, 22nd International Conference on Field Programmable Logic and Applications (FPL).

[9]  Seok-Bum Ko,et al.  FPGA Implementation of a Face Detector using Neural Networks , 2006, 2006 Canadian Conference on Electrical and Computer Engineering.

[10]  Gang Hua,et al.  A convolutional neural network cascade for face detection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Frank Vahid,et al.  Scalable object detection accelerators on FPGAs using custom design space exploration , 2011, 2011 IEEE 9th Symposium on Application Specific Processors (SASP).

[12]  Tsuhan Chen,et al.  Proposed FPGA Hardware Architecture for High Frame Rate (≫100 fps) Face Detection Using Feature Cascade Classifiers , 2007, 2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems.

[13]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[14]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[15]  Donald G. Bailey,et al.  Design for Embedded Image Processing on FPGAs , 2011 .

[16]  Edwin Naroska,et al.  A hardware-efficient color segmentation algorithm for face detection , 2010, 2010 IEEE Asia Pacific Conference on Circuits and Systems.

[17]  Xu An Wang,et al.  Cascade Face Detection Based on Histograms of Oriented Gradients and Support Vector Machine , 2015, 2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC).

[18]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[19]  Shengcai Liao,et al.  Face Detection Based on Multi-Block LBP Representation , 2007, ICB.

[20]  Shih-Lien Lu,et al.  Novel FPGA based Haar classifier face detection algorithm acceleration , 2008, 2008 International Conference on Field Programmable Logic and Applications.

[21]  Tomasz Kryjak,et al.  An Efficient Hardware Architecture for Block Based Image Processing Algorithms , 2016, ARC.

[22]  Vivienne Sze,et al.  An Energy-Efficient Hardware Implementation of HOG-Based Object Detection at 1080HD 60 fps with Multi-Scale Support , 2016, J. Signal Process. Syst..