Improving the Accuracy of Arctan for Face Detection

Youngsoo Kim; Hossein Shahdoost; Shrikant S Jadhav; Clay S Gloster

Improving the Accuracy of Arctan for Face Detection

Youngsoo Kim
, Hossein Shahdoost
, Shrikant S Jadhav
, Clay S Gloster

Computer Systems Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Significant barriers to real time face detection have been the complexity of computation kernels, minimal costand superior accuracy requirements for both software and hardware implementation based on traditional high performance computing. It is desirable to develop variable precision face detection block for high dynamic range applications including night vision and infrared face detection applications. This paper developed an Arctan fucntion for face detection which supports input ranges upto 360 degrees for Histogram of Oriented Graph. Our implementation takes advantage of mathematical identities for the pedestrian HOG computation. We compare our HOG block design to fixed point implementations and found that using floating point HOG is not be computationally expensive and can accelerate face detection process.

Original language	English
Title of host publication	2017 IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)
State	Published - 2017

Cite this

@inproceedings{1e4bca19e8434d8eb6373c56316f6868,

title = "Improving the Accuracy of Arctan for Face Detection",

abstract = "Significant barriers to real time face detection have been the complexity of computation kernels, minimal costand superior accuracy requirements for both software and hardware implementation based on traditional high performance computing. It is desirable to develop variable precision face detection block for high dynamic range applications including night vision and infrared face detection applications. This paper developed an Arctan fucntion for face detection which supports input ranges upto 360 degrees for Histogram of Oriented Graph. Our implementation takes advantage of mathematical identities for the pedestrian HOG computation. We compare our HOG block design to fixed point implementations and found that using floating point HOG is not be computationally expensive and can accelerate face detection process.",

author = "Youngsoo Kim and Hossein Shahdoost and Jadhav, \{Shrikant S\} and Gloster, \{Clay S\}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.",

year = "2017",

language = "English",

booktitle = "2017 IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)",

}

TY - GEN

T1 - Improving the Accuracy of Arctan for Face Detection

AU - Kim, Youngsoo

AU - Shahdoost, Hossein

AU - Jadhav, Shrikant S

AU - Gloster, Clay S

PY - 2017

Y1 - 2017

N2 - Significant barriers to real time face detection have been the complexity of computation kernels, minimal costand superior accuracy requirements for both software and hardware implementation based on traditional high performance computing. It is desirable to develop variable precision face detection block for high dynamic range applications including night vision and infrared face detection applications. This paper developed an Arctan fucntion for face detection which supports input ranges upto 360 degrees for Histogram of Oriented Graph. Our implementation takes advantage of mathematical identities for the pedestrian HOG computation. We compare our HOG block design to fixed point implementations and found that using floating point HOG is not be computationally expensive and can accelerate face detection process.

AB - Significant barriers to real time face detection have been the complexity of computation kernels, minimal costand superior accuracy requirements for both software and hardware implementation based on traditional high performance computing. It is desirable to develop variable precision face detection block for high dynamic range applications including night vision and infrared face detection applications. This paper developed an Arctan fucntion for face detection which supports input ranges upto 360 degrees for Histogram of Oriented Graph. Our implementation takes advantage of mathematical identities for the pedestrian HOG computation. We compare our HOG block design to fixed point implementations and found that using floating point HOG is not be computationally expensive and can accelerate face detection process.

M3 - Conference contribution

BT - 2017 IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)

ER -

Improving the Accuracy of Arctan for Face Detection

Abstract

Fingerprint

Cite this