TY - GEN
T1 - A robust face recognition algorithm using Markov Stationary Features and adjacent pixel intensity difference quantization histogram
AU - Lee, Feifei
AU - Kotani, Koji
AU - Chen, Qiu
AU - Ohmi, Tadahiro
PY - 2011/12/1
Y1 - 2011/12/1
N2 - In this paper, we present a robust face recognition algorithm using adjacent pixel intensity difference quantization (APIDQ) histogram combined with Markov Stationary Features (MSF). Previously, we have proposed a very simple yet highly reliable face recognition algorithm using Adjacent Pixel Intensity Difference Quantization (APIDQ) histogram. After the intensity variation vectors for all the pixels in an image are calculated, each vector is quantized directly in (dIx, dIy) plane instead of r-θ plane. By counting the number of elements in each quantized area in the (dIx, dIy) plane, a histogram can be created. This histogram, obtained by APIDQ for facial images, is utilized as a very effective personal feature. In this paper, we combine the APIDQ histogram with MSF so as to add spatial structure information to histogram. Experimental results show maximum average recognition rate of 97.16% is obtained for 400 images of 40 persons from the publicly available face database of AT&T Laboratories Cambridge. Furthermore, Top 1 recognition rate of 98.2% is achieved by using FB task of the publicly available face database of FERET.
AB - In this paper, we present a robust face recognition algorithm using adjacent pixel intensity difference quantization (APIDQ) histogram combined with Markov Stationary Features (MSF). Previously, we have proposed a very simple yet highly reliable face recognition algorithm using Adjacent Pixel Intensity Difference Quantization (APIDQ) histogram. After the intensity variation vectors for all the pixels in an image are calculated, each vector is quantized directly in (dIx, dIy) plane instead of r-θ plane. By counting the number of elements in each quantized area in the (dIx, dIy) plane, a histogram can be created. This histogram, obtained by APIDQ for facial images, is utilized as a very effective personal feature. In this paper, we combine the APIDQ histogram with MSF so as to add spatial structure information to histogram. Experimental results show maximum average recognition rate of 97.16% is obtained for 400 images of 40 persons from the publicly available face database of AT&T Laboratories Cambridge. Furthermore, Top 1 recognition rate of 98.2% is achieved by using FB task of the publicly available face database of FERET.
KW - Adjacent pixel intensity difference quantization (APIDQ)
KW - Face recognition
KW - Histogram feature
KW - Markov stationary features (MSF)
UR - http://www.scopus.com/inward/record.url?scp=84855975096&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84855975096&partnerID=8YFLogxK
U2 - 10.1109/SITIS.2011.40
DO - 10.1109/SITIS.2011.40
M3 - Conference contribution
AN - SCOPUS:84855975096
SN - 9780769546353
T3 - Proceedings - 7th International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2011
SP - 334
EP - 339
BT - Proceedings - 7th International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2011
T2 - 7th International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2011
Y2 - 28 November 2011 through 1 December 2011
ER -