|Table of Contents|

Fast Face Detection Based on Walsh Feature and Enhanced Cascade Algorithm

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2008年01期
Page:
60-64
Research Field:
Publishing date:

Info

Title:
Fast Face Detection Based on Walsh Feature and Enhanced Cascade Algorithm
Author(s):
GUO Zhi-bo12YAN Yun-yang1YANG Jing-yu1
1.School of Information Engineering,Yangzhou University,Yangzhou 225009,China;2.School of Computer Science and Technology,NUST,Nanjing 210094,China
Keywords:
Walsh feature AdaBoost enhanced Cascade face detection
PACS:
TP391.41
DOI:
-
Abstract:
The training time cost is very expensive when mass Haar-Like features are used to obtain the face detector based on AdaBoost and Cascade algorithm.The paper presents a Walsh feature to replace Haar-Like feature in the training process,which can decrease the redundancy among the features and save the training time and memory.Aiming at the shortage of entirely inheriting prior classifiers in the Nesting Cascade algorithm,an enhanced Cascade algorithm that has independence characteristic and inheritance speciality is proposed.The experimental results from MIT-CBCL database show that the Walsh feature can accelerate the training process and the enhanced Cascade algorithm can increase the test precision.A trained face detector is used to detect faces in the MIT+CMU test set,and the detected results demonstrate that the proposed algorithm is more effective than other correlative methods.

References:

[1]Freund Y, Schap ire R E. Exper iments w ith a new boosting algor ithm [ A]. Proceedings of the 13 th Con ference onM ach ine Learning [ C ]. USA: Interna tion alM ach ine Learn ing Soc ie ty, 1996. 148- 156.
[2] Schap ire R E, Singer Y. Improved boosting a lgo rithm s using con fidencera ted pred ictions [ J]. M a ch ine Learn ing, 1999, 37( 3) : 297- 336.
[3] 李闯, 丁晓青, 吴佑寿. 一种改进的AdaBoost算 法ADAdaBoost [ J]. 计算机学报, 2007, 30( 1): 103- 109.
[4] L iu C, Shum H. KullbackLe ibler Boosting [ A]. Pro ceed ing s of IEEE Conference on CVPR, 2003 [ C ]. W ashington, D. C. , USA: IEEE Computer So ciety, 2003. 587- 594.
[5] Li S Z, Zhang Z. Floatboost lea rning and sta tistica l face de tection [ J]. IEEE T rans on Patte rn Ana lysis andM ach ine In tellig ence, 2004, 26 ( 9 ): 1 112- 1 123.
[6] H uang C, A iH Z, LiY, et a.l H ighperform ance ro tation invarian t mu ltiv iew face detection [ J]. IEEE Trans on Pattern Ana lys is and M ach ine Inte lligence, 2007, 29( 4): 671- 686.
[7] V io la P, JonesM. Rapid object detection using a boos ted cascade of sim ple features [ A ]. Proceedings o f IEEE Conference on CVPR, 2001 [ C ]. W ashington, D. C. , USA: IEEE Com puter Soc iety, 2001. 511- 518.
[8] X iao R, Zhu L, Zhang H J. Boosting cha in learn ing fo r object de tection [ A ]. Proceed ings o f IEEE Con fe r ence on ICCV, 2003 [ C]. W ashington, D. C. , USA: IEEE Computer Soc ie ty, 2003. 709- 715.
[9] Wu B, A iH Z, H uang C, et a.l Fast ro tation invar i ant m ultiv iew face de tection based on rea l AdaBoost [ A]. Proceed ing s o f IEEE Con ference on FGR, 2004 [ C ]. W ash ington, D. C. , USA: IEEE Compu ter So c iety, 2004. 79- 84.

Memo

Memo:
-
Last Update: 2012-12-05