基于改进的SIFT算子和SVM分类器的瞳孔中心定位

田耘; 甄雯; 赵海军

doi:doi:10.3788/yjyxs20173206.0499

液晶与显示, 2017, 32 (6): 499, 网络出版: 2017-06-27

基于改进的SIFT算子和SVM分类器的瞳孔中心定位

Accurate pupil center location with SIFT descriptor and SVM classifier

论文大纲

田耘 ^*甄雯赵海军

作者单位

北京电子科技职业学院, 北京 100176

瞳孔定位分类器 SIFT特征修正矩形框 pupil center localization classification SIFT feature correction rectangular block

摘要

瞳孔定位的精确度很大程度取决于图片质量, 但实际应用中通常要在低质量图片下进行瞳孔定位。我们的目标是在图片质量不佳的情况下进行精确的瞳孔中心定位。对于这个目标, 本文提出一种基于改进SIFT特征和SVM分类器的瞳孔中心初始定位方法, 并通过一个大小可变的修正矩形框得到最终瞳孔中心位置。实验结果表明, 相比于其他国内外先进方法, 本文的方法可以在低质量(光照不均、表情变化等)图片上拥有更高的瞳孔定位精度, 定位结果在瞳孔区域内的精度为87.32%。

Abstract

The accuracy of gaze tracking largely depends on the quality of images, but additional constraints and large amount of calculation make gaze tracking impractical on high-resolution images. Our aim is to get the accurate localization of pupil center on low-resolution image. To this aim, we proposed a simple but effective method which can accurately locate pupil center in real time. The method first gets initial eye center based on improved SIFT descriptor and SVM classifier, and then gets final position of the pupil center through a size variable correction rectangular block. In this paper, comparing with the reported state-of-the-art methods, the experimental results demonstrate that our system can achieve a more accurate result on low-resolution images, the precision of positioning result in the pupil area was 87.32%.

参考文献

[1] DUCHOWSKI A. Eye Tracking Methodology: Theory and Practice [M]. London: Springer, 2007.

[2] SUGANO Y, MATSUSHITA Y, SATO Y. Appearance-based gaze estimation using visual saliency [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(2): 329-341.

[3] CAMPADELLI P, LANZAROTTI R, LIPORI G. Precise eye localization through a general-to-specific model definition [C]//Proceedings of the British Machine Vision Conference. Edinburgh, Scotland: BMVC, 2006: 187-196.

[4] TIMM F, BARTH E. Accurate eye centre localisation by means of gradients [C]//Proceedings of the Sixth International Conference on Computer Vision Theory and Applications. Vilamoura, Algarve, Portugal: VISAPP, 2011: 125-130.

[5] VALENTI R, GEVERS T. Accurate eye center location through invariant isocentric patterns [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(9): 1785-1798.

[6] MARKU N, FRLJAK M, PANDIC＇I S, et al. Eye pupil localization with an ensemble of randomized trees [J]. Pattern Recognition, 2014, 47(2): 578-587.

[7] KOTHARI R, MITCHELL J L. Detection of eye locations in unconstrained visual images [C]//Proceedings of International Conference on Image Processing. Lausanne: IEEE, 1996, 3: 519-522.

[8] KROON B, HANJALIC A, MAAS S M P. Eye localization for face matching: is it always useful and under what conditions[C]//Proceedings of the 2008 International Conference on Content-based Image and Video Retrieval. New York, NY, USA: ACM, 2008: 379-388.

[9] MIKOLAJCZYK K, SCHMID C. A performance evaluation of local descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630.

[10] HE X F,CAI D, HAN J W. Learning a maximum margin subspace for image retrieval [J]. IEEE Transactions on Knowledge and Data Engineering, 2008, 20(2): 189-201.

田耘, 甄雯, 赵海军. 基于改进的SIFT算子和SVM分类器的瞳孔中心定位[J]. 液晶与显示, 2017, 32(6): 499. TIAN Yun, ZHEN Wen, ZHAO Hai-jun. Accurate pupil center location with SIFT descriptor and SVM classifier[J]. Chinese Journal of Liquid Crystals and Displays, 2017, 32(6): 499.

基于改进的SIFT算子和SVM分类器的瞳孔中心定位

关于本站 Cookie 的使用提示

全站搜索

基于改进的SIFT算子和SVM分类器的瞳孔中心定位

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索