Feature detection method of fingertip and palm based on depth image

doi:10.11772/j.issn.1001-9081.2015.06.1791

Journal of Computer Applications ›› 2015, Vol. 35 ›› Issue (6): 1791-1794.DOI: 10.11772/j.issn.1001-9081.2015.06.1791

Previous Articles Next Articles

Feature detection method of fingertip and palm based on depth image

FAN Wenjie¹, WANG Mingyan¹, YANG Wenji²

1. School of Information Engineering, Nanchang University, Nanchang Jiangxi 330031, China;
2. School of Software Design, Jiangxi Agriculture University, Nanchang Jiangxi 330045, China

Received:2014-12-22 Revised:2015-03-26 Online:2015-06-12

基于深度图像的指尖和掌心特征提取方法

范文婕¹, 王命延¹, 杨文姬²

1. 南昌大学信息工程学院, 南昌 330031;
2. 江西农业大学软件学院, 南昌 330045

通讯作者: 杨文姬(1984-),女,江西上饶人,讲师,硕士,主要研究方向:计算机视觉、模式识别、人工智能。yangwenji614@163.com
作者简介:范文婕(1991-),女,江西抚州人,硕士研究生,主要研究方向:人工智能;王命延(1959-),男,安徽宣城人,教授,CCF会员,主要研究方向:人工智能、软件工程.
基金资助:
国家自然科学基金资助项目(61462038)。

Abstract

Abstract:

To solve the gesture segmentation deviation problem under the interference of other skins and overlapping objects, a method of using depth data and skeleton tracking to segment gesture accurately was proposed. The minimum circumscribed circle, the average and the maximal inscribed circle of convexity defect, were combined to improve the detection of palm and the palm region's radius of various gesture. A fingertip candidate set was got through integrating the finger arc with convex hull, then real fingertips were obtained with three-step filtering. Six gestures have been tested in four transform cases, the recognition rate of flip, parallel, overlapping are all higher than 90% but the rate decreases obviously when tilting more than 70 degree and yawing more than 60 degree. The experimental results show that the accuracy of the proposed method is high in a variety of real scenes.

Key words: gesture segmentation, convexity defect, minimum circumscribed circle, palm, fingertip arc, convex hull

摘要：

针对在其他肤色和重叠物干扰下手势分割出现偏差的问题,提出深度数据和骨骼追踪实现准确手势分割。结合凸缺陷的最小外接圆、平均值、最大内切圆三种不同的掌心提取方法来提高不同手势下掌心和掌心区域半径的精确度,通过提取出指尖弧并结合凸包来得到拟指尖集,再通过3步过滤来得到准确的指尖。实验中对6种手势进行了4种变换情况下的检验,其中翻转、平行、重叠的识别率都高于90%,倾斜和偏转分别超过70°、60°时准确度明显下降。实验结果表明了该方法在多种真实手势场景下具有较高的准确率。

关键词: 手势分割, 凸缺陷, 最小外接圆, 掌心, 指尖弧, 凸包

CLC Number:

TP391.41

FAN Wenjie, WANG Mingyan, YANG Wenji. Feature detection method of fingertip and palm based on depth image[J]. Journal of Computer Applications, 2015, 35(6): 1791-1794.

范文婕, 王命延, 杨文姬. 基于深度图像的指尖和掌心特征提取方法[J]. 计算机应用, 2015, 35(6): 1791-1794.

References

[1] SUAREZ J, MURPHY R R. Hand gesture recognition with depth images: a review [C]//Proceedings of the 2012 IEEE RO-MAN.Piscataway: IEEE, 2012: 411-417.
[2] MITRA S, ACHARYA T. Gesture recognition: a survey [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 2007, 37(3): 311-324.
[3] EROL A, BEBIS G, NICOLESCU M. Vision-based hand pose estimation: a review [J]. Computer Vision and Image Understanding, 2007, 108(1/2): 52-73.
[4] MALASSISOTIS S, AIFANTI N, STRINTZIS M G. A gesture recognition system using 3D data [C]//TDPVT 2002: Proceedings of the First International Symposium on 3D Data Processing Visualization and Transmission. Piscataway: IEEE, 2002: 190-193.
[5] KOLSCH M, TURK M. Robust hand detection [C]//AFGR 2004: Proceedings of the 2004 International Conference on Automatic Face and Gesture Recognition. Piscataway: IEEE, 2004: 614-619.
[6] ONG E-J, BOWDEN R. A boosted classifier tree for hand shape detection [C]//AFGR 2004: Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition. Piscataway: IEEE, 2004: 889-894.
[7] RAHEJA J L, CHAUDHARY A, SINGAL K. Tracking of fingertips and centers of palm using KINECT [C]//CIMSiM 2011: Proceedings of the 2011 Third International Conference on Computational Intelligence, Modelling and Simulation. Piscataway: IEEE, 2011: 248-252.
[8] WANG X, WANG R, ZHOU F. Fingertips detection and hand tracking based on curve fitting [C]//CISP 2014: Proceedings of the 2014 7th International Congress on Image and Signal Processing. Piscataway: IEEE, 2014: 99-103.
[9] CAO C, LI R, ZHAO L. Hand posture recognition method based on depth image technology [J]. Computer Engineering, 2012, 38(8): 16-21. (曹雏清, 李瑞峰, 赵立军.基于深度图像技术的手势识别方法[J]. 计算机工程, 2012, 38(8):16-2.)
[10] LI B, LIN F. Fingertip detection method based on curvature [J]. Journal of Nanjing University of Aeronautics & Astronautics, 2012, 44(4): 587-591. (李博男, 林凡.基于曲率的指尖检测方法[J].南京航空航天大学学报, 2012, 44(4):587-591.)
[11] YU Y, SONG Y, ZHANG Y. Real time fingertip detection with Kinect depth image sequences [C]//ICPR 2014: Proceedings of the 2014 International Conference on Pattern Recognition. Piscataway. IEEE, 2014: 550-555.
[12] GANAPATHYRAJU S. Hand gesture recognition using convexity hull defects to control an industrial robot [C]//ICA 2013: Proceedings of the 2013 International Conference on Instrumentation Control an Automation. Piscataway: IEEE, 2013: 63-67.
[13] BISWAS K K, BASU S K. Gesture recognition using Microsoft Kinect [C]//ICARA 2011: Proceedings of the 2011 5th International Conference on Automation, Robotics and Applications. Piscataway: IEEE, 2011: 100-103.
[14] DROESCHEL D, STUCKLER J. BEHNKS S. Learning to interpret pointing gestures with a time-of-flight camera [C]//HRI 2011: Proceedings of the 2011 ACM/IEEE International Conference on Human-Robot Interaction. New York: ACM, 2011: 481-488.
[15] CHEN C, CHEN Y., LEE P, et al. Real-time hand tracking on depth images [C]//VCIP 2011: Proceedings of the 2011 IEEE International Conference on Visual Communications and Image Processing. Piscataway: IEEE, 2011:1-4.
[16] WEN X, NIU Y. A method for hand gesture recognition based on morphology and fingertip-angle [C]//ICCAE 2010: Proceedings of 2010 the 2nd International Conference on Computer and Automation Engineering. Piscataway: IEEE, 2010: 688-691.
[17] LARSEN B, AONE C. Fast and effective text mining using linear-time document clustering [C]//Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 1999: 16-22.

Feature detection method of fingertip and palm based on depth image

基于深度图像的指尖和掌心特征提取方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	WANG Yajie, ZHANG Yunbo, WU Yanyan, DING Aodong, QI Bingzhi. General chess piece positioning method under uneven illumination [J]. Journal of Computer Applications, 2020, 40(12): 3490-3498.
[2]	LOU Mengying, WANG Tianjing, LIU Yaqin, YANG Feng, HUANG Jing. Palm vein image recognition based on side chain connected convolution neural network [J]. Journal of Computer Applications, 2020, 40(12): 3673-3678.
[3]	ZHU Kai, FU Zhongliang, CHEN Xiaoqing. Left ventricular segmentation method of ultrasound image based on convolutional neural network [J]. Journal of Computer Applications, 2019, 39(7): 2121-2124.
[4]	LIU Yuzhen, JIANG Zhengquan, ZHAO Na. Three dimensional palmprint recognition based on neighbor ternary pattern and collaborative representation [J]. Journal of Computer Applications, 2019, 39(6): 1690-1695.
[5]	LOU Mengying, YUAN Lisha, LIU Yaqin, WAN Xuemei, YANG Feng. Palm vein enhancement method based on adaptive fusion [J]. Journal of Computer Applications, 2019, 39(4): 1176-1182.
[6]	LIN Haibo, WANG Shengbin, ZHANG Yi. Gesture segmentation and positioning based on improved depth information [J]. Journal of Computer Applications, 2017, 37(1): 251-254.
[7]	SHI Lixing, HU Fangyu. Users' mobility analysis based on call detail record in two-dimensional space [J]. Journal of Computer Applications, 2015, 35(9): 2453-2456.
[8]	LI Junhao, LIU Zhi. Object detection based on visual saliency map and objectness [J]. Journal of Computer Applications, 2015, 35(12): 3560-3564.
[9]	WEI Shang-qing GU Xiao-dong. Palm-dorsal vein recognition based on uniform discrete curvelet transformation [J]. Journal of Computer Applications, 2012, 32(04): 1122-1125.
[10]	ZHANG Jing XU Li ZHANG Shun-miao. α-hulls based localization for Jamming attack in wireless sensor network [J]. Journal of Computer Applications, 2012, 32(02): 461-464.
[11]	SHANG Li SU Pingang DU Jixiang. Palmprint recognition method based on localized non-negative sparse coding [J]. Journal of Computer Applications, 2011, 31(06): 1609-1612.
[12]	. Symmetry axes search of 2D point set based on convex hull technology [J]. Journal of Computer Applications, 2010, 30(4): 905-908.
[13]	. Palm-dorsa vein recognition based on two-dimensional Fisher linear discriminant [J]. Journal of Computer Applications, 2010, 30(3): 646-649.
[14]	. Voronoi diagram generation algorithm based on Delaunay triangulation [J]. Journal of Computer Applications, 2010, 30(1): 75-77.
[15]	Chuang YANG Jia-xin CHEN Wei LI. Palm vein features extraction based on median-length included angle chain [J]. Journal of Computer Applications, 2009, 29(11): 3048-3050.