An Interactive Image Segmentation Method in Hand Gesture Recognition

被引:55
作者
Chen, Disi [1 ]
Li, Gongfa [1 ]
Sun, Ying [1 ]
Kong, Jianyi [1 ]
Jiang, Guozhang [1 ]
Tang, Heng [1 ]
Ju, Zhaojie [2 ]
Yu, Hui [2 ]
Liu, Honghai [2 ]
机构
[1] Wuhan Univ Sci & Technol, Sch Machinery & Automat, Wuhan 430081, Peoples R China
[2] Univ Portsmouth, Sch Comp, Portsmouth PO1 3HE, Hants, England
基金
中国国家自然科学基金; 英国工程与自然科学研究理事会;
关键词
image segmentation; Gibbs Energy; min-cut/max-flow algorithm; sparse representation; SURFACE EMG; CLASSIFICATION; SIGNALS; MODELS;
D O I
10.3390/s17020253
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
In order to improve the recognition rate of hand gestures a new interactive image segmentation method for hand gesture recognition is presented, and popular methods, e.g., Graph cut, Random walker, Interactive image segmentation using geodesic star convexity, are studied in this article. The Gaussian Mixture Model was employed for image modelling and the iteration of Expectation Maximum algorithm learns the parameters of Gaussian Mixture Model. We apply a Gibbs random field to the image segmentation and minimize the Gibbs Energy using Min-cut theorem to find the optimal segmentation. The segmentation result of our method is tested on an image dataset and compared with other methods by estimating the region accuracy and boundary accuracy. Finally five kinds of hand gestures in different backgrounds are tested on our experimental platform, and the sparse representation algorithm is used, proving that the segmentation of hand gesture images helps to improve the recognition accuracy.
引用
收藏
页数:17
相关论文
共 40 条
[1]  
[Anonymous], 2015, INT J IMAGE PROCESS
[2]  
[Anonymous], P IEEE 11 INT C COMP
[3]  
[Anonymous], The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results
[4]   MAXIMUM LIKELIHOOD ESTIMATION OF FACTOR MODELS ON DATASETS WITH ARBITRARY PATTERN OF MISSING DATA [J].
Banbura, Marta ;
Modugno, Michele .
JOURNAL OF APPLIED ECONOMETRICS, 2014, 29 (01) :133-160
[5]   Adaptive classification of hyperspectral images using local consistency [J].
Bian, Xiaoyong ;
Zhang, Xiaolong ;
Liu, Renfeng ;
Ma, Li ;
Fu, Xiaowei .
JOURNAL OF ELECTRONIC IMAGING, 2014, 23 (06)
[6]  
Chen Q., 2007, P EEE INSTRUMENTATIO, P1
[7]   The Thermodynamic Properties of MgSiO3 Perovskite by Using a New Set Interaction Potential Parameters [J].
Chen, Qiong .
JOURNAL OF COMPUTATIONAL AND THEORETICAL NANOSCIENCE, 2015, 12 (07) :1263-1265
[8]  
Couprie C, 2011, BIOL MED PHYS BIOMED, P27, DOI 10.1007/978-1-4419-9779-1_3
[9]   Power watersheds: A new image segmentation framework extending graph cuts, random walker and optimal spanning forest [J].
Couprie, Camille ;
Grady, Leo ;
Najman, Laurent ;
Talbot, Hugues .
2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2009, :731-738
[10]   The Extraction of Neural Information from the Surface EMG for the Control of Upper-Limb Prostheses: Emerging Avenues and Challenges [J].
Farina, Dario ;
Jiang, Ning ;
Rehbaum, Hubertus ;
Holobar, Ales ;
Graimann, Bernhard ;
Dietl, Hans ;
Aszmann, Oskar C. .
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2014, 22 (04) :797-809