正在加载图片...
·434 智能系统学报 第10卷 [6]DARDAS N H,GEORGANAS N D.Real-time hand gesture 5 结束语 detection and recognition using bag-of-features and support 本文提出了一种基于空间金字塔特征包的特征 vector machine techniques[J].IEEE Transaction on Instru- 对手势图像进行表示,该方法相比于传统的BoF mentation and Measurement,2011,60(11):3592-3607. SIFT方法的优势在于能同时从局部和全局描述手 [7]JIANG Yugang,NGO C W,YANG Jun.Towards optimal 势图像的特征点,还能描述特征点的分布特性。采 bag-of-features for object categorization and semantic video 用直方图相交核支持向量机对所提取特征进行识 retrieval[C]//Proceedings of the 6th ACM International 别,该方法的优点在于无需选择参数,增加了系统的 Conference on Image and Video Retrieval.New York,USA, 稳定性。实验表明了新方法的有效性。后续工作将 2007:494-501. 考虑与其他识别算法的融合,以进一步提高识别的 [8]CHUANG Yuelong,CHEN Ling,CHEN Gencai.Hierarchi- cal bag-of-features for hand gesture recognition[C]//Pro- 准确率。 ceedings of 18th IEEE International Conference on Image 参考文献: Processing.Brussels,Belgium,2011:1777-1780. [9]LOWE D G.Distinctive image features from scale-invariant [1]隋云衡,郭元术.融合Hu矩与BoF-SURF支持向量机的 keypoints[J].International Journal of Computer Vision, 手势识别[J].计算机应用研究,2013,31(3):953-956, 2004,60(2):91-110. 960 [10]LAZEBNIK S,SCHMID C,PONCE J.Beyond bags of fea- SUI Yunheng,GUO Yuanshu.Hand gesture recognition tures:Spatial pyramid matching for recognizing natural based on combining Hu moments and BoF-SURF support scene categories[C]//Proceedings of the 2006 IEEE Com- vector machine[J].Application Research of Computers, puter Society Conference on Computer Vision and Pattern 2013,31(3):953-956,960. Recognition.New York,USA,2006:2169-2178. [2]张良国,吴江琴,高文,等.基于Hausdorff距离的手势 [11]ARTHER D,VASSILVITSKII S.K-means++:the advan- 识别[J刀.中国图象图形学报,2002,7(11):1144-1150. tages of careful seeding [C]//Proceedings of the Eigh- ZHANG Liangguo,WU Jiangqin,GAO Wen,et al.Hand teenth Annual ACM-SIAM Symposium on Discrete Algo- gesture recognition based on Hausdorff distance[J].Journal rithms.New York,USA,2007:1027-1035. of Image and Graphics,2002,7(11):1144-1150. [12]易晓梅,吴鹏,刘丽娟,等.一种基于改进支持向量机 [3]黄国范,毛红阁.基于切线距离的中国手指语字母手势 的入侵检测方法研究[J].计算机工程与应用,2012, 识别[J].吉林化工学院学报,2013,30(3):79-81. 48(15):74-77. HUANG Guofan,MAO Hongge.Tangent distance-based YI Xiaomei,WU Peng,LIU Lijuan,et al.Intrusion detec- Chinese finger alphabet gesture recognition[J].Journal of tion method based on improved SVM[J].Computer Engi- Jilin Institute of Chemical Technology,2013,30(3):79- neering and Applications,2012,48(15):74-77. 81 [13]BARLA A,ODONE F,VERRI A.Histogram intersection [4]张汗灵,李红英,周敏.融合多特征和压缩感知的手势 kernel for image classification C//Proceedings of Inter- 识别J].湖南大学学报:自然科学版,2013,40(3):87- national Conference on Image Processing.Barcelona, 92 Spain,2003:513-516. ZHANG Hanling,LI Hongying,ZHOU Min.Hand posture [14]CHANG C C,LIN C J.LIBSVM:a library for support vec- recognition based on multi-feature and compressive sensing tor machines[EB/OL].[2014-05-10].http://www.csie. [J].Journal of Hunan University:Natural Sciences,2013, ntu.edu.tw/cjlin/libsvm. 40(3):87-92. [15]TRIESCH J.MALSBURG C,MARCEL S.Hand posture [5]丁友东,庞海波,吴学纯,等.一种用于手势识别的局 and gesture datasets:Jochen Triesch static hand posture 部均值模式纹理描述子[J].应用科学学报,2013,31 database[EB/OL].[2014-05-10].http://www.idiap.ch/ (5):526-532 resources/gestures/. DING Youdong,PANG Haibo,WU Xuechun,et al.Local [16]JUST A,RODRIGUEZ Y,MARCEL S.Hand posture clas- mean pattern texture descriptor for gesture recognition[J]. sification and recognition using the modified census trans- Journal of Applied Sciences,2013,31(5):526-532. form[C]//Proceedings of the IEEE International Confer-5 结束语 本文提出了一种基于空间金字塔特征包的特征 对手势图像进行表示,该方法相比于传统的 BoF⁃ SIFT 方法的优势在于能同时从局部和全局描述手 势图像的特征点,还能描述特征点的分布特性。 采 用直方图相交核支持向量机对所提取特征进行识 别,该方法的优点在于无需选择参数,增加了系统的 稳定性。 实验表明了新方法的有效性。 后续工作将 考虑与其他识别算法的融合,以进一步提高识别的 准确率。 参考文献: [1]隋云衡, 郭元术. 融合 Hu 矩与 BoF⁃SURF 支持向量机的 手势识别[J]. 计算机应用研究, 2013, 31(3): 953⁃956, 960. SUI Yunheng, GUO Yuanshu. Hand gesture recognition based on combining Hu moments and BoF⁃SURF support vector machine [ J ]. Application Research of Computers, 2013, 31(3): 953⁃956, 960. [2]张良国, 吴江琴, 高文, 等. 基于 Hausdorff 距离的手势 识别[J]. 中国图象图形学报, 2002, 7(11): 1144⁃1150. ZHANG Liangguo, WU Jiangqin, GAO Wen, et al. Hand gesture recognition based on Hausdorff distance[J]. Journal of Image and Graphics, 2002, 7(11): 1144⁃1150. [3]黄国范, 毛红阁. 基于切线距离的中国手指语字母手势 识别[J]. 吉林化工学院学报, 2013, 30(3): 79⁃81. HUANG Guofan, MAO Hongge. Tangent distance⁃based Chinese finger alphabet gesture recognition [ J]. Journal of Jilin Institute of Chemical Technology, 2013, 30( 3): 79⁃ 81. [4]张汗灵, 李红英, 周敏. 融合多特征和压缩感知的手势 识别[J]. 湖南大学学报:自然科学版, 2013, 40(3): 87⁃ 92. ZHANG Hanling, LI Hongying, ZHOU Min. Hand posture recognition based on multi⁃feature and compressive sensing [J]. Journal of Hunan University: Natural Sciences, 2013, 40(3): 87⁃92. [5]丁友东, 庞海波, 吴学纯, 等. 一种用于手势识别的局 部均值模式纹理描述子[ J]. 应用科学学报, 2013, 31 (5): 526⁃532. DING Youdong, PANG Haibo, WU Xuechun, et al. Local mean pattern texture descriptor for gesture recognition[ J]. Journal of Applied Sciences, 2013, 31(5): 526⁃532. [6]DARDAS N H, GEORGANAS N D. Real⁃time hand gesture detection and recognition using bag⁃of⁃features and support vector machine techniques[J]. IEEE Transaction on Instru⁃ mentation and Measurement, 2011, 60(11): 3592⁃3607. [7] JIANG Yugang, NGO C W, YANG Jun. Towards optimal bag⁃of⁃features for object categorization and semantic video retrieval[ C] / / Proceedings of the 6th ACM International Conference on Image and Video Retrieval. New York, USA, 2007: 494⁃501. [8]CHUANG Yuelong, CHEN Ling, CHEN Gencai. Hierarchi⁃ cal bag⁃of⁃features for hand gesture recognition [ C] / / Pro⁃ ceedings of 18th IEEE International Conference on Image Processing. Brussels, Belgium, 2011: 1777⁃1780. [9]LOWE D G. Distinctive image features from scale⁃invariant keypoints [ J ]. International Journal of Computer Vision, 2004, 60(2): 91⁃110. [10]LAZEBNIK S, SCHMID C, PONCE J. Beyond bags of fea⁃ tures: Spatial pyramid matching for recognizing natural scene categories[C] / / Proceedings of the 2006 IEEE Com⁃ puter Society Conference on Computer Vision and Pattern Recognition. New York, USA, 2006: 2169⁃2178. [11]ARTHER D, VASSILVITSKII S. K⁃means++: the advan⁃ tages of careful seeding [ C] / / Proceedings of the Eigh⁃ teenth Annual ACM⁃SIAM Symposium on Discrete Algo⁃ rithms. New York, USA, 2007: 1027⁃1035. [12]易晓梅, 吴鹏, 刘丽娟, 等. 一种基于改进支持向量机 的入侵检测方法研究[ J]. 计算机工程与应用, 2012, 48(15): 74⁃77. YI Xiaomei, WU Peng, LIU Lijuan, et al. Intrusion detec⁃ tion method based on improved SVM[ J]. Computer Engi⁃ neering and Applications, 2012, 48(15): 74⁃77. [13]BARLA A, ODONE F, VERRI A. Histogram intersection kernel for image classification[C] / / Proceedings of Inter⁃ national Conference on Image Processing. Barcelona, Spain, 2003: 513⁃516. [14]CHANG C C, LIN C J. LIBSVM: a library for support vec⁃ tor machines[EB/ OL]. [ 2014⁃05⁃10]. http: / / www. csie. ntu.edu.tw/ cjlin / libsvm. [15] TRIESCH J, MALSBURG C, MARCEL S. Hand posture and gesture datasets: Jochen Triesch static hand posture database[EB/ OL]. [2014⁃05⁃10]. http: / / www.idiap.ch / resources/ gestures/ . [16]JUST A, RODRIGUEZ Y, MARCEL S. Hand posture clas⁃ sification and recognition using the modified census trans⁃ form[C] / / Proceedings of the IEEE International Confer⁃ ·434· 智 能 系 统 学 报 第 10 卷
<<向上翻页向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有