混合点状和非规则军标的在线手绘识别

邓维; 吴玲达; 张友根; 赵志鹏

doi:10.13700/j.bh.1001-5965.2014.0826

混合点状和非规则军标的在线手绘识别

doi: 10.13700/j.bh.1001-5965.2014.0826

1.
装备学院复杂电子系统仿真实验室, 北京 101416
2. 国防信息学院信息系统系, 武汉 430010
3. 桂林电子科技大学信息科技学院, 桂林 541004

基金项目: "核高基"国家科技重大专项(2013ZX01045-004)

详细信息

作者简介:
邓维(1986-),男,湖北武汉人,博士研究生,dengwei@whu.edu.cn

通讯作者:
吴玲达(1962-),女,上海人,教授,wld@nudt.edu.cn,主要研究方向为空间信息获取与处理.

中图分类号: TP391
计量
- 文章访问数: 1021
- HTML全文浏览量: 95
- PDF下载量: 394
- 被引次数: 0
出版历程
- 收稿日期: 2014-12-30
- 修回日期: 2015-04-10
- 网络出版日期: 2015-10-20

Online sketch recognition for mixed point and irregular military symbols

1.
Science and Technology on Complex Electronic System Simulation Laboratory, Academy of Equipment, Beijing 101416, China
2. Department of Information Systems, Academy of National Defense Information, Wuhan 430010, China
3. Institute of Information Technology of Guilin, Guilin 541004, China

摘要

摘要: 当前对在线手绘军标图符识别的研究只针对单一类型的手绘点状军标或非规则军标,分别使用不同方法进行识别.但在特殊应用中二者常混合输入,当待识别军标图符的类型未知时,如何识别是一个重要问题.提出一种基于最小生成树(MST)覆盖模型的混合识别方法,训练阶段,分别对点状和非规则军标样本建立MST覆盖模型,并训练一个二分类支持向量机(SVM)分类器;识别阶段,先通过几何和结构信息粗判断军标类型,再通过置信度估计和融合的方法确定未知军标的类型.在113类点状军标和36类非规则军标的数据集中实验,军标类型区分准确率为94.7%,最终识别率为91.6%,且能满足实时要求.
- 草图识别 /
- 点状军标 /
- 非规则军标 /
- 最小生成树(MST) /
- 分类
Abstract: Most of current research on online sketched military symbols recognition concerns only one type of symbols, point symbols or irregular symbols, using different methods to recognize separately. But in practical applications the two types of symbols are mixed. It becomes a major issue to find a way to recognize a type-unknown military symbol. A minimum spanning tree (MST) covering model-based mixed recognition method was proposed. In the training phase, two MST-based covering models were built for point and irregular symbols respectively. And then a two-class support vector machine (SVM) classifier was trained. In the recognition phase, the coarse type identification was accomplished by using the geometrical and structural information firstly. Then the confidence estimations were calculated and integrated to identify the type of the unknown symbol. Different types of symbols were classified by two existing modules. The algorithm was tested on 113 classes of point symbols and 36 classes of irregular symbols. The accuracy rate of symbol type identification was 94.7%, and the final recognition rate was 91.6% in real time.
- sketch recognition /
- point military symbol /
- irregular military symbol /
- minimum spanning tree (MST) /
- classify

HTML全文

参考文献(21)

[1]	Sun Z B,Wang C H,Zhang L Q,et al.Query-adaptive shape topic mining for hand-drawn sketch recognition[C]∥Proceedings of 20th ACM International Conference on Multimedia.New York:ACM,2012:519-528.
[2]	巩应奎,范玉青,吴志方.笔式草图的增量识别[J].北京航空航天大学学报,2006,32(5):621-624.Gong Y K,Fan Y Q,Wu Z F.Incremental recognition method for pen-based sketch[J].Journal of Beijing University of Aeronautics and Astronautics,2006,32(5):621-624(in Chinese).
[3]	陈鸿,汤晓安,杨耀明,等.基于位移映射的非规则军队标号绘制算法[J].计算机辅助设计与图形学学报,2011,23(5):797-804.Chen H,Tang X A,Yang Y M,et al.Using displacement mapping for irregular military symbols rendering[J].Journal of Computer-Aided Design & Computer Graphics,2011,23(5):797-804(in Chinese).
[4]	邓维,吴玲达,张友根,等.采用快速图元匹配的手绘非规则军标识别[J].计算机辅助设计与图形学学报,2014,26(10):1835-1843.Deng W,Wu L D,Zhang Y G,et al.Using fast primitive matching to recognize sketched irregular military marking symbols[J].Journal of Computer-Aided Design & Computer Graphics,2014,26(10):1835-1843(in Chinese).
[5]	吴玲达,张友根,邓维,等.面向手绘军标图形的旋转自由识别方法[J].中国图象图形学报,2014,19(3):456-462.Wu L D,Zhang Y G,Deng W,et al.Rotation free recognition of hand-drawn military marking symbols[J].Journal of Image and Graphics,2014,19(3):456-462(in Chinese).
[6]	Hammond T,Logsdon D,Peschel J,et al.A sketch recognition interface that recognizes hundreds of shapes in course-of-action diagrams[C]∥Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI).New York:ACM,2010:4213-4218.
[7]	Cummings D,Fymat S,Hammond T.Sketch-based interface for interaction with unmanned air vehicles[C]∥Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems,2012.
[8]	Deng W,Wu L D,Yu R H,et al.On-line sketch recognition using direction feature[C]∥Proceedings of Human-Computer Interaction (INTERACT 2013).Heidelberg:Springer Verlag,2013:259-266.
[9]	Delaye A,Liu C L.Contextual text/non-text stroke classification in online handwritten notes with conditional random fields[J].Pattern Recognition,2014,47(3):959-968.
[10]	Malakar S,Das R K,Sarkar R,et al.Handwritten and printed word identification using gray-scale feature vector and decision tree classifier[J].Procedia Technology,2013,10:831-839.
[11]	Song Y H,Xiao G L,Zhang Y L,et al.A handwritten character extraction algorithm for multi-language document image[C]∥Proceedings of 11th International Conference on Document Analysis and Recognition (ICDAR).Piscataway,NJ:IEEE Press,2011:93-98.
[12]	Rani R,Dhir R,Lehal G S.Script identification of pre-segmented multi-font characters and digits[C]∥Proceedings of 12th International Conference on Document Analysis and Recognition (ICDAR).Piscataway,NJ:IEEE Press,2013:1150-1154.
[13]	付强,丁晓青,蒋焰.基于多信息融合的中文手写地址字符串切分与识别[J].电子与信息学报,2008,30(12):2916-2920.Fu Q,Ding X Q,Jiang Y.Segmentation and recognition algorithm for Chinese handwritten address character string[J].Journal of Electronics & Information Technology,2008,30(12):2916-2920(in Chinese).
[14]	Blagojevic R,Chang S H H,Plimmer B.The power of automatic feature selection:Rubine on steroids[C]∥Proceedings of the Seventh Sketch-Based Interfaces and Modeling Symposium (SBIM).Goslar:Eurographics Association,2010:79-86.
[15]	Paulson B,Hammond T.PaleoSketch:Accurate primitive sketch recognition and beautification[C]∥Proceedings of 13th International Conference on Intelligent User Interfaces (IUI2008).New York:ACM,2008:1-10.
[16]	Paulson B.Rethinking pen input interaction:Enabling freehand sketching through improved primitive recognition[D].State of Texas:Texas A&M University,2010.
[17]	胡正平,冯凯.高维空间多分辨率最小生成树模型的自适应一类分类算法[J].自动化学报,2012,38(5):769-775.Hu Z P,Feng K.An adaptive one-class classification algorithm based on multi-resolution minimum spanning tree model in high-dimensional space[J].Acta Automatic Sinica,2012,38(5):769-775(in Chinese).
[18]	谢毓湘,栾悉道,陈丹雯,等.一种基于局部不变特征的图像特定场景检测方法[J].国防科技大学学报,2013,35(6):78-83.Xie Y X,Luan X D,Chen D W,et al.A method of specific image scene detection based on local invariant features[J].Journal of National University of Defense Technology,2013,35(3):78-83(in Chinese).
[19]	Liu C L,Hao H W,Sako H.Confidence transformation for combining classifiers[J].Pattern Analysis and Applications,2004,7(1):2-17.
[20]	Liu C L.Classifier combination based on confidence transformation[J].Pattern Recognition,2005,38(1):11-28.
[21]	Costagliola G,de Rosa M,Fuccella V.Recognition and autocompletion of partially drawn symbols by using polar histograms as spatial relation descriptors[J].Computers & Graphics,2014,39(2):101-116.