|
|
|
| Plant species identification method based on flower feature coding classification |
| BAI Fan, ZHENG Hui feng, SHEN Ping ping, WANG Cheng, YU Sang sang |
| Institute of Precision Measurement and Control, China Jiliang University, Hangzhou 310018, China |
|
|
|
Abstract An approximate identification method of plant species based on the encoding of the flowers’feature was proposed. Images of the flowers were segmented using maximum entropy threshold combined with GrabCut algorithm in order to extract and select the color, contour, texture and spatial structure satisfying good human visual features and classification performances. The coding classification system was built to narrow the range of recognition according to the concept of maximum spacing classification, binary node models and classification network structure. The color histogram, contour histogram and spatial gradient co occurrence matrix were compared to the fitting operation to calculate the similarity degree of each class object and the testing target. The approximate identification was completed when the class object with the highest similarity degree was found. The method was verified, analyzed and improved through experiments. Experimental results show that the method has the advantages of high recognition speed, accuracy and good extensibility.
|
|
Published: 29 October 2015
|
|
|
基于花朵特征编码归类的植物种类识别方法
提出基于花朵特征编码分类的植物种类近似识别方法.运用以最大熵阈值为主,GrabCut算法为辅的体系进行花朵图像分割,提取并筛选出符合人眼视觉特性且分类性能良好的颜色、轮廓、纹理、空间结构等特征.依照最大间隔分类理念、节点二分模式和分类网络结构,搭建编码分类体系以缩小识别范围.将颜色直方图、轮廓直方图和梯度空间共生矩阵相交进行相似比对拟合运算,得到库中各已知类别对象与待测目标的相似程度,列出最近似的对象,完成近似识别.对该方法进行实验验证、分析和完善,实验结果表明,该方法具备识别速度快、准确度高、识别目标扩展性能好等优点.
|
|
| ［1］ ZHANG J, HUANG X Y. A survey of plant recognition method based on image processing ［C］∥ International Conference on IEEE Electrical and Control Engineering. Wuhan: IEEE, 2010: 4974-4977.
［2］ 张蕾.基于叶片特征的计算机自动植物种类识别研究［D］.长春:东北师范大学, 2007: 10-24.
ZHANG Lei. The research of computer aided plant species identification based on leaf feature ［D］. Changchun: Northeast Teachers University, 2007: 10-24.
［3］ TAN W N, SEM R, TAN Y F. Blooming flower recognition by using eigenvalues of shape features ［C］∥ 6th International Conference on Digital Image Processing International Society for Optics and Photonics. ［S. l.］: ICDIP, 2014: 4177-4180.
［4］ SAITOH T, KANEKO T. Automatic recognition of wild flowers ［C］∥ Pattern Recognition, International Conference on IEEE Computer Society. ［S. l.］: IEEE, 2000: 2507.
［5］ NILSBACK M, ZISSERMAN A. Automated flower classification over a large number of classes ［C］∥6th Indian Conference on Computer Vision, Graphics and Image Processing. Bhubaneswar: IEEE, 2008: 722-729.
［6］ 吴清锋.基于内容的中草药植物图像检索关键技术研究［D］.厦门：厦门大学,2007.
WU Qing feng. Research on key techniques of content based Chinese herbal medicine botanic image retrieval ［D］. Xiamen: Xiamen University, 2007.
［7］ PORNPANOMCHAI C, SAKUNRERARATSAME P, WONGSASIRINART R, et al. Herb flower recognition system (HFRS) ［C］∥Electronics and Information Engineering. Kyoto, Japan: ICEIE, 2010(V1): 123-127.
［8］ HSU T, LEE C, CHEN L. An interactive flower image recognition system ［J］. Multimed Tools, 2011, 53 (1): 53-73.
［9］ CHO S Y. Content based structural recognition for flower image classification［C］∥7th IEEE Conference on Industrial Electronics and Applications. Singapore: IEEE, 2012.
［10］ 冯伟兴,贺波,王臣业.数字图像模式识别技术详解［M］.2版.北京：机械工业出版社,2013.
［11］ SPAGNOLO P, ORAZIO T D, LEO M, et al. Moving object segmentation by background subtraction and temporal analysis ［J］. Image and Vision Computing, 2006, 24(5): 411-423.
［12］ NILSBACK M, ZISSERMAN A. A visual vocabulary for flower classification ［C］∥Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. ［S. l.］: IEEE, 2006: 1447-1454.
［13］ HONG A X, CHI Z R, CHEN G, et al. Region of interest based flower images retrieval ［C］∥International Conference on Acoustics, Speech and Signal Processing. Hong Kong: IEEE, 2003: 589-592.
［14］ 孙即祥.图像分析［M］.北京：科技出版社,2005: 29-45.
［15］ 游福成.数字图像处理［M］.北京：电子工业出版社,2011: 73-86.
［16］ 王晅,马建峰.数字图像分析与模式识别［M］.北京：科技出版社, 2011: 232-258.
［17］ 苏见欣，姚剑敏，郭太良，等.基于成对几何直方图的PCB标志检测与匹配[J].计算机与现代化,2012(6):43-46.
SU Jian xin, YAO Jian min, GUO Tai liang, et al. Dectection and match of PCB mark based on pair wise geometrical histogram [J]. Jisuanji Yu Xiandaihua, 2012(6): 43-46. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
