[1]周伟 武港山.基于显著图的花卉图像分类算法研究[J].计算机技术与发展,2011,(11):15-18.
 ZHOU Wei,WU Gang-shan.Research on Saliency Map Based Flower Image Classification Algorithm[J].,2011,(11):15-18.
点击复制

基于显著图的花卉图像分类算法研究()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2011年11期
页码:
15-18
栏目:
智能、算法、系统工程
出版日期:
1900-01-01

文章信息/Info

Title:
Research on Saliency Map Based Flower Image Classification Algorithm
文章编号:
1673-629X(2011)11-0015-04
作者:
周伟 武港山
南京大学计算机科学与技术系
Author(s):
ZHOU Wei WU Gang-shan
Department of Computer Science and Technology, Nanjing University
关键词:
显著图特征提取特征融合图像分类
Keywords:
saliency map feature extraction feature combination image classification
分类号:
TP391
文献标志码:
A
摘要:
在计算机视觉领域,图像分类已成为最近几年的研究热点,取得了很大的发展。然而目前的研究大多基于开放领域,分类粒度较粗,不能很好地满足花卉图像精细分类的需求。传统的图像分类算法都是基于分割后的图像进行的,较为依赖分割效果的好坏,不太适用于花卉这一类拥有复杂背景的图像。因此结合花卉图像的自身特点,提出了一种新的基于显著图的图像分类算法,将显著图融入到图像特征的提取过程中,从而避免对图像进行分割,增强了算法的适应性和可靠性,随后又对基于SVM的多特征融合方法进行了简单的介绍。通过在花卉图像库进行的实验,证明了算法的有效性
Abstract:
Recently, the technology of image classification has been well developed. However, most of the current study is based on open fields, for coarse-grained classification, which cannot meet the demand for automated flower classification task. Traditionally, the feature extraction process is done on the segmented images. But for the flower images with complex background, the image segmentation is not always reliable. So proposed to use the saliency map to assist the feature extraction process, which could improve the robustness of the system. And also discuss the method of combining different features using SVM classifier. Finally, executed experiments on flower image data sets, and comparative results show that the algorithm is effective

相似文献/References:

[1]田昕辉 李成基.带有短语切分的中文文本分类方法[J].计算机技术与发展,2010,(01):5.
 TIAN Xin-hui,LEE Sung-kee.Phrase Segmentation for Chinese Text Classification[J].,2010,(11):5.
[2]何小娜 逄焕利.基于二维直方图和改进蚁群聚类的图像分割[J].计算机技术与发展,2010,(03):128.
 HE Xiao-na,PANG Huan-li.Image Segmentation Based on Improved Ant Colony Clustering and Two- Dimensional Histogram[J].,2010,(11):128.
[3]罗林波 陈绮.氨基酸序列特征提取方法研究[J].计算机技术与发展,2010,(02):206.
 LUO Lin-bo,CHEN Qi.Research of Feature Extraction Methods of Amino Acid Sequence[J].,2010,(11):206.
[4]姜鹤 陈丽亚.SVM文本分类中一种新的特征提取方法[J].计算机技术与发展,2010,(03):17.
 JIANG He,CHEN Li-ya.A New Feature Selection Method in SVM Text Categorization[J].,2010,(11):17.
[5]毛雁明 兰美辉 王运琼 冯乔生.一种改进的基于Harris的角点检测方法[J].计算机技术与发展,2009,(05):130.
 MAO Yan-ming,LAN Mei-hui,WANG Yun-qiong,et al.An Improved Corner Detection Method Based on Harris[J].,2009,(11):130.
[6]赵辉 张鹏.网络异常的主动检测与特征分析[J].计算机技术与发展,2009,(08):159.
 ZHAO Hui,ZHANG Peng.Active Detection and Feature Analysis About Network Anomaly[J].,2009,(11):159.
[7]汤婷 吴小培 项明.指纹图像增强与特征提取[J].计算机技术与发展,2009,(01):81.
 TANG Ting,WU Xiao-pei,XIANG Ming.Fingerprint Image Enhancement and Minutiae Extraction[J].,2009,(11):81.
[8]张国富 凌捷 彭辉 谷保平.基于支持向量机的手写签名研究[J].计算机技术与发展,2008,(05):57.
 ZHANG Guo-fu,LING Jie,PENG Hui,et al.Research of Handwritten Signature Based on SVM[J].,2008,(11):57.
[9]黄国宏 刘刚.一种新的基于Fisher准则的线性特征提取方法[J].计算机技术与发展,2008,(05):227.
 HUANG Guo-hong,LIU Gang.A New Linear Feature Extraction Method Based on Fisher Criterion[J].,2008,(11):227.
[10]黄国宏 刘刚.一种新的基于DCT变换的线性判别分析[J].计算机技术与发展,2008,(06):97.
 HUANG Guo-hong,LIU Gang.A Novel Linear Discriminant Analysis Based on DCT[J].,2008,(11):97.

备注/Memo

备注/Memo:
国家自然科学基金项目(60975043,61021062)周伟(1986-),男,江苏盐城人,硕士研究生,主要研究领域为计算机视觉、图像分类;武港山,博导,CCF会员,主要研究领域为多媒体技术
更新日期/Last Update: 1900-01-01