期刊文献+

基于人体检测的网络商品图像分类算法 被引量:1

Online Product Images Clustering By Human Body Detection
下载PDF
导出
摘要 当前各大购物网站存储了海量商家上传的商品图像。其中大量图像没有明确标注商品类别,或描述词模糊,这使得网上商品图像的自动分类问题变得急迫和重要。本文分析的图像视觉内容,发现服装类商品图像中普遍出现人体区域,提出算法有效地识别服装类商品图像。算法通过检测图像中的人体的区域得到特征,从训练集图像的特征中学习出鲁棒的SVM分类器用于分类图像。在真实的淘宝网商品图像数据集上取得较理想的效果。 Nowadays users upload huge amount of text and images on online commercial websites to sale products.A large number ofthese products are with implicit textual description and hence hard to be categorized.This leads to a headache problem for shoppingwebsites who want to categorize these products.In this paper,we propose a novel approach which relies on the visual content of images for distinguishing clothing related products from other ones.Our algorithm detects human body in pictures to discover the purpose of showing clothes.Using body area as features,the resulting SVM classifier achieves significant classification precision on realdata from taobao.com.
出处 《微计算机信息》 2010年第29期15-17,共3页 Control & Automation
基金 基金申请人:孙林 项目名称:商业连锁物流发展研究 基金颁发部门:北京市教委(sm200900001003)
关键词 网络图像分类 人体检测 HOG特征 支持向量机 web image categorization human body detection HOG feature SVM classification
  • 相关文献

参考文献5

二级参考文献5

共引文献28

同被引文献9

  • 1FERNANDO B, FROMONT E, MUSELET D,et al. Discriminative feature fusion for image classification [ C ]//Prec. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). [ S. 1. ]: 1EEE Press,2012:3434-3441.
  • 2WANG X, HAN T X,YAN S. An HOG-LBP human detector with partial ocelusion handling[ C]//Proc. 2009 IEEE 12th International Conference on Computer Vision. Kyoto, Japan: IEEE Press, 2009 : 32-39.
  • 3GEHLER P, NOWOZIN S. On feature combination for multiclass ob- ject classification [ C ]//Proc. 2009 IEEE 12th International Confer- ence on Computer Visnn. [ S. 1. ] :IEEE Press,2009:221-225.
  • 4PERAZZI F, KRAHENBUHL P, PRITCH Y,et al. Saliency filters: contrast based filtering ftr salient region detection[ C ]//Proc. the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC, USA : IEEE Computer Society, 2012:733-740.
  • 5ROTHER C, KOLMOGOROV V, BLAKE A. Grabeut: Interactive foreground extraction using iterated graph cuts [ J l- ACM Trans. Graphics, 2004 ( 23 ) : 309 -314.
  • 6ZISSERMAN B, MUNOZ X. Representing shape with a spatial pyr- amid kernel[ C ]//Proc. the 6th ACM International Conference on Image and Video Retrieval (CVIR 07). [S. 1. ]: ACM,2007: 401 - 408.
  • 7WANG Zhiyong, LU Bin, CH1 Zheru,et al. Leaf image classifica- tion with shape context and SIFT descriptors [ C ]//Proe. Interna- tional Conference on Digital Image Computing:Techniques and Ap- plications. Noosa, QLD : IEEE Press,2011:650-654.
  • 8姜兰池,沈国强,张国煊.基于HSV分块颜色直方图的图像检索算法[J].机电工程,2009,26(11):54-57. 被引量:51
  • 9翟艳东,于明,王岩,韩淑珍.一种图像多级分类方法[J].电视技术,2013,37(19):32-35. 被引量:1

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部