文章詳目資料
Journal of Computers EIMEDLINEScopus
加入收藏
下載文章
| 篇名 | Multiclass Object Classification Using Covariance Descriptors with Kernel SVM |
|---|---|
| 卷期 | 29:5 |
| 作者 | Chun-Yi Tsai 、 Wen-Hsiu Chung |
| 頁次 | 244-249 |
| 關鍵字 | covariance feature 、 kernel method 、 object classification 、 SVM 、 EI 、 MEDLINE 、 Scopus |
| 出刊日期 | 201810 |
| DOI | 10.3966/199115992018102905019 |
中文摘要
英文摘要
Feature descriptor is a crucial part for image object detection and classification in computer vision. This study adopts the covariance descriptor which is a ROI(region of interest) based feature reserving the integrity of regions with rotation and scale invariant, combining with kernel SVM for multiclass object classification. The experimental results show that the combination of covariance descriptor and kernel SVM is very feasible and practical to be applied on dataset images in which the foreground objects are the major portions and the backgrounds are relatively simple.
本卷期文章目次
- A Multicast-Tree Construction Algorithm for Efficient Data Collection over Mobile Networks of Military Vehicles / Tien-Yu Chang、Jichiang Tsai、Wen-Tien Huang
- Convex Defect Detection and Density Distribution Based Hand Gesture Recognition / Yanan Xu、Yunhai Dai
- Study of Stress Rules Based on HRV Features / Gang Zheng、Yingli Wang、Yanhui Chen
- Algorithm of Video Semantic Classification Based on IAGA and Deep Convolution Neural Network / Min Wang、Ke-Xin Liu、Ming-Fei Wei、Li-Cai Zhang
- Optic Disk Detection and Segmentation for Retinal Images Using Saliency Model Based on Clustering / Lan-Yan Xue、Jia-Wen Lin、Xin-Rong Cao、Shao-Hua Zheng、Lun Yu