Generalizing intersection kernel support vector machines for color texture based recognition
详细信息 查看全文
- 作者：Jian Zoua ; jzouzj@ahpu.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Gui-Fu Lub ; Yue Zhanga ; Chuancai Liuc
- 关键词：Perceptual uniform color space ; Component-adaptive color co-occurrence matrices (CACCMs) ; CCM intersection kernel support vector machines (CIKSVMs) ; Color texture based recognition
- 刊名：Journal of Visual Communication and Image Representation
- 出版年：2016
- 出版时间：November 2016
- 年：2016
- 卷：41
- 期：Complete
- 页码：1-14
- 全文大小：1671 K
文摘
- •
Exploring color co-occurrence matrix (CCM) intersection kernel SVMs, named CIKSVMs.
- •
Designing component-adaptive CCMs descriptors for images encoded by any color model.
- •
Providing a framework for synchronously training CIKSVMs and CCMs’ extractors.
- •
Combining marginal CIKSVMs in weighted majority voting for competitive recognition.