On a Quest for Image Descriptors Based on Unsupervised Segmentation Maps
On a Quest for Image Descriptors Based on Unsupervised Segmentation Maps
复制标题
DOI：
10.1109/icpr.2010.192
复制
发表时间：
2010-08
期刊：
影响因子：
--
通讯作者：
Piotr Koniusz;K. Mikolajczyk
中科院分区：
文献类型：
--
作者：
Piotr Koniusz;K. Mikolajczyk
本文研究了基于分割的图像描述符的对象类别识别。与常用的兴趣点相比，所提出的描述符是从由分割方法给出的相邻区域对中提取的。以这种方式，我们利用半局部结构信息的图像。我们建议使用的片段作为空间箱的描述符的各种图像统计的基础上梯度，颜色和区域形状。建议的描述符验证标准的识别基准。结果表明，它们的性能优于最先进的参考描述符，数据减少了5.6倍，并实现了与它们相当的结果，数据减少了8.6倍。所提出的描述符是SIFT的补充，并且当在基于内核的分类器内组合在一起时实现最先进的结果。
This paper investigates segmentation-based image descriptors for object category recognition. In contrast to commonly used interest points the proposed descriptors are extracted from pairs of adjacent regions given by a segmentation method. In this way we exploit semi-local structural information from the image. We propose to use the segments as spatial bins for descriptors of various image statistics based on gradient, colour and region shape. Proposed descriptors are validated on standard recognition benchmarks. Results show they outperform state-of-the-art reference descriptors with 5.6x less data and achieve comparable results to them with 8.6x less data. The proposed descriptors are complementary to SIFT and achieve state-of-the-art results when combined together within a kernel based classifier.