Contour Detection-Based Discovery of Mid-Level Discriminative Patches for Scene Classification
Contour Detection-Based Discovery of Mid-Level Discriminative Patches for Scene Classification
复制标题
基于轮廓检测的场景分类中级判别块的发现
DOI：
10.5772/62266
复制
发表时间：
2016
影响因子：
2.3
通讯作者：
Ming
中科院分区：
文献类型：
--
作者：
Jinfu Yang;Jizhao Zhang;Guanghui Wang;Ming
特征提取和表示是场景分类的关键步骤。提出了一种基于轮廓检测的中层特征学习方法用于场景分类。首先，提出了一种基于草图标记的轮廓检测方案，初始化种子块用于学习中间层块，并选择具有更多轮廓像素的块作为种子块。该程序被证明是有助于场景分类。接着，种子块被用来训练一个样本SVM来发现其他类似的出现，并利用熵秩准则来挖掘有区别的补丁。最后，场景类别的识别是通过匹配的判别补丁和测试图像。在MIT Indoor-67数据集、15场景数据集和IUC-sports数据集上进行的大量实验表明，所提出的方法比其他最先进的方法具有更好的性能。
Feature extraction and representation is a key step in scene classification. In this paper, a contour detection-based mid-level features learning method is proposed for scene classification. First, a sketch tokens-based contour detection scheme is proposed to initialize seed blocks for learning mid-level patches and the patches with more contour pixels are selected as seed blocks. The procedure is demonstrated to be helpful for scene classification. Next, the seed blocks are employed to train an exemplar SVM to discover other similar occurrences and an entropy-rank criterion is utilized to mine the discriminative patches. Finally, scene categories are identified by matching the discriminative patches and testing images. Extensive experiments on the MIT Indoor-67 dataset, the 15-scene dataset and the UIUC-sports dataset show that the proposed approach yields better performance than other state-of-the-art counterparts.
DOI：
10.1007/11744023_32
发表时间：
2006-01-01
期刊：
COMPUTER VISION - ECCV 2006 , PT 1, PROCEEDINGS
影响因子：
--
作者：
Bay, Herbert;Tuytelaars, Tinne;Van Gool, Luc
通讯作者：
Van Gool, Luc