In this paper we have analyzed two state-of-the-art techniques for composite sketch image recognition: Self-similarity descriptor (SSD)-based composite sketch recognition and local descriptors (LD)-based composite sketch recognition. SSD is mainly used for developing a SSD dictionary-based feature ...
local self-similaritySIFTPCAregion descriptionimage matchingThe advanced descriptor, i.e., Local Self-Similarities (LSS), is successfully adopted for object classification and scene recognition. However, it is only invariance against small geometric and photometric transformations. In this paper, two low...
The local self-similarity descriptor is a kind of important image or video local feature description method. It is often used for detection, identification and recognition. In this paper we propose a new local self-similarity descriptor based on structural similarity (SSIM) index. It is showed in...
We test our self similarity descriptor using support vector machine based classification on the PASCAL VOC 2007 database consisting of 20 object classes. Comparative results indicate performance competitive with the prior approaches of computing self-similarity descriptors. 展开 ...
The self-similarity inspiredlocal descriptoris proposed for non-rigid multi-modal registration. • The Zernike moments is introduced into the proposed method to explore rotational self-similarity. • The effective computation of self-similarity based both intensities and edge/texture features of the ...
Here are some options: 1. Take a histogram after converting your image to log polar coordinates. The following thread has some code for converting to log-polar coordinates:
Then, the his- togram of the DBC dimensions on all blocks is used as the descriptor. See Sec. 4.2 for details. feature map from 1st layer feature map from th layer Figure 1. Illustration of basic idea of CLASS. 1.2. Contributions Integrating the C...
We present a descriptor, called fully convolutional self-similarity (FCSS), for dense semantic correspondence. To robustly match points among different instances within the same object class, we formulate FCSS using local self-similarity (LSS) within a fully convolutional network. In contrast to exi...
We use a concise shape descriptor to identify and cluster similar patches. Decoding is achieved through simple instancing of the representative patches. Encoding is efficient, and can be applied to large data sets consisting of millions of points. Moreover, our technique offers random access to ...
compact geometric patch descriptor, which will guide the clustering process. An important feature of our compression scheme is that it easily affords random access, which makes ray tracing possible without the need of a full decoding step.