Application of Data Compactness in Image Mining
| Autor: | Yaohui Li, Yuqing Song, Shaoqing Mo |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
General Computer Science
Contextual image classification Computer science business.industry Binary image ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION General Engineering Nonlinear dimensionality reduction Automatic image annotation Image texture Knowledge extraction Computer Science::Computer Vision and Pattern Recognition Digital image processing Computer vision Artificial intelligence business Image retrieval |
| Zdroj: | International Journal of Intelligent Engineering and Systems. 6:8-17 |
| ISSN: | 2185-3118 |
| DOI: | 10.22266/ijies2013.0630.02 |
| Popis: | Image mining is concerned with knowledge discovery in image databases. With the advance of multimedia technology and growth of image collections, it is becoming crucial to analyze the compactness of image data and apply it to image mining. In this paper, we study the class compactness and boundary compactness of image data, which are used in image classification and data confining, respectively. The data confining procedure produces a relevance graph representing relevant image pairs and their relevancy. Based on relevant image pairs, a manifold learning technique is applied to compute distances between images and manifolds of images. Image retrieval is based on these distances. The effectiveness of the proposed approach has been validated by experiments on real-world images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|