| Autor: |
Ayan, Mehmet, Erdem, O. Ayhan, Bilge, Hasan Şakir |
| Zdroj: |
Applied Mechanics and Materials; August 2016, Vol. 850 Issue: 1 p136-143, 8p |
| Abstrakt: |
Content-based image retrieval (CBIR) system becomes a hot topic in recent years. CBIR system is the retrieval of images based on visual features. CBIR system based on a single feature has a low performance. Therefore, in this paper a new content based image retrieval method using color and texture features is proposed to improve performance. In this method color histogram and color moment are used for color feature extraction and grey level co-occurrence matrix (GLCM) is used for texture feature extraction. Then all extracted features are integrated for image retrieval. Finally, color histogram, color moment, GLCM and proposed methods are tested respectively. As a result, it is observed that proposed method which integrates color and texture features gave better results than the other methods used independently. To demonstrate the proposed system is successful, it was compared with existing CBIR systems. The proposed method showed superior performance than other comparative systems. |
| Databáze: |
Supplemental Index |
| Externí odkaz: |
|
