Texture Feature Extraction Based on Fractional Mask Convolution with Cesáro Means for Content-Based Image Retrieval

This paper introduces a texture features extraction technique for content-based image retrieval using fractional differential operator mask convolution with Cesáro means. We propose one general fractional differential mask on eight directions for texture features extraction. Image retrieval based on texture features is getting unusual concentration because texture is an important feature of natural images. Experiments show that, the capability of texture features extraction by fractional differential-based approach appears efficient to find the best combination of relevant retrieved images for different resolutions. To compare the performance of image retrieval method, average precision and recall are computed for query image. The results showed an improved performance (higher precision and recall values) compared with the performance using other methods of texture extraction.