Computational Perceptual Features for CBIR Systems

P. H. D. Arun Kumar; M. Chinna Rao

Content Based Image Retrieval (CBIR) systems represent images in the database by color, texture, and shape information. Texture refers to the spatial distribution of grey-levels and can be defined as the deterministic or random repetition of one or several primitives in an image. Any type of texture can be visualized and recognized using human perception. For this human beings use some textural features. Some of these perceptual textural features include coarseness, contrast, directionality, and busyness. Textures are usually easily visible for the human eye while the automatic processing of these textures is very complex. Because computational methods use mathematical features that have no perceptual meaning easily comprehensible by users. Computational methods that allow a quantitative and computational estimation of these perceptual textural features can easily distinguish and represent images. This paper presents an overview of how the perceptional textural features can be used to represent textures and applying these features to content- based mage retrieval systems.

Select Volume / Issues:

• Volume 3 Issue 5, Sept. 2012

Year:

2012

Type of Publication:

Article

Keywords:

CBIR systems; Computational method; Perception; Texture

Journal:

IJECCE

Volume:

3

Number:

5

Pages:

1238-1240

Month:

Sept.