Article Preview
Top1. Introduction
Expedited growth of world-wide web has to lead to easy access to huge volume of digital multimedia data especially image data. Unfortunately, this image data in most cases are scatted and unorganized, making searching, analysis and retrieval of such data difficult. Extensive work is carried out by researchers towards image feature detectors that are used to establish feature descriptors. Image processing applications like image classification (Fang, 2017), content based image retrieval (CBIR). (Guo, 2015), (Yang, 2017), (Elalami, 2014), image representation (Yap, 2010), image classification (Liu, 2012), motion tracking and crowd analysis (Zerdi, 2014) [7], texture analysis and classification (Song, 2017), medical image processing (Satheesha, 2017), to name a few rely on accurate feature detectors and feature descriptors for robust operations. Significance of image features in image processing applications is clearly highlighted in (Satheesha, 2017), (Godtliebsen, 2004), (Hassaballah, 2016). In this paper discusses about CBIR and texture classification applications.
In CBIR systems a set of visually similar images are obtained from a large collection of images in a database. To retrieve visually similar images, it is essential to understand the content present in images. Researchers have proposed various features to describe content. In (Guo, 2015), color co-occurrence feature and bit pattern features are considered to understand content. Numerous features like gray, color co-occurrence matrix, difference observed between pixels of scan patterns, histogram of oriented gradient and local binary patterns features is considered in (Yang, 2017). Though researchers have considered numerous feature combinations, the existing CBIR systems in place neglect to describe correlation that exists between low-level features and high-level concepts observed in images effecting performance (Zhao, 2016).