08-17-2017, 12:29 AM
matlab source code for local tetra pattern
Abstract
In medical field, the digital images used for diagnostics and therapy are produced in ever increasing quantities. So there is necessity of feature extraction and classification of medical images for easy and efficient retrieval. In this paper, a framework based on Local Tetra Pattern and Fourier Descriptor for content based image retrieval from medical databases is proposed. The proposed approach formulates the relationship between the reference or centre pixel and its neighbours, considering the vertical and horizontal directions calculated using the first-order derivatives. The texture feature of an image is of prime concern; the images filtered by this feature are more appropriate ones as a response to the query image. In this research work, the association of Euclidean Distance(ED) with local tetra pattern is also explored. The proposed framework is successfully tested on standard Messidor dataset of 1200 Retinal images which are annotated with Retinopathy and Macular Edema grades. A tool SS-SVM is applied on binary patterns for endoscopy, dental, skull and retinal images for classification, which results in better classification of images for various dataset, thus improving classifiers.
INTRODUCTION
Database of more than thousands of images has to be managed in large hospitals every year, making the database management an extremely annoying and uncouth task [1]. These images need to be indexed, classified and searched for easy retrieval [3]. To accomplish this task, a technique called CBIR has been extensively used to describe the process of retrieving desired images from a large scale medical database on the basis of features (such as colour, texture and shape) that can be extracted from the images themselves [6- 7].There exist three basic levels of feature extraction; namely - global, local and pixel. The simplest of all visual image features are based on the pixel values of the image without any deviation. Images are first scaled to a common size and then compared with database images. Local features are extracted from small sub images which are derived from the original image. The global feature can be extracted to describe the whole image in an average fashion. The low-level features extracted from images and their local patches constitute the colour, texture, and shape [9].Texture is an important and extensively used feature in the human visual system for recognition and interpretation