International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 02 | Feb -2017
p-ISSN: 2395-0072
www.irjet.net
A Study on Surf & Hog Descriptors for Alzheimer’s Disease Detection Ameer Nisha.S1, Shajun Nisha.S2, Dr.M.Mohamed Sathik3 1
M.Phil. (PG Scholar) Dept of Computer Science, Sadakathullah Appa College, Tirunelveli, Tamil Nadu, India
2 Prof
& Head, P.G Dept of Computer Science, Sadakathullah Appa College, Tirunelveli, Tamil Nadu, India 3Principal, Sadakathullah Appa College, Tirunelveli, TamilNadu, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Medical imaging has become a major tool in
clinical trials since it enables rapid diagnosis with visualization and quantitative assessment. In the study, a detecting method of brain abnormality is proposed through magnetic resonance imaging. Very tiny and minute structural difference of brain may gradually & slowly results in major disorder of brain which may cause Alzheimer’s disease. Here the primary focus is given for detection & diagnosis of Alzheimer’s disease. This paper introduces a simple user friendly GUI based application for detection of Alzheimer’s disease by processing images of brain by taking MRI scanned images of brain as input data source, and analyzing its morphological abnormalities for the diagnosis. Surf descriptor and hog descriptor are very good features to use among the existing techniques to detect the disease. Key Words: Brain MRI, Alzheimer’s disease, Image Registration, Magnetic Resonance Imaging, SURF & HOG
1. INTRODUCTION Medical imaging seeks to reveal internal structures hidden by the skin and bones, as well as to diagnose and treat disease. Magnetic Resonance Imaging of the nervous system uses magnetic fields and radio waves to produce high quality two- or three-dimensional images of nervous system structures without use of ionizing radiation (X-rays) or radioactive tracers. One advantage of MRI of the brain over computed tomography of the head is better tissue contrast, and it has fewer artifacts than CT when viewing the brainstem. The human brain is the center of the human nervous system and is the most complex organ in any creature on earth. Any abnormality in brain leads to the total collapse of entire vital functions of the body. Such brain abnormality may result in Alzheimer’s disease. It is a neurodegenerative disease, which means there is progressive brain cell death that happens over a course of time. This paper introduces a concept of simple user friendly GUI application to process an image of brain and analyze its morphological abnormalities. It is detected by Image Registration Technique. Image Registration (IR) occupied a dominant role in the digital Image processing in general and Image analysis in particular. Image registration is a process of transforming different sets of data into one © 2017, IRJET
|
Impact Factor value: 5.181
|
coordinate system. It is widely used in various applications in the fields of remote sensing, medical imaging and computer vision. The combining features of surf and hog descriptor is used to detect such disease. Speeded Up Robust Features (SURF) is a local feature detector and descriptor. It can be used for tasks such as object recognition, image registration, classification or 3D reconstruction. It is partly inspired by the scale-invariant feature transform (SIFT) descriptor. The histogram of oriented gradients (HOG) is a feature descriptor used in computer vision and image processing for the purpose of object detection. The technique counts occurrences of gradient orientation in localized portions of an image. 2. RELATED WORK A variety of feature detection algorithms have been proposed to compute reliable descriptors for image matching. HOG and SURF descriptors are the most promising due to good performance and have now been used in many applications. Most common form of abnormality of brain is the deformation of cerebral [1, 2] cortex due to shrinking of brain. In the paper [3] by Manjusha Deshmukh et.al has proposed about image registration and use of Mutual Information for image registration. In the paper [4] by YAOMING YU had proposed an effective detecting system to distinguish the tumor from brain MRIs and to find the location and coarse contour of brain tumor. In the paper [5] by SOOJIN KIM et.al has proposed a novel algorithm of fast HOG feature calculation to remove the redundant operations totally in trilinear interpolation. By identifying key rules and sharing common operations in trilinear interpolation, high detection rate is still achieved but the number of required multiplications is reduced up to 60.5%. In the paper [6] by K. Jagan Mohan et.al has used HOG feature to extract features from the disease affected images. Then these features are used to recognize and classify the images using SVM. This work mainly concentrates on three main diseases of paddy plant, namely Brown spot, Leaf blast and Bacterial blight. In the paper[7] by P.Tamilsankar has used HOG techniques, the gradient feature value of betel leaf images are obtained. Mimimum
ISO 9001:2008 Certified Journal
|
Page 626