Computer Image Process in Medical Area Name : Zhangyu(115033940117) Major : Computer Technology.

Slides:



Advertisements
Similar presentations
Advanced Image Processing Student Seminar: Lipreading Method using color extraction method and eigenspace technique ( Yasuyuki Nakata and Moritoshi Ando.
Advertisements

Photography and CS Philip Chan. Film vs Digital Camera What is the difference?
Computational Biology, Part 23 Biological Imaging II Robert F. Murphy Copyright  1996, 1999, All rights reserved.
DESCRIBING INPUT DEVICES
IntroductionIntroduction AbstractAbstract AUTOMATIC LICENSE PLATE LOCATION AND RECOGNITION ALGORITHM FOR COLOR IMAGES Kerem Ozkan, Mustafa C. Demir, Buket.
CS 551 / CS 645 Antialiasing. What is a pixel? A pixel is not… –A box –A disk –A teeny tiny little light A pixel is a point –It has no dimension –It occupies.
Computer Vision Lecture 16: Region Representation
Normal Vision Cataracts A cataract is a painless, cloudy area in the lens of the eye. A cataract blocks the passage of light from the lens to the nerves.
Morphological Image Processing Md. Rokanujjaman Assistant Professor Dept of Computer Science and Engineering Rajshahi University.
Bohr Robot Group OpenCV ECE479 John Chhokar J.C. Arada Richard Dixon.
Fingerprint Imaging: Wavelet-Based Compression and Matched Filtering Grant Chen, Tod Modisette and Paul Rodriguez ELEC 301 : Rice University, Houston,
Quadtrees, Octrees and their Applications in Digital Image Processing
1Ellen L. Walker Edges Humans easily understand “line drawings” as pictures.
December 5, 2013Computer Vision Lecture 20: Hidden Markov Models/Depth 1 Stereo Vision Due to the limited resolution of images, increasing the baseline.
Processing Digital Images. Filtering Analysis –Recognition Transmission.
Computer Vision Introduction to Image formats, reading and writing images, and image environments Image filtering.
An Approach to Korean License Plate Recognition Based on Vertical Edge Matching Mei Yu and Yong Deak Kim Ajou University Suwon, , Korea 指導教授 張元翔.
Image representation using arrays Image processing examples
Preprocessing ROI Image Geometry
Registration-Based Change Detection Charles V. Stewart Department of Computer Science Rensselaer Polytechnic Institute.
Iris localization algorithm based on geometrical features of cow eyes Menglu Zhang Institute of Systems Engineering
Three-Dimensional Concepts
COS 429 PS3: Stitching a Panorama Due November 4 th.
Stockman MSU/CSE Math models 3D to 2D Affine transformations in 3D; Projections 3D to 2D; Derivation of camera matrix form.
Image processing Lecture 4.
Robust fitting Prof. Noah Snavely CS1114
Automatic Camera Calibration
VEHICLE NUMBER PLATE RECOGNITION SYSTEM. Information and constraints Character recognition using moments. Character recognition using OCR. Signature.
Tal Mor  Create an automatic system that given an image of a room and a color, will color the room walls  Maintaining the original texture.
GmImgProc Alexandra Olteanu SCPD Alexandru Ştefănescu SCPD.
Image processing Second lecture. Image Image Representation We have seen that the human visual system (HVS) receives an input image as a collection of.
Computer Graphics Lecture 1 July 11, Computer Graphics What do you think of? The term “computer graphics” is a blanket term used to refer to the.
General Anatomy of the Eye & Degenerative Diseases of Human Retina
CS 6825: Binary Image Processing – binary blob metrics
By Doğaç Başaran & Erdem Yörük
Shape from Stereo  Disparity between two images  Photogrammetry  Finding Corresponding Points Correlation based methods Feature based methods.
September 5, 2013Computer Vision Lecture 2: Digital Images 1 Computer Vision A simple two-stage model of computer vision: Image processing Scene analysis.
Digital Image Processing CCS331 Relationships of Pixel 1.
Quadtrees, Octrees and their Applications in Digital Image Processing.
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
An Introduction to Analyzing Colors in a Digital Photograph Rob Snyder.
Fast Localization and Segmentation of Optic Disk in Retinal Images Using Directional Matched Filtering and Level Sets Project Guide/Co-Guide: P.Rekha Sharon,
Eye regions localization Balázs Harangi – University of Debrecen Ciprian Pop – Technical University of Cluj-Napoca László Kovács – University of Debrecen.
More digital reading explaining LUT RT 244 Perry Sprawls, Ph.D. Professor Emeritus Department of Radiology Emory University School of.
September 19, 2013Computer Vision Lecture 6: Image Filtering 1 Image Filtering Many basic image processing techniques are based on convolution. In a convolution,
CS654: Digital Image Analysis
CS COMPUTER GRAPHICS LABORATORY. LIST OF EXPERIMENTS 1.Implementation of Bresenhams Algorithm – Line, Circle, Ellipse. 2.Implementation of Line,
FACE DETECTION : AMIT BHAMARE. WHAT IS FACE DETECTION ? Face detection is computer based technology which detect the face in digital image. Trivial task.
Introduction to JPEG m Akram Ben Ahmed
An Improved Approach For Image Matching Using Principle Component Analysis(PCA An Improved Approach For Image Matching Using Principle Component Analysis(PCA.
What is Digital Image processing?. An image can be defined as a two-dimensional function, f(x,y) # x and y are spatial (plane) coordinates # The function.
More digital 244 wk 12 Perry Sprawls, Ph.D. Professor Emeritus Department of Radiology Emory University School of Medicine Atlanta, GA,
EE368: Digital Image Processing Bernd Girod Leahy, p.1/15 Face Detection on Similar Color Images Scott Leahy EE368, Stanford University May 30, 2003.
Course 3 Binary Image Binary Images have only two gray levels: “1” and “0”, i.e., black / white. —— save memory —— fast processing —— many features of.
Pixel Parallel Vessel Tree Extraction for a Personal Authentication System 2010/01/14 學生:羅國育.
September 26, 2013Computer Vision Lecture 8: Edge Detection II 1Gradient In the one-dimensional case, a step edge corresponds to a local peak in the first.
The Human Retina. Retina Function To detect movement To detect color To detect detail.
License Plate Recognition of A Vehicle using MATLAB
Zhaoxia Fu, Yan Han Measurement Volume 45, Issue 4, May 2012, Pages 650–655 Reporter: Jing-Siang, Chen.
Date of download: 6/25/2016 Copyright © 2016 American Medical Association. All rights reserved. From: Normal Macular Thickness Measurements in Healthy.
Date of download: 7/2/2016 Copyright © 2016 SPIE. All rights reserved. Diagrams demonstrating shadow imaging. (a) The position of the shadow moves as the.
Fundus Image Enhancement and Glaucoma Detection
Introduction to Skin and Face Detection
Fundus Image Enhancement and Glaucoma Detection
1-Introduction (Computing the image histogram).
Image Processing, Lecture #8
Image Analyzer John Ponte SAS Abstract References
Image Processing, Lecture #8
Digital Image Processing Week III
Presentation transcript:

Computer Image Process in Medical Area Name : Zhangyu( ) Major : Computer Technology

Main Research The process of eye fundus image Color fundus images has been widely used in systemic diseases such as Diabetic Retinopathy( 糖尿病性视网膜病变 )and related eye diseases such as glaucoma( 青光眼 ), high blood pressure, auxiliary diagnosis or screening in.

Optic disk detection macular lutea ( 黄斑病变 ) detection Blood vessel detection

Some special character of eye fundus image Obvious features of optic disk in fundus image: (1)Approximate circle and it’s usually yellow or bright white spot; (2) blood vessel extend from optic disk center; (3) the extension has similarity in the direction of blood vessels.

Optic disk Detect by the brightness information Module matching algorithm The combine of the two method Through the position of blood vessels

A color image could be demonstrated by a three dimensional array, then there is the equivalent of three matrix, said the three matrix image of R channel, G, B channel. Separation of the three image channel can highlight some image characteristics. Example:

Channel R : It highlights the brightness information of the image.

To cope with the two-dimensional image, we need two images: the original image and template image, which is used as matching template. The ultimate goal of template matching is to detect the template image's matching area. The diagram below: Module Mathching algorithm

The key problem of this algorithm is how to get that template. Randomly select 25 standard fundus images, of which 12 left eye image, 13 of the right eye image. Centered on optic disk center and cut out the size of 110 * 110 DVD region, and then add these 25 plates to get the average figure, the subgraph as template.

The combination The basic idea is to narrow the search area of module matching algorithm. We can be obtained the rough coordinates of center by brightness detection algorithm, then we use matching algorithm in the area around the coordinates. This can greatly reduce the running time, can almost get the answer soon. In addition, you can search across two or three or more pixels to search, other than search one by one, this also can reduce the running time.

Through the position of blood vessels (1)Approximate circle and it’s usually yellow or bright white spot; (2) blood vessel extend from optic disk center; (3) the extension has similarity in the direction of blood vessels. We could utilize the blood vessels

Thank you.