Send the link below via email or IMCopy
Present to your audienceStart remote presentation
- Invited audience members will follow you as you navigate and present
- People invited to a presentation do not need a Prezi account
- This link expires 10 minutes after you close the presentation
- A maximum of 30 users can follow your presentation
- Learn more about this feature in our knowledge base article
Do you really want to delete this prezi?
Neither you, nor the coeditors you shared it with will be able to recover it again.
Make your likes visible on Facebook?
Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.
Transcript of Imagic
Content-based Image Retrieval
Dr. Mohammed Abdeen
Ass. Amr Gamgom
Muhammad Ibrahim Alsayed
Mahmoud Mustafa Mohamed
Mohamed Fahmy Ismail Emara
Omar Abd-Elaziz Omar
Imagic Web Crawler
Visual Feature Extraction
If a space scientist has a picture for the moon and wants to have a lot of information about these case or slice of the moon.
These picture may have some changes by other specialists, or it may become part of another whole picture.
So searching by name wouldn’t give nice results.
Also names in most cases is a dummy names
Like ‘aaa.jpg’ , ‘m.gif’, or in different languages".jpg"
These problem faces a lot of people not only space scientists, also doctors, plant scientists, researchers, students, even ordinary man.
We have to search INSIDE the image ( in the content )
User should enter an image as input and get similar images is our mission.
Even it would search for images that has changes like:
Spatial Translated (Ratation, Transalation).
Sharpened, Smoothed, …etc
Imagic Web Crawler
Is a computer program that browses the World Wide Web in a methodical, automated manner .
Use spidering as a means of providing up-to-date data .
Web crawlers are mainly used to create a copy of all the visited pages for later processing by a search engine that will index the downloaded pages to provide fast searches.
Image Search Engines
.NET Tecgnologies ( C#,ASP.NET )
SQl Server 2008
Adobe Dreamweaver CS4
Thank You !
Download Url's & Images
Any web page consists of a group of html elements
One of them Called ‘A’ which refers to another page address.
It carries the address in attribute called ‘href’
There are html elements called ‘IMG’
<img src="http://l.yimg.com/a/i/mntl/ww/events/p.gif" height="50" width="202" border="0" alt="Yahoo" id="l_logo" />
Visual Feature Extraction
Low level – They include visual features such as color, texture, shape, spatial information and motion.
Middle level – Examples include presence or arrangement of specific types of objects, roles and scenes.
High level – Include impressions, emotions and meaning associated with the combination of perceptual
provides information in the spatial arrangement of colors or intensities in an image characterized by the spatial distribution of intensity levels in a neighbourhood repeating pattern of local variations in image intensity
Texture is a repeating pattern of local variations in image intensity
Intensity VS. Texture
Three different images with the same intensity distribution, but with different textures.
Angular second moment: represents the joint probability of occurrence of pixels with intensities .
Contrast is a measure of the local variations present in an image.
Entropy: is a measure of information content. It measures the randomness of intensity distribution.
Correlation: is a measure of image linearity.
Intenisity ( RGB v.s HSV )
RGB Histograms shows the frequency of each color individual and it is useful on the type of the images which need color the spate the object and also give information about the most repeated colors and the shape of the image.
histogram the bars in a color histogram are referred to as bins and they represent the x-axis. The number of bins depends on the number of colors there are in an image. The y-axis denotes the number of pixels there are in each bin. In other words how many pixels in an image are of a particular color?
Through out our working with this image retreival system we discovered that the most important diffrenciate features between images are ( Texture , Intenisity) as most of the current image retrieval engines depend on image name or only one of our system's features.
We found that other image retrieval engines like ( Tineye,Image Miner) consuming long time calculating and retreiving the needed output or just miss the most similar images to the input image.
By using the Shape or Text recognition we will be able to produce a fully image retrieval engine with little limitations on the retreiving criteria.
Haralick, R.M., K. Shanmugam, and I. Dinstein, "Textural features for image
classification” IEEE Transactions on Systems, Man and Cybernetics: pp; 610-621. 1973.
• Image Processing - Principles and Applications - T. Acharya, A. ray (Wiley, 2005)
John P. Eakins and Margaret E. Graham, Content-based image retrieval, a report to the JISC technology applications programme, Institute for image database research, University of Northumbria at Newcastle, U.KJanuary 1999.
Remco C. Veltkamp, Mirela Tanase, Content-based image retrieval systems, a survey, Technical report, department of computer science, Utrecht University, October 2000.
Rong Zhao and William I. Grosky , Bridging the Semantic Gap in Image Retrieval, Wayne State University, USA, Idea group publishing, 2002
Zoran Pecenovic, Final year graduate thesis, Image Retrieval Using latent semantic indexing , Department of Electrical Engineering, Swiss Federal University of Technology, Laussanne