Download First Term - UWC Computer Science

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Object-oriented programming wikipedia , lookup

Transcript
By Roland Foster
Supervisors: Mr. Mehrdad Ghaziasgar
Mr. James Connan
Assisted by Warren Nel
Overview
 Background
 User Requirements
 Requirements Analysis
 Project Plan
 References
Background
Image Management Suite
 Organize and easily retrieve images and their metadata
 Detect images on hard drive
 Eliminate duplicates
 Ability to tag images
 Manual
 Automatic (Object Recognition)
 Easily retrieve images based on these tags
Background (cont.)
Current Solutions:
 Picasa
 Windows Live Photo Gallery
Problems with these solutions:
 Duplicate images
 Limited tagging options
 Very limited auto-tagging
User Requirements
 Eliminate Duplicate Images
 Label Images with a set of Tags
Andres Iniesta
Mark Van Bommel
Place: Soccer City
(Johannesburg)
Occasion: FIFA World
Cup 2010 Final
Description: Iniesta and
Sneijder contest for the
ball
Date: 11th July 2010
Wesley Sneijder
Time: 23h30
User Requirements (cont.)
 Object Detection
Human
Detect and label
objects
Dog
User Requirements (cont.)
 Searching Function
Search:
Roland
User Requirements (cont.)
 Searching Function
Search:
Roland at the University of the Western Cape
Requirements Analysis
Software and programming tools required:
 Python
 PyScripter (IDE)
 Tkinter
 Pyexiv2
 Open CV libraries (Open Source Computer Vision Library)
Project Plan
Term 1
Gather Requirements and Analysis
Learn to use:
Image processing tools/techniques in Open CV
Programming in Python
Term 2
Design and development of the prototype
Develop the following functions :
• Eliminate duplicates
• Adding tags to images
• Detecting objects
Term 3
Coding the final application
Develop the GUI for the application
Develop search function
Term 4
Testing and Evaluation
Refactoring code if necessary
References
 Willow Garage, 2010. Object Detection. Available at:
http://opencv.willowgarage.com/documentation/python/objdetect_cascade_classificati
on.html#haardetectobjects. Last accessed 12 March 2012.
 Google, 2012. Picasa. Available at: http://picasa.google.com. Last accessed 13 Mar 2012.
 Google, 2011. Project Home of PyScripter. Available at:
http://code.google.com/p/pyscripter/. Last accessed 20 February 2012.
 Olivier Tilloy, 2010. Pyexiv2 Documentation. Available at:
http://tilloy.net/dev/pyexiv2/doc/release-0.2.0/index.html. Last accessed 27 February
2012.
Questions