Content-based Image Retrieval
Jason Kroge
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Guidelines and tips
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Content Based Image Retrieval - Computer Vision - Slides | EECS 841, Study notes of Electrical and Electronics Engineering
Material Type: Notes; Professor: Potetz; Class: Computer Vision; Subject: Elect Engr & Computer Science; University: University of Kansas; Term: Fall 2008;
Typology: Study notes
Pre 2010
1 / 13
This page cannot be seen from the preview
Don't miss anything!
Related documents
Partial preview of the text
Download Content Based Image Retrieval - Computer Vision - Slides | EECS 841 and more Study notes Electrical and Electronics Engineering in PDF only on Docsity!
Content-based Image Retrieval
Jason Kroge
Overview
l Introduction
l Query by Content
l Methodology
l Application
l Results
l Conclusion
Query by Content
l Take a user-drawn sketch and match it to images in a database l Has applications in:
- Graphic design, and intellectual property
- Retail catalogs
- Medical imaging
- Geographical information and remote sensing systems
- Crime prevention, and filtering objectionable images
Methodology
l Used a discrete wavelet transform
- Extracts features that resemble some form of similarity which a human subject can perceive
- Features contain information about color, texture, and shape l Wavelet Type: Haar wavelet transform l Color Space: YIQ instead of RGB l Truncation: 40 most significant coefficients l Quantization: Stored only the sign of the coefficients (+1 or -1)
Algorithm (continued)
Application
Application
Application
Conclusion
l Works well if…
- you have already seen the image
- the image has distinct features