This document discusses content-based image retrieval (CBIR), which uses computer vision techniques to search for images based on their visual content rather than metadata. CBIR systems allow users to query image databases using either an example image or sketch. The system then analyzes features of the query image like color, texture, and shape to find visually similar images in the database. Users can provide relevance feedback to refine search results. CBIR has applications in domains like art collections, medical imaging, and scientific databases.

1. CONTENT BASED IMAGE
RETRIEVAL

2. INTRODUCTION:
• Content-based image retrieval (CBIR), also
known as query by image content (QBIC) and
content-based visual information retrieval
(CBVIR) is the application of computer vision
techniques to the image retrieval problem,
that is, the problem of searching for digital
images in large databases.

3. INTRODUCTION:
• Searching or Browsing a database of digital
images based on the content of the image
itself rather than on information about the
image.
• User searches database by providing a query
image.
• Content: Refers colors,shapes,textures or any
other information that can derived from
image itself.

4. BASIC TECHNIQUE:

5. TECHNIQUES:
QUERY TECHNIQUES:
Different implementations of CBIR make use
of different types of user queries:
 What is query?
• An image you already have.
• A rough sketch you draw.
• A symbolic description of what you want.
Eg:an image of man and a woman on a beach.

6. Query By example
• It is a technique that involves providing the
CBIR system with an example image that it
will then base its search upon.
• The algorithms may vary depending on the
application, but result images should all share
common elements with the provided example

7. Options for Providing example:
• Preexisting image chosen from random set by
the user.
• User draws a rough approximation of the
image they are looking for.eg: general shapes
• This techniques removes the difficulties that
can arise when trying to describe images with
words.

8. RELEVANCE FEEDBACK:
• Here user progressively refines the search
result by marking images in the results as
“relevant” ,“not relevant”, or “neutral” to the
search query.
• And then repeating the search with the new
information.

9. OTHER QUERY METHOD:
• Other methods include specifying the
proportions of colors desired (e.g. “80%
red,20% blue”) and searching for images that
contain an object given in a query image.

10. IMAGE FEATURES/DISTANCE
MEASURES

11. CONTENT COMPARISON TECHNIQUES:
The sections below describe common
methods for extracting content from images so
that they can be easily compared:
 COLOR:
• Examine the image based on the colour.
• Doesn’t depend on image size or orientation.
• Based on (histograms, gridded layout, wavelets)

12. CONTENT COMPARISON TECHNIQUES
 TEXTURE:
• Texture measures look for visual patterns in
images and how they are spatially defined.
• Represented by texels which are then placed
into a number of sets, depending on how
many textures are detected in the image.

13. CONTENT COMPARISON TECHNIQUES
 SHAPE:
• It doesn’t refer to shape of an image but to
the shape of particular region that is being
sought out.
• It determined by first applying segmentation
or edge detection to an image.

14. APPLICATIONS:
• Art collections.
• Medical Image Databases
CT, MRI, Ultrasound, The Visible Human
• Scientific Databases
e.g. Earth Sciences
• General image Collections for Licensing

15. THANK YOU…..