Scribd
Upload
70 views2 pages

Study On Content Based Image Retrieval

The document discusses content-based image retrieval (CBIR). It describes CBIR as searching an image database to find images that match a query image based on visual features. The key phases of a CBIR system are feature extraction, retrieval methods, and ranking results. Visual features like color and spacing are extracted from images by analyzing color values and distances between colors. Color histograms are commonly used for CBIR. The paper presents a CBIR system that uses color and spacing features to retrieve similar images from a database based on a query image.

Uploaded by

sandy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
70 views2 pages

Study On Content Based Image Retrieval

The document discusses content-based image retrieval (CBIR). It describes CBIR as searching an image database to find images that match a query image based on visual features. The key phases of a CBIR system are feature extraction, retrieval methods, and ranking results. Visual features like color and spacing are extracted from images by analyzing color values and distances between colors. Color histograms are commonly used for CBIR. The paper presents a CBIR system that uses color and spacing features to retrieve similar images from a database based on a query image.

Uploaded by

sandy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Study on Content Based Image Retrieval

Saurabh Sharma Shubham Nath Ratnesh Pathak


CSE 4th Year CSE 4th Year CSE 4th Year
660970101004 150970101031 660970101003
THDC- IHET THDC- IHET THDC- IHET

Abstract :- In this paper we learn about the different techniques which were used or can be
used in future for image retrieval based on content. It gives a basic idea of currently
accessible theory on content based image retrieval. There are various features on basis of
those we can retrieve image instead of using the old method, the text-based indexes for large
images archives. It basically relies on the characterization of primitive features such as
colour, shape and texture that can be automatically extracted from the images themselves.

Keywords :- : Content based image retrieval, Feature extraction, Retrieval, Performance.

INTRODUCTION:-

Content based image retrieval is the in it. This system consists of three main
searching of images from database to phase:
complete the query based on the features
a) Feature Extraction
of images. The need for content-based
b) Retrieving Methods, and
image retrieval is to retrieve images that
are more appropriate, along with multiple c) Ranking Results and Present
features for better retrieval accuracy. Images.
Mission of this work is to retrieve similar
In this we use features like color and
kind of images from the database based on
spacing which is done by extracting the
the features extracted from the query
colors and distance between them in every
image. In this we use features like color
image. The feature extraction is the
and spacing which is done by extracting
essential process of a CBIR system. First,
the colors and distance between them in
the CBIR retrieval system selects
every image. Color and shape are the
appropriate features spaces and explores
features which are used by IBM for its
various visual features to represent an
image retrieval project. Mostly the color
image. Second, based on the selected
feature is used for CBIR technique
features, the images are represented by
particularly the color histogram. CBIR
feature vectors. A retrieval system
image retrieval system presented in this
searches the nearest neighbors in the
paper is called GEO SPATIAL IMAGE
feature space by weighting different
RETREIVAL SYSTEM. Given a query
image , with single/ multiple object present
feature vectors and computing a similarity measurement for these feature vectors.

You might also like