Image search engine

Post on 18-Dec-2014

74 views 0 download

description

Engine explained in this ppt ,takes a query image as an input do some process on it ,compare this image with images present in database and retrieve similar images. It uses the concept of content based image retrieval.

Transcript of Image search engine

IMAGE SEARCH ENGINE

Presented to: Presesnted by:Mr. Sanjeev Patel Avanish Kr. Singh (9910103451)Mr. Himanshu Mittal

Date- November 19, 2013

Image search engine is a type of search engine specialised on finding pictures, images, animations etc. Like the text search, image search is an information retrieval system designed to help to find information on the Internet and it allows the user to look for images etc. using keywords or search phrases and to receive a set of thumbnail images, sorted by relevancy.

Types Of Search Engine:  Image Meta Search- search of images based on associated

metadata such as keywords, text, etc. 

Content-based image retrieval (CBIR) –CBIR aims at avoiding the use of textual descriptions and instead retrieves images based on similarities in their contents (textures, colors, shapes etc.) to a user-supplied query image or user-specified image features.

Introduction

Color histogram: A colour histogram is a type of bar graph, where each bar represents a particular colour of the colour space being used.

Texture: It contains important information about the structural arrangement of the surface, such as; clouds, leaves, bricks, fabric, etc.

Edge Detection: Edge detection is the name for a set of mathematical methods which aim at identifying points in a digital image at which the image brightness changes sharply or, more formally, has discontinuities.

Background Study

example of edge detection:

Contd.

Digital Image Processing

A Framework of Web Image Search Engine(RESEARCH PAPER)

An Effective Content-based Web Image Searching Engine Algorithm(RESEARCH PAPER)

http://tarekmamdouh.hubpages.com/hub/Global-and-Local-Color-Histogram - hub

http://tarekmamdouh.hubpages.com/hub/Image-Retrieval-Color-Coherence-Vector

Introduction to matlab

Books ,Url’s and Research Paper that have been used

(a) Text based image comparison algorithm

(b) semantic-gap in the literature, is a gap between inferred understanding / semantics by pixel domain processing using low level cues and human perceptions of visual cues of given image.

 

List some relevant current/open problems.

Histogram Approach:

GCH (Global Color Histogram): Problem with GCH is that it doesn’t include information about color spatial distribution.

LCH(Local Color Histogram): Main disadvantage with LCH is it never give you two same images are equal if one of them is rotated.

histograms for classification is that the representation is

dependent of the color of the object being studied, ignoring its shape and texture. Color histograms can potentially be identical for two images with different object content which happens to share color information.

Contd.

The problem involves comparative study between different feature

detection techniques and entering an image as a query into a software

application that is designed to employ CBIR techniques in extracting

visual properties, and matching them. This is done to retrieve images

that are visually similar to the query image.

Problem Statement

There are two major steps involved in image comparison,So based on that I have divided my project into two parts:

Feature Extraction

Feature Matching

Talking about Feature Extraction I have divided my project into three sub parts(color,edge and texture),each of which includes two different algorithms ,one for feature extraction and another for feature matching

Division Of Project

A) colorHistogram:

Feature Extraction

Texture:

Contd.

Edge:

Contd.

Colour: The color histogram can be built for any

kind of color space, although the term is more often used for three-dimensional spaces like RGB or HSV.

A histogram is created consisting of number of bins on x-axis and and pixel insenties on y-axis.

Here we have used RGB model.

Algo. for feature extraction

A)Sobel The operator consists of a pair of 3×3 convolution kernels as shown in Figure 1. One kernel is simply the other rotated by 90°.

These kernels are designed to respond maximally to edges running vertically and horizontally relative to the pixel grid, one kernel for each of the two perpendicular orientations. The kernels can be applied separately to the input image, to produce separate measurements of the gradient component in each orientation (call these Gx and Gy). These can then be combined together to find the absolute magnitude of the gradient at each point and the orientation of that gradient. The gradient magnitude is given by:

   

 

Edge Detection

   

which is much faster to compute. The angle of orientation of the edge

(relative to the pixel grid) giving rise to the spatial gradient is given by:

a).Energy Level Algorithm:1. Decompose the image into four sub-images

2. Calculate the energy of all decomposed images at the same scale, using :

where M and N are the dimensions of the image, and X is the intensity of

the pixel located at row i and column j in the image map.

3. Repeat from step 1 for the low-low sub-band image, until index ind is equal to 5. Increment ind.

Using the above algorithm, the energy levels of the sub-bands were calculated, and further decomposition of the low-low sub-band image. This is repeated five times, to reach fifth level decomposition. These energy level values are stored to be used in the Euclidean distance algorithm.

Texture

Color: Quadratic distance

Feature Matching

Texture and edges: Euclidean Distance

Contd.