CONTENT-BASED IMAGE

RETRIEVAL

“A picture speaks more than a thousand words !!”

Presented By:

D.SRIKANTH
V.M.SRI KRISHNA
G.SRIRAM
B.ABHILASH
INTRODUCTION

2
INTRODUCTION
 Image Retrieval system for retrieving images
from large database of digital images

 Common method of image retrieval utilizes

metadata / keywords

 Manual image annotation is time consuming

 Locating desired image from small database is

possible, where as in large database more
effective techniques are needed

3
EXISTING SYSTEM

 QBIC supports users to retrieve image by colour,

shape and texture

 QBIC provides several query methods

 Simple Query
 Mutli-Feature Query
 Mutli-Pass Query

4
EXISTING SYSTEM

 Photo Book system supports users to

retrieve image by colour, shape and texture

 Photo Book provides set of matching

algorithms, divergence, vector space angle,
histogram and Fourier peak

5
PROPOSED SYSTEM

 Currently most widely used image search engine is

GOOGLE. It provides its users with textual
annotation. Not many images are annotated with
proper description so many relevant images go
unmatched

 CBIR uses Quadratic Distance & Integrated Regional

Matching (I.R.M)
 Quadratic Distance yield metric distance
 IRM is non-metric and gives result that are not optimal

6
PROPOSED SYSTEM

 Our proposed system uses modified IRM and

colour feature which overcomes above
mentioned disadvantages

 We also provide an interface where user can

give query images as input, automatically
extracts the colour feature and compared with
the images in database, retrieve the matching
image

7
HARDWARE REQUIREMENTS

System Configuration:

 Pentium III Processor with 700 MHz

Clock Speed

 256 MB RAM 20 GB HDD, 32 Bit PCI

Ethernet Card.

8
SOFTWARE REQUIREMENTS

Operating System

 Windows NT/2000 (Client/Server).

Software requirements

 Java, JDK 1.4, J2SDK 1.4, Swings, RMI

and Java Network Programming.
9
MODULES

10
MODULES

 ADMINISTRATOR MODULE

 USER MODULE

 SEARCHING MODULE

11
 ADMINISTRATOR MODULE
 Maintaining the
image database.

 Update the database

according to the
users request.

 Classify the images

for efficient
searching.

12
 USER MODULE

 Upload the query

images.

13
SEARCHING MODULE

 Searching based on a given image.

 Integrate the search with the existing

application.

 Combine querying techniques with

content independent metadata.

14
 IMAGE FEATURES

• Texture (Laws, Gabor filters, local binary partition)

• Color (histograms, grid layout, wavelets)

• Shape (first segment the image, then use statistical

or structural shape similarity measures)

• Objects and their Relationships

15
 IMAGE FEATURE / HISTOGRAMS
Query Image Retrieved Images

User
Image Database

Colour Measure

Comparison
Images Histogram 16
 TIGER IMAGE AS A COLOUR
GRAPH

sky

image above above

adjacent
inside
tiger grass

above above
adjacent
sand
17
abstract regions
Global Shape Properties:
Tangent-Angle Histograms

135

0 30 45 135

18
 Gridded Colour

Gridded colour distance is the sum of the color distances

in each of the corresponding grid squares.

1 2 1 2

3 4 3 4

19
 Object Detection:
Rowley’s Face Finder

1. Convert to gray
scale
2. Normalize for
lighting
3. Histogram
equalization
4. xApply
32 neural net(s)
32 windows in
trained structure
a pyramid on 16K
images

20
UML DIAGRAMS

21
CLASS DIAGRAM
DISPLAY
INPUT private : thread image
package image rawimj1 private : imagetodisplay
integer : package_imagecolomns1 ptivate : imagearray
integer : package_imagerows1 integer : noimgs
package_image_tracker1 integer : currentimage
integer : package_pix1 integer : sleeptime
integer : package_pix3 integer : imgcols1
integer : fileno integer : imgrows1
float : he1 integer : pix1
string : str integer : pix3
float : hes
public void main string() float : hes1
package input() integer : fileno1
integer : n
integer : l
integer;k
integer : m
string : str1
string : str2
HISTOGRAM
string : str3
string : str0 integer : imgno
integer : x string : imgname
integer : y float : he1

void init() public histogram()

void start()
void suspend()
void destroy()
void run()
void paint()
void input123() 22
USE CASE DIAGRAM
query image

DBA

image database
visual content description
user

visual content description

feature vector

feature dabase

includes

similarity comparsion

23

retrieval result
SEQUENCE DIAGRAM
USER
User Image Visual Content Feature Vector Similarity Result

Query Image()

Description()

Feature Vector()

Compare Similarity()

Retrive Result()

24
SEQUENCE DIAGRAM
DBA
DBA Image Visual Content Database Similarity Result User

Create image Database()

Visual Content Description()

Feature Database()

Includes()

Retrive result()

User()

25
HOME PAGE

26
HOME PAGE

27
HOME PAGE

28
HOME PAGE

29
CONCLUSION

30
 CONCLUSION

 Satisfactory progress

 It’s easy to compute.

 It’s more stable than the color histogram,

QBIC, Photo Book methods.

31