Content-Based Image Retrieval QBIC Homepage The State Hermitage Museum db2www/qbicSearch.mac/qbic?selLang=English.

Slides:



Advertisements
Similar presentations
Representation and Description
Advertisements

電腦視覺 Computer and Robot Vision I
November 12, 2013Computer Vision Lecture 12: Texture 1Signature Another popular method of representing shape is called the signature. In order to compute.
Automatic Video Shot Detection from MPEG Bit Stream Jianping Fan Department of Computer Science University of North Carolina at Charlotte Charlotte, NC.
Automated Shot Boundary Detection in VIRS DJ Park Computer Science Department The University of Iowa.
1 Texture Texture is a description of the spatial arrangement of color or intensities in an image or a selected region of an image. Structural approach:
1 Texture Texture is a description of the spatial arrangement of color or intensities in an image or a selected region of an image. Structural approach:
July 27, 2002 Image Processing for K.R. Precision1 Image Processing Training Lecture 1 by Suthep Madarasmi, Ph.D. Assistant Professor Department of Computer.
Concepts of Database Management Seventh Edition
Computer Vision Lecture 16: Texture
Chapter 8 Content-Based Image Retrieval. Query By Keyword: Some textual attributes (keywords) should be maintained for each image. The image can be indexed.
Image Indexing and Retrieval using Moment Invariants Imran Ahmad School of Computer Science University of Windsor – Canada.
Image Retrieval by Content (CBIR)
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Lecture 12 Content-Based Image Retrieval
1 Content-Based Retrieval (CBR) -in multimedia systems Presented by: Chao Cai Date: March 28, 2006 C SC 561.
A presentation by Modupe Omueti For CMPT 820:Multimedia Systems
1 Texture Texture is a description of the spatial arrangement of color or intensities in an image or a selected region of an image. Structural approach:
A Study of Approaches for Object Recognition
SWE 423: Multimedia Systems
Stockman MSU CSE1 Image Database Access  Find images from personal collections  Find images on the web  Find images from medical cases  Find images.
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman University of Oxford ICCV 2003.
CS292 Computational Vision and Language Visual Features - Colour and Texture.
1Ellen L. Walker Matching Find a smaller image in a larger image Applications Find object / pattern of interest in a larger picture Identify moving objects.
Lecture 6: Feature matching and alignment CS4670: Computer Vision Noah Snavely.
Content-based Image Retrieval (CBIR)
November 29, 2004AI: Chapter 24: Perception1 Artificial Intelligence Chapter 24: Perception Michael Scherger Department of Computer Science Kent State.
Introduction --Classification Shape ContourRegion Structural Syntactic Graph Tree Model-driven Data-driven Perimeter Compactness Eccentricity.
Computer vision.
Digital Image Processing
Image and Video Retrieval INST 734 Doug Oard Module 13.
Multimedia Information Retrieval
Content-Based Image Retrieval Readings: Chapter 8: Queries Commercial Systems Retrieval Features Indexing in the FIDS System Lead-in to Object.
Image Retrieval Part I (Introduction). 2 Image Understanding Functions Image indexing similarity matching image retrieval (content-based method)
Digital Image Processing, 2nd ed. © 2002 R. C. Gonzalez & R. E. Woods Chapter 11 Representation & Description Chapter 11 Representation.
Digital Image Processing Lecture 20: Representation & Description
Local invariant features Cordelia Schmid INRIA, Grenoble.
Digital Image Processing CSC331
A 3D Model Alignment and Retrieval System Ding-Yun Chen and Ming Ouhyoung.
Digital Camera and Computer Vision Laboratory Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan, R.O.C.
Lecture 7: Features Part 2 CS4670/5670: Computer Vision Noah Snavely.
Local invariant features Cordelia Schmid INRIA, Grenoble.
2005/12/021 Content-Based Image Retrieval Using Grey Relational Analysis Dept. of Computer Engineering Tatung University Presenter: Tienwei Tsai ( 蔡殿偉.
Levels of Image Data Representation 4.2. Traditional Image Data Structures 4.3. Hierarchical Data Structures Chapter 4 – Data structures for.
CS654: Digital Image Analysis Lecture 36: Feature Extraction and Analysis.
CS654: Digital Image Analysis
1 Overview representing region in 2 ways in terms of its external characteristics (its boundary)  focus on shape characteristics in terms of its internal.
VISUAL INFORMATION RETRIEVAL Presented by Dipti Vaidya.
Image features and properties. Image content representation The simplest representation of an image pattern is to list image pixels, one after the other.
Instructor: Mircea Nicolescu Lecture 5 CS 485 / 685 Computer Vision.
1 Faculty of Information Technology Enhanced Generic Fourier Descriptor for Object-Based Image Retrieval Dengsheng Zhang, Guojun Lu Gippsland School of.
1 Review and Summary We have covered a LOT of material, spending more time and more detail on 2D image segmentation and analysis, but hopefully giving.
Sheng-Fang Huang Chapter 11 part I.  After the image is segmented into regions, how to represent and describe these regions? ◦ In terms of its external.
Content-Based Image Retrieval Readings: Chapter 8:
Processing visual information for Computer Vision
Goals of Computer Vision
Image Representation and Description – Representation Schemes
Automatic Video Shot Detection from MPEG Bit Stream
Digital Image Processing Lecture 20: Representation & Description
IMAGE PROCESSING Questions and Answers.
Content-Based Image Retrieval Readings: Chapter 8:
Content-based Image Retrieval (CBIR)
Slope and Curvature Density Functions
Paper Presentation: Shape and Matching
Feature description and matching
Computer Vision Lecture 16: Texture II
بازیابی تصاویر بر اساس محتوا
Aim of the project Take your image Submit it to the search engine
Feature descriptors and matching
Presentation transcript:

Content-Based Image Retrieval QBIC Homepage The State Hermitage Museum db2www/qbicSearch.mac/qbic?selLang=English

Query By Keyword: Some textual attributes (keywords) should be maintained for each image. The image can be indexed according to these attributes, so that they can be rapidly retrieved when a query is issued. This type of query can be expressed in Structured Query Language (SQL). Query By Example (QBE): User just show the system a sample image, then the system should be able to return similar images or images containing similar objects. Image Database Queries

Image Distance & Similarity Measures 1.Color Similarity 2.Texture Similarity 3.Shape Similarity 4.Object & Relationship similarity

Color Similarity Color percentages matching: R:20%, G:50%, B:30% Color histogram matching D hist (I,Q)=(h(I)-h(Q)) T A(h(I)-h(Q)) A is a similarity matrix  colors that are very similar should have similarity values close to one.

Color Example

Color layout matching: compares each grid square of the query to the corresponding grid square of a potential matching image and combines the results into a single image distance  where C I (g) represents the color in grid square g of a database image I and C Q (g) represents the color in the corresponding grid square g of the query image Q. some suitable representations of color are 1.Mean 2.Mean and standard deviation 3.Multi-bin histogram Color Layout Similarity

Color Layout Example1

Color Layout Example2

Pick and click Suppose T(I) is a texture description vector which is a vector of numbers that summarizes the texture in a given image I (for example: Laws texture energy measures), then the texture distance measure is defined by Texture layout Texture Similarity

IQ based on Pick and Click

Shape Similarity 1.Shape Histogram 2.Boundary Matching 3.Sketch Matching

1. Shape Histogram Projection matching Horizontal & vertical projection: Each row and each column become a bin in the histogram. The count that is stored in a bin is the number of 1-pixels that appear in that row or column. Diagonal projection: An alternative is to define the bins from the top left to the bottom right of the shape. Size invariant  the number of row bins and the number of column bins in the bounding box can be fixed, histograms can be normalized before matching. Translation invariant Rotation invariant  compute the axis of the best-fitting ellipse and rotate the shape

水平垂直投影 Horizontal and vertical projections H(i) V(j)

對角投影 (Diagonal projection)

Orientation histogram Construct a histogram over the tangent angle at each pixel on the boundary of the shape. Size invariant  histograms can be normalized before matching. Translation invariant Rotation invariant  choosing the bin with the largest count to be the first bin. Starting point invariant 1. Shape Histogram θ # of pixels

2. Boundary Matching 1D Fourier Transform 1D Fourier Transform on the boundary

If only the first M coefficients (a 0, a 1, …, a M-1 ) are used, then is an approximation of u n Fourier Descriptors the coefficients (a 0, a 1, …, a M-1 ) is called Fourier Descriptors The Fourier distance measure is defined as: Fourier Descriptors

傅立葉描述元之特性 Properties of Fourier Descriptors Simple geometric transformations of a boundary, such as translation, rotation, and scaling, are related to simple operations of the boundary’s Fourier descriptors. TransformationBoundaryFourier descriptor Identity Translation Scaling or zooming Starting point Rotation Reflection

A formula for Fourier Descriptor that is invariant to translation, scaling, rotation, and starting point. A secret formula

IQ based on Boundary Matching

3. Sketch Matching For every image in the database to be compared, perform the following steps. 1.Affine transformation to specified size and applying median filter. 2.Edge detection using a gradient-based edge-finding algorithm  Refined edge image 3.Thinning and shrinking  Abstract image 4.The images are divided into grid squares and matching is performed based on local correlation.

The sketch distance measure is the inverse of the sum of each of the local correlations  where I(g) refres to grid square g of the abstract image I, Q(g) refers to grid square g of the linear sketch resulting from query image Q. 3. Sketch Matching

Object and Relational Similarity Ask for images containing certain objects, such as people or dogs. Face finding Flesh finding Ask for images containing abstract concepts, such as happiness or beauty. Asks for objects with certain spatial relationships, such as cowboy riding a horse. construct a relational graph whose nodes represent objects and edges represent spatial relationships.

Detecting significant changes in videos 1.Scene change 2.Shot change 3.Camera pan 4.Camera zoom 5.Camera effects: fade, dissolve, and wipe  Segment and store video subsequences in digital libraries for random access.

Segmenting Video Sequences The transitions can be used to segment the video and can be detected by large changes in the features of the images over time.

Similarity measure by histogram

Similarity measure by likelihood ratio Break the image into larger blocks and test to see if a majority of the blocks are essentially the same in both images.