Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi...

37
nuMAP A Content Based Image Retrieval Project

description

Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.BSCS Final Year of 2009 Evening.Group Members:Mohammad Umer Sheikh EP046125Syed Arbab Ahmed EP046142Pervaiz Ahmed EP04A6136Noman Iqbal EP046133Mustafa Turab Ali EP04A6132Project Supervisor:Professor Dr.Aqil BurnyMr. Badar Sami

Transcript of Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi...

Page 1: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

nuMAPA Content Based Image Retrieval Project

Page 2: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

BSCS Final Year EveningGroup Members

• Mohammad Umer Sheikh EP046125• Syed Arbab Ahmed EP046142• Pervaiz Ahmed EP04A6136• Noman Iqbal EP046133• Mustafa Turab Ali

EP04A6132

Project Supervisor• Dr.Aqil Burny• Badar Sami

Page 3: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

• Syed Arbab Ahmed

• EP046142

Page 4: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Definition

• 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 to the image retrieval problem, that is, the problem of searching for digital images in large databases.

Page 5: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Scope of the project

• Content-based image retrieval potentially provides new opportunities to extend and enhance the constraints and limitations imposed by the traditional information retrieval paradigm on image collections.

• The number of CBIR systems is extremely encouraging.

Page 6: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

CBIR Systems

Page 7: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Potential uses for CBIR include

• Photograph archives • Retail catalogs • Medical diagnosis • Crime prevention • The military • Art collections • Intellectual property • Architectural and engineering design • Geographical information and remote sensing

systems

Page 8: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Difference b/w human with Computer

• The basic reason why image retrieval is more difficult than text retrieval is that the digital representation for most images is as a collection of pixels.

• The only information which is explicit in such a representation is the color values at each pixel point.

Page 9: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

CBIR software systems and techniques

• Query by example

• Semantic retrieval

• Other query methods

Page 10: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

• Pervaiz Ahmed

• EP04A6136

Page 11: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Our CBIR System Design

Page 12: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Problem Statement

The problem involves 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 in the database that are visually similar to the query image

Page 13: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Requirement Analysis

At the very first step we require an algorithm which extract features from images.

SIFT algorithm for features extraction

NNS for matching

Page 14: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

SIFT Algorithm (Scale-Invariant Feature Transform )

• SIFT is an image processing algorithm which can be used to detect distinct features in an image.

• Once features have been detected for two different images, one can use these features to answer questions like “are the two images taken of the same object?”

Page 15: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Out put of SIFT

Page 16: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

• Noman Iqbal

• EP046133

Page 17: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Algorithm working phases

Four phases of SIFT

1 Scale-space Extrema Detection 2 Key point localization 3 Orientation Assignment 4 Key point descriptor

Page 18: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Phase 1: Scale-space Extrema Detection

The first phase of the computation seeks to identify potential interest points. It searches over all scales and image locations. The computation is accomplished by using a difference-of-Gaussian (DoG) function. The resulting interest points

are invariant to scale and rotation, meaning that they are persistent across image scales and rotation.

Page 19: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Phase 2: Key point localization

For all interest points found in phase 1, a detailed model is created to determine location and scale.

Key points are selected based on their stability. A stable key point is thus a key point resistant to image distortion

Page 20: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Phase 3: Orientation Assignment

For each of the key points identified in phase 2, SIFT computes the direction of gradients around.

One or more orientations are assigned to each key point based on local image gradient directions.

Page 21: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Phase 4: Key point descriptor

The local image gradients are measured in the region around each key point.

These are transformed into a representation that allows for significant levels of local shape distortion and change in illumination.

Page 22: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

• Mustufa Turab Ali

• EP04A6132

Page 23: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

NNS Algorithm (nearest neighbor search)

For matching we use a NNS.

An algorithm that is able to detect similarities between key points.

Page 24: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Output of NNS

Page 25: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

KD-tree

KD-tree is the most important multidimensional structure decomposes a multidimensional space into hyper rectangles.

A binary tree with both a dimension number and splitting value at each node Each node corresponds to a hyper rectangle Fields of KD-tree node.

Page 26: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

KD-Tree

Page 27: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Image matching

A match where the whole of one image matches the whole of another image.

Part of one image matching the whole of another image.

Part of one image matching part of another image.

Page 28: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Image Test 1

Page 29: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Image Test 2

Page 30: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Image Test 3

Page 31: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

• Muhammad Umer Sheikh

• EP046125

Page 32: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Key point generation

Page 33: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Key point matching

Select a node from the set of all nodes not yet

selected. Mark the node as selected.

Locate the two nearest neighbors of the selected node.

If the distance between the two neighbors are less than or equal to a given distance, we have a match.

Mark the key points as match.

Page 34: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Key points matching

Page 35: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Quality of Match

KS the numbers of Key points in source image

KC the numbers of Key points in compare image

KM the numbers of Key points in match image

Page 36: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Summary and Conclusion

SIFT does what it is designed to do, and it does it well. The most obvious drawback with SIFT is the time it takes to compare two images. The running time of an NNS search is so large that it effectively renders SIFT useless for a System like M2S. However, with modifications like quality of match and the utilization of other metadata, SIFT could be an extremely robust resource for object detection and image matching.

Page 37: Final Presentation of CBIR through SIFT algorithm of our final project of BS(CS) from Karachi University.

Thank you

Questions?