Image Annotation and Feature Extraction

Slides:



Advertisements
Similar presentations
LEARNING SEMANTICS OF WORDS AND PICTURES TEJASWI DEVARAPALLI.
Advertisements

Image Retrieval With Relevant Feedback Hayati Cam & Ozge Cavus IMAGE RETRIEVAL WITH RELEVANCE FEEDBACK Hayati CAM Ozge CAVUS.
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Inference Network Approach to Image Retrieval Don Metzler R. Manmatha Center for Intelligent Information Retrieval University of Massachusetts, Amherst.
Automatically Annotating and Integrating Spatial Datasets Chieng-Chien Chen, Snehal Thakkar, Crail Knoblock, Cyrus Shahabi Department of Computer Science.
Image Retrieval Basics Uichin Lee KAIST KSE Slides based on “Relevance Models for Automatic Image and Video Annotation & Retrieval” by R. Manmatha (UMASS)
1 Content-Based Retrieval (CBR) -in multimedia systems Presented by: Chao Cai Date: March 28, 2006 C SC 561.
Content Based Image Clustering and Image Retrieval Using Multiple Instance Learning Using Multiple Instance Learning Xin Chen Advisor: Chengcui Zhang Department.
Young Deok Chun, Nam Chul Kim, Member, IEEE, and Ick Hoon Jang, Member, IEEE IEEE TRANSACTIONS ON MULTIMEDIA,OCTOBER 2008.
Chapter 11 Beyond Bag of Words. Question Answering n Providing answers instead of ranked lists of documents n Older QA systems generated answers n Current.
Search and Retrieval: More on Term Weighting and Document Ranking Prof. Marti Hearst SIMS 202, Lecture 22.
Morris LeBlanc.  Why Image Retrieval is Hard?  Problems with Image Retrieval  Support Vector Machines  Active Learning  Image Processing ◦ Texture.
Image Search Presented by: Samantha Mahindrakar Diti Gandhi.
Semantics of words and images Presented by Gal Zehavi & Ilan Gendelman.
Automatic Image Annotation and Retrieval using Cross-Media Relevance Models J. Jeon, V. Lavrenko and R. Manmathat Computer Science Department University.
Expectation Maximization Method Effective Image Retrieval Based on Hidden Concept Discovery in Image Database By Sanket Korgaonkar Masters Computer Science.
Support Vector Machines Pattern Recognition Sergios Theodoridis Konstantinos Koutroumbas Second Edition A Tutorial on Support Vector Machines for Pattern.
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman ICCV 2003 Presented by: Indriyati Atmosukarto.
Gimme’ The Context: Context- driven Automatic Semantic Annotation with CPANKOW Philipp Cimiano et al.
Relevance Feedback based on Parameter Estimation of Target Distribution K. C. Sia and Irwin King Department of Computer Science & Engineering The Chinese.
February, Content-Based Image Retrieval Saint-Petersburg State University Natalia Vassilieva Il’ya Markov
WORD-PREDICTION AS A TOOL TO EVALUATE LOW-LEVEL VISION PROCESSES Prasad Gabbur, Kobus Barnard University of Arizona.
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman University of Oxford ICCV 2003.
1 An Empirical Study on Large-Scale Content-Based Image Retrieval Group Meeting Presented by Wyman
Ranking by Odds Ratio A Probability Model Approach let be a Boolean random variable: document d is relevant to query q otherwise Consider document d as.
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
Content-based Image Retrieval (CBIR)
SIEVE—Search Images Effectively through Visual Elimination Ying Liu, Dengsheng Zhang and Guojun Lu Gippsland School of Info Tech,
Information Retrieval in Practice
A Search Engine for Historical Manuscript Images Toni M. Rath, R. Manmatha and Victor Lavrenko Center for Intelligent Information Retrieval University.
Content-Based Video Retrieval System Presented by: Edmund Liang CSE 8337: Information Retrieval.
1 Faculty of Information Technology Generic Fourier Descriptor for Shape-based Image Retrieval Dengsheng Zhang, Guojun Lu Gippsland School of Comp. & Info.
Multimedia Databases (MMDB)
Image and Video Retrieval INST 734 Doug Oard Module 13.
Exploiting Ontologies for Automatic Image Annotation M. Srikanth, J. Varner, M. Bowden, D. Moldovan Language Computer Corporation
Image Retrieval Part I (Introduction). 2 Image Understanding Functions Image indexing similarity matching image retrieval (content-based method)
HANOLISTIC: A HIERARCHICAL AUTOMATIC IMAGE ANNOTATION SYSTEM USING HOLISTIC APPROACH Özge Öztimur Karadağ & Fatoş T. Yarman Vural Department of Computer.
Content-Based Image Retrieval
Automatic Image Annotation by Using Concept-Sensitive Salient Objects for Image Content Representation Jianping Fan, Yuli Gao, Hangzai Luo, Guangyou Xu.
IEEE Int'l Symposium on Signal Processing and its Applications 1 An Unsupervised Learning Approach to Content-Based Image Retrieval Yixin Chen & James.
Image Search using Google Image Outreach Activity July 2011 Virginia Tech.
Fitting: The Hough transform
A Model for Learning the Semantics of Pictures V. Lavrenko, R. Manmatha, J. Jeon Center for Intelligent Information Retrieval Computer Science Department,
Object Recognition a Machine Translation Learning a Lexicon for a Fixed Image Vocabulary Miriam Miklofsky.
Competence Centre on Information Extraction and Image Understanding for Earth Observation 29th March 2007 Category - based Semantic Search Engine 1 Mihai.
1 A Web Search Engine-Based Approach to Measure Semantic Similarity between Words Presenter: Guan-Yu Chen IEEE Trans. on Knowledge & Data Engineering,
From Text to Image: Generating Visual Query for Image Retrieval Wen-Cheng Lin, Yih-Chen Chang and Hsin-Hsi Chen Department of Computer Science and Information.
Semi-Automatic Image Annotation Liu Wenyin, Susan Dumais, Yanfeng Sun, HongJiang Zhang, Mary Czerwinski and Brent Field Microsoft Research.
Effective Automatic Image Annotation Via A Coherent Language Model and Active Learning Rong Jin, Joyce Y. Chai Michigan State University Luo Si Carnegie.
A Novel Visualization Model for Web Search Results Nguyen T, and Zhang J IEEE Transactions on Visualization and Computer Graphics PAWS Meeting Presented.
V. Clustering 인공지능 연구실 이승희 Text: Text mining Page:82-93.
Yixin Chen and James Z. Wang The Pennsylvania State University
Combining Text and Image Queries at ImageCLEF2005: A Corpus-Based Relevance-Feedback Approach Yih-Cheng Chang Department of Computer Science and Information.
On Using SIFT Descriptors for Image Parameter Evaluation Authors: Patrick M. McInerney 1, Juan M. Banda 1, and Rafal A. Angryk 2 1 Montana State University,
VISUAL INFORMATION RETRIEVAL Presented by Dipti Vaidya.
Relevance Feedback in Image Retrieval System: A Survey Tao Huang Lin Luo Chengcui Zhang.
Jianping Fan Department of Computer Science University of North Carolina at Charlotte Charlotte, NC Relevance Feedback for Image Retrieval.
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman University of Oxford ICCV 2003.
Multi-Class Sentiment Analysis with Clustering and Score Representation Yan Zhu.
Content-Based Image Retrieval Readings: Chapter 8:
Video Google: Text Retrieval Approach to Object Matching in Videos
Color-Texture Analysis for Content-Based Image Retrieval
Brain Hemorrhage Detection and Classification Steps
Multimedia Information Retrieval
Improving Retrieval Performance of Zernike Moment Descriptor on Affined Shapes Dengsheng Zhang, Guojun Lu Gippsland School of Comp. & Info Tech Monash.
Matching Words with Pictures
Multimedia Information Retrieval
Authors: C. Shyu, C.Brodley, A. Kak, A. Kosaka, A. Aisen, L. Broderick
Video Google: Text Retrieval Approach to Object Matching in Videos
Presentation transcript:

Image Annotation and Feature Extraction Digital Forensics: Image Annotation and Feature Extraction Latifur Khan, November 2007

Outline How do we retrieve Images? Motivation Annotation Enhancement Correspondence: Models Enhancement Future Work Results Reference

How do we retrieve images? Use Google image search ! Google uses filenames, surrounding text and ignores contents of the images.

Motivation How to retrieve images/videos? CBIR is based on similarity search of visual features Doesn’t support textual queries Doesn’t capture “semantics” Automatically annotate images then retrieve based on the textual annotations. Example Annotations: Tiger, grass.

Motivation Query by CBIR Retrieved image There is a gap between perceptual issue and conceptual issue. Semantic gap: Hard to represent semantic meaning using low-level image features like color, texture and shape. It’s possible to answer query ‘Red ball’ with ‘Red Rose’. Query by CBIR Retrieved image

Motivation Most of current automatic image annotation and retrieval approaches consider Keywords Low-level image features for visual token/region/object Correspondence between keywords and visual tokens Our goal is to develop automated image annotation tecniques with better accuracy

Annotation

Annotation Major steps: Segmentation into regions Clustering to construct blob-tokens Analyze correspondence between key words and blob-tokens Auto Annotation

Annotation: Segmentation & Clustering Images Segments Blob-tokens

Annotation: Correspondence/Linking Our purpose is to find correspondence between words and blob-tokens. P(Tiger|V1), P(V2|grass)…

Auto Annotation Lion Grass Tiger … …. ??

Segmentation: Image Vocabulary Can we represent all the images with a finite set of symbols? Text documents consist of words Images consist of visual terms V123 V89 V988 V4552 V12336 V2 V765 V9887 copyright © R. Manmatha

Construction of Visual Terms Segmented images ( e.g., Blobworld, Normalized-cuts algorithm.) Cluster segments. Each cluster is a visual term/blob-token Images Segments Visterms/blobtoken V1 V2 V3 V4 V1 V5 V6 … …

Discrete Visual terms Rectangular partition works better! Partition keyframe, clusters across images. Segmentation problem can be avoided at some extent. copyright © R. Manmatha

Visual terms Or partition using a rectangular grid and cluster. Actually works better.

Grid vs Segmentation Segmentation vs Rectangular Partition. Results - Rectangular Partition better than segmentation! Model learned over many images. Segmentation over one image.

Feature Extraction & Clustering Color Texture Shape K-means clustering: To generate finite visual terms. Each cluster’s centroid represents a visual term.

Co-Occurrence Models Mori et al. 1999 w1 w2 w3 w4 V1 12 2 1 V2 32 40 13 V3 V4 65 43 Mori et al. 1999 Create the co-occurrence table using a training set of annotated images Tend to annotate with high frequency words Context is ignored Needs joint probability models P( w1 | v1 ) = 12/(12+2+0+1)=0.8 P( v3 | w2 ) = 12/(2+40+12+43)=0.12

Correspondence: Translation Model (TM) Pr(f|e) = ∑ Pr(f,a|e) a Pr(w|v) = ∑ Pr(w,a|v)

Translation Models Duygulu et al. 2002 Use classical IBM machine translation models to translate visterms into words IBM machine translation models Need a bi-lingual corpus to train the models Mary did not slap the green witch Mary no daba una botefada a la bruja verde V2 V4 V6 Maui People Dance V1 V34 V321 V21 Tiger grass sky … … … … … …

Correspondence (TM ) B B N X = W N W

Correspondence (TM ) B W Bj Wi N N

Results Dataset Corel Stock Photo CDs. 600 CDs, each of them consists of 100 images under same topic. We select 5000 images (4500 training, 500 testing). Each image has manual annotation. 374 words and 500 blobs. sun city sky mountain grizzly bear meadow water

Results Experimental Context 3,000 training objects 300 images for testing Each object is represented by a vector of 30 dimensions: color, texture, and shape

Results Each Image Object/Blob-token has 30 features: Size -- portion of the image covered by the region. Position -- coordinates of the region center of mass normalized by the image dimensions. Color -- average and standard deviation of (R,G, B), (L, a, b) over the region. Texture -- average and variance of 16 filter responses, four differences of Gaussian filters with different sigmas, and 12 oriented filters, aligned in 30-degree increments. For shape, we use six features (i.e., area, x, y, boundary, convexity, and moment of inertia).

Results Examples for automatic annotation

Results The number of segments annotated correctly among 299 testing segments for different models

Results Correspondence based on K-means--- PTK. Correspondence based on Weighted Feature Selection --- PTS. With GDR dimensionality of image object will be reduced (say from 30 to 20) and then apply K-means and so on.

Results Precision p Recall r Result of Common E measure NumCorrect NumCorrect means the number of retrieved images which contain query keyword in its original annotation NumRetrieved is the number of retrieved images NumExist is the total number of images in test set containing query keyword in annotation Result of Common E measure E=1-2/(1/p+1/r) NumCorrect NumExist NumRetrieved

Results: Precision, Recall and E Precision of retrieval for different models

Results: Precision, Recall and E-measure Recall of retrieval for different models

Results: Precision, Recall and E-measure E Measure of retrieval for different models