Improving Web Image Search using Meta Re-rankers

Size: px
Start display at page:

Download "Improving Web Image Search using Meta Re-rankers"

Transcription

1 VOLUME-1, ISSUE-V (Aug-Sep 2013) IS NOW AVAILABLE AT: Improvng Web Image Search usng Meta Re-rankers B.Kavtha 1, N. Suata 2 1 Department of Computer Scence and Engneerng, Chtanya Bharath Insttute of Technology,Hyderabad, INDIA 2 Department of Computer Scence and Engneerng,Srdev Women s Engneerng College,Hyderabad, INDIA Abstract: The prevous methods for mage search rerankng suffer from the unrelablty of the assumptons under whch the ntal text based mage search result s employed n the rerankng process. In our proposed system, prototype-based rerankng method s suggested address ths problem n scalable fashon. Ths typcal assumpton that the top-mages n the text-based search result are equally relevant s relaxed by lnkng the relevance of the mages to ther ntal rank postons. The number of mages s employed by the ntal search result as the prototypes that serve to vsually represent the query and that are subsequently used to construct Meta re-rankers. For applyng dfferent Meta re-rankers to an mage from the ntal result, then the re-rankng scores are generated, whch are then aggregated by usng a lnear model to produce the fnal relevance score and the new rank poston for an mage n the re-ranked search result. It s mprovng the performance over the text-based mage search engne. Key concepts: Prototype based Meta re-ranker, Text based search Image Re-rankng. 1. Introducton The exstng web mage search engnes, ncludng Google, Bng and Yahoo retreve and rank mages mostly based on the textual nformaton assocated wth the mage n the hostng web pages, such as the ttle and the surroundng text. Whle text-based mage rankng s often effectve to search for relevant mages, the precson of the search result s largely lmted by the msmatch between the true relevance of an mage and ts relevance nferred from the assocated textual descrptons. To mprove the precson of the text-based mage search rankng and vsual rerankng has been proposed to refne the search result from the textbased mage search engne by ncorporatng the nformaton conveyed by the vsual modalty. Based on the mages n the ntal result, vsual prototypes are generated that are vsually representng the query. Each of the prototypes s used to construct a Meta reranker to produce a rerankng score for any other mage from the ntal lst. Fnally, the scores from all the Meta rerankers are aggregated together usng a lnear rerankng model to produce the fnal relevance score for an mage and to defne ts poston n the reranked results lst. The lnear rerankng model s learned n a supervsed fashon to assgn approprate weghts to dfferent meta rerankers. Snce the learned model weghts are related to the ntal text-based rank poston of the correspondng mage and not to the mage tself, then the rerankng model s queryndependent and can be generalzed across queres. Fgure 1. A hgh-level overvew of web mage Search engne 2. Proposed work To mprove the performance of searchng mages vsual search rerankng s very good opton. 4 steps are needed n our module text rankng, Prototype 71 IJDCST

2 VOLUME-1, ISSUE-V (Aug-Sep 2013) IS NOW AVAILABLE AT: generaton, and Meta Re-Ranker and also Re- Rankng Result. Text Rankng: Intal search s text based search. We need mage search engne to submt query from user. In the search engne query s n text format. It s the text based Image search n whch we get the mage rankng on the bases of text query whch we gve. Prototype generaton: In prototype generaton phase we create a rules for mage rerankng on whch further mages has been reranked. In ths we examne the vsual smlartes. From the top L mage set prototypes are generated usng vsual smlartes. These prototypes are used as an nput to the meta ranker. Meta Rankng: In meta rerankng, multple set prototype technque s used. Ths technque s used to compute the rankng score. The computed rerankng score gve as an nput to rerankng model to estmate ultmate rerankng score. In re-rankng module use of K-means clusterng s benefcal. The K-means handles the rankng problem. Thus the basc dea s for decomposng a rankng n to a set off par-wse preferences and then to reduce the rankng-learnng problem nto a par wse classfcaton problem. Rerankng Result: In ths step we get fnal reranked mages n prototype based rankng. In ths paper we proposed a prototypebased rerankng framework, whch constructs meta rerankers correspondng to vsual prototypes score of a gven mage taken from the ntal textbased search result. Fgure 2: Archtecture of Image re-rankng. 3. Image Rerankng Framework The proposed prototype-based rerankng method conssts of two steps. Onlne: In the onlne part, when a textual query s submtted to the mage search engne by a user, ntal search s performed usng any contemporary text-based search technque. Then, the vsual prototypes are generated and for each prototype a meta reranker s constructed. So, for each of the top N mages n the ntal search result, an L-dmensonal score vector s obtaned comprsng the scores from all meta rerankers when appled to that mage. Fnally, the score vector s used as nput to a rerankng model, whch s already turn to offlne to estmate the rankng scores n the reranked mage search lst. representng the textual query and learns the weghts of a lnear rerankng model to combne the results of ndvdual meta rerankers and produces the rerankng 72 IJDCST

3 VOLUME-1, ISSUE-V (Aug-Sep 2013) IS NOW AVAILABLE AT: Offlne: Fgure 3 Image Rerankng Framework The offlne component s devoted to learnng the rerankng model from user-labeled tranng data. Snce the learned model wll be used for rerankng the text-based search results, the tranng set s constructed from these results through the followng steps. Frst, several representatve queres sampled from the query log are selected. Then, usng these queres the top mages are retreved from the textbased mage search engne and downloaded for processng. Fnally for each query-mage par, people are nvted to label the relevance between them to form the ground-truth. After the tranng data s collected, score vector can be computed from the meta rerankers, as mentoned n the onlne part, for each mage and the correspondng query. Then the rerankng model s learned and stored n the memory to be used n the onlne part for respondng to user s submtted queres. Learnng the rerankng model: The lnear rerankng model has learned by estmatng the weghts of the combned scores comng from dfferent meta rerankers. Ths problem can be addressed usng a learnng-to-rank method, by regardng ths score vector as the rankng feature of an mage. Rankng K-means s among the most popular learnng to rank algorthms. Ths algorthm s wdely used K-means clusterng s to handle a rankng problem. The basc dea has to decompose a rankng nto a set of par wse preferences and then to reduce the rankng-learnng problem nto a par-wse classfcaton problem. The basc dea was to decompose a rankng nto a set of par-wse preferences and then to reduce the rankng-learnng problem nto a par-wse classfcaton problem. Standard effcent approaches are to learnng K- means clusterng, such that a sequental mnmal optmzaton, t can be drectly employed for learnng the Rankng K-means. Moreover, the fast algorthm, e.g., the cuttng-plane algorthm, can be adopted to speed up the tranng of a lnear Rankng K-means. The reason s why the learned rerankng model descrbed above can be generalzed across queres beyond those used for the tranng was that the model weghts are not related to specfc mages but to ther rank postons n the text-based search result. The separaton of the model weghts from specfc mages s the key to ensure that there rankng model only needs to be learned once and then t can be appled to any arbtrary query. The exstng learnng s to-rerank methods, ncludng the supervsed-rerankng and query-relatve classfer, desgn the rerankng model based on the hand desgned rankng features defned at a hgher abstracton level or on the ordered vsual words, respectvely. When compared to them, the prototypebased learnng to rerank method learns how lkely the mages at each of the ranked poston n by text-based result are to be relevant to the query. 4. Constructng Meta Rerankers One of the key steps n the Multple Set Prototype mage rerankng method s the constructon of meta 73 IJDCST

4 VOLUME-1, ISSUE-V (Aug-Sep 2013) IS NOW AVAILABLE AT: rerankers. The computed scores are used to nput for the rerankng model to estmate the ultmate rankng scores to determne the rank poston of the mages n the reranked result. There are three types to construct meta rerankers, dependng on how the prototypes are generated from the ntal text-based search result. Sngle mage prototype, Multple average prototype and multple set prototype are the three algorthms for constructng meta rerankers. Sngle-Image Prototype: A straghtforward way to generate a set of A prototype s to select top mages from the text based result, as llustrated n fg: 4. If we denote ths set as then the meta reranker can be bult smply based on the vsual smlarty S(.) between the prototype mage I to be reranked as S P S P L 1, and the to the lnear rerankng model n order to compute the defntve rankng score for mage I : R S ( I ) Where W are the ndvdual weghts from the model weght vector W. Multple average prototypes: Prototype 1 W xs( I P can be construct by frst selectng the top L mages n the ntal search result lst and then by cumulatvely averagng the features of all mages ranked startng from the topmost poston to the poston, as llustrated n Fg. 4. In other words, the prototype P 1 L 1, P s ) ( 2) P can be defned as I (3) Then, ths prototype can be employed to compute the scores of ndvdual meta rerankers by agan computng the vsual smlarty between a prototype and the mage to be reranked: M I / P SI, P......( 4) M S Fgure 4 Sngle-Image prototype s s I / P SI, P (1 ) The score vector aggregatng the values (1) from all meta rerankers s then used as nput 74 IJDCST

5 VOLUME-1, ISSUE-V (Aug-Sep 2013) IS NOW AVAILABLE AT: The multple-set prototype s a more flexble representaton, whch can support the development of more types of Meta rerankers. Gven a multple-set prototype P can learn a vsual classfer by Fgure 5 Multple Average prototype Multple set prototype: The multple-set prototype P MS at rank s defned as a bag of mages ranked from the topmost poston to the rank, as llustrated n Fg.6. regardng all the mages n P as postve samples, whch s then employed as meta reranker and the predcton score s used as the meta rerankng score. Snce a dscrmnatve learnng method s usually more effectve for learnng a vsual model, there s K- means n ths paper. However, t needs not only postve samples but also negatve samples. The Meta reranker wth a multple-set prototype can be defned as follows: M MS ( I / P arg max MS ) p( I ( P MS Where θ s the learned model and / ) (6) / ) ( 7) Here s the analyss of the propertes of the rerankng method based on the multple-average prototype. By usng the dot product as the smlarty measure, a correspondng meta reranker, leads to the followng expresson: P MS Fgure 6 Multple set prototype I (5 ) J 1... The multple-average prototype s the average of features for the mages n the multple-set prototype and can be seen as a specal case of ths prototype. R L 1 ( I ) L xs( I I 1 w x 1 k1, S( I, I )....(8) where L w = k (10) k k The above expressons transform the model based on a multple average prototype on to the model based on a sngle mage prototype, however, wth dfferent weghts. It states that the rankng n the text-based search result represents the orderng of the mportance for each ndvdual mage to be used as a prototype for rerankng. In other words, there rankng k ) (9) 75 IJDCST

6 VOLUME-1, ISSUE-V (Aug-Sep 2013) IS NOW AVAILABLE AT: based on a multple-average prototype wll rely more on the ntal text based result than that based on a sngle mage prototype. Weghts for ndvdual mages by the rerankng based on a multple-average prototype wll declne gradually wth the decreasng ranks. Ths may make ths rerankng model less aggressve and more robust than the one based on a sngle mage prototype. Meanwhle, t makes the rerankng model learned by the multple-average prototype-based rerankng method hardly over-fttng to the tranng queres % 25.00% 20.00% 15.00% 10.00% 5.00% 0.00% P P 5. Comparson and Results a) Comparson TABLE I Performance comparson of varous rerankng methods. Method Precson (Mean Avg. Precson) Text based Rankng 4.39% Pseudo Relevance 15.64% Feed Back Supervsed 16.87% Rerankng Sngle Prototype 19.16% Multple Average 17.57% Prototype Multple Set 23.60% Prototype Multple Set 25.45% Prototype +Text 76 IJDCST

7 VOLUME-1, ISSUE-V (Aug-Sep 2013) IS NOW AVAILABLE AT: Performance comparson of Prototype-Set and Textbaselne from the search engne. The query s arranged n the ascendng order of the performance of Text-baselne. Generally Image search engnes apparently provde an effortless route. But they are presently lmted by returned mage precson. Our obectve n ths work s to re rank a large number of mages of a partcular class automatcally, and to acheve ths wth the hgh precson. Image clusters for each topc are formed by selectng mages where nearby text s top ranked by the topc. The user then parttons the clusters nto postve and negatve for the class. Then second, mages and the assocated text from these clusters are used as exemplars to tran a classfer based on votng on vsual (shape, color, and texture) and text features. Fg 5.1 Query Image P comparson of Prototype-Sngle and Prototype- Average methods. b) Results Query Image When we are searchng for an mage n search engnes, the correspondng mages are loaded. Among them uncategorzed mages are also spotted. However, by producng such databases contanng a large number of mages and wth hgh precson s stll an arduous manual task. Fg 5.2 Gvng Query 77 IJDCST

8 VOLUME-1, ISSUE-V (Aug-Sep 2013) IS NOW AVAILABLE AT: Download Assocate Images, Url Parsng We are usng Google search engne to downloadng mages from the Web. Image Search gves a very low precson (only about 4 percent) and s not used for the harvestng experments. Ths low precson s probably due to the fact that Google selects many mages from Web gallery pages whch contan mages of all sorts. Google s able to select the nclass mages from those pages, e.g., the ones wth the obect-class n the flename; however, f we use those Web pages as seeds, the overall precson greatly decreases. Therefore, we only use Web Search and Google Images, whch are merged nto one data set per obect class. Table 2 lsts the 18 categores downloaded and the correspondng statstcs for nclass and non-class mages. The overall precson of the mages downloaded for all 18 classes s about 29 percent. textual attrbutes whose presence s a strong ndcaton of the mage content. The goal s to re rank the retreved mages. Each feature s treated as bnary: True f t contans the query word (e.g., pengun) and False otherwse. To rerank mages for one partcular class (e.g., pengun), we do not employ the whole mages for that class. Instead, we tran the classfer usng all avalable annotatons except the class we want to rerank. Fg 5.4 Re-Rankng Fg 5.3 Downloadng Images Apply Re-Rankng Algorthm Now descrbe the re rankng of the returned mages based on text and metadata alone. Here, we follow and extend the method proposed by usng a set of Fg 5.5 Applyng Re-rankng K-means Implementaton K-means clusterng s used to form the cluster of smlar mages. Ths technque wll flter PNG or GIF format mages. Based on threshold value the re rankng process wll be done. 78 IJDCST

9 VOLUME-1, ISSUE-V (Aug-Sep 2013) IS NOW AVAILABLE AT: Fg 5.6 K-means Implementaton 6. Concluson Ths paper proposes a prototype based mage rerankng by usng K-means clusterng, whch constructs Meta rerankers correspondng to vsual prototypes representng the textual query and learns the weghts of a lnear rerankng model to combne the results of ndvdual Meta rerankers and produce the rerankng score of a gven mage taken from the ntal text-based search result. It mproves the performance by 25.48% over the text-based search result by combnng prototypes and textual rankng features. The natural extenson of the approach descrbed n ths paper would be to apply the proposed methods to learn concept models from mage search engnes n a semautomatc fashon. Compared to the fully automatc methods, then the sem-automatc approach could learn then the concept models for any arbtrary concept much better and wth only lttle human supervson. Whle the proposed methods have proved effectve for rerankng mage search results, There was envson of two drectons for future work to further mprove the rerankng performance. Frst, It could be could further speed up the Prototype-Set method varant whle decreasng the precson degradaton. Snce top mages are ncrementally added nto the multple-set prototypes to tran the meta rerankers, one of the possble approaches n ths drecton s to utlze the onlne learnng algorthms. Next the second, although It assume that the rank poston s generally correlated wth the relevance value of the mage found there, and whle our results show that ths assumpton can be regarded vald n a general case, stll the devatons from ths expectaton can occur for ndvdual quered. One possble approach here would be to automatcally estmate the query-relatve relablty and accuracy of each meta-reranker and then ncorporate t nto the rerankng model. The another approach may be to learn the rerankng models for dfferent query classes. ACKNOWLEDGMENT We wsh to acknowledge the efforts of Pantech Soluton Pvt ltd., Hyderabad, for gudance whch helped us work hard towards producng ths research work. 7. References [1] Lnun Yang, and Alan Hanalc, Prototype based Image search Rrrankng, IEEE Transactons on Mltmeda, vol. 14, no. 3, June [2] L. Yang and A. Hanalc "Supervsed rerankng for web mage search", Proc. ACM Multmeda, 2010 [3] R. Fergus, L. Fe-Fe, P. Perona and A. Zsserman "Learnng obect categores from Google's mage search", Proc. ICCV, [4] W. H. Hsu, L. S. Kennedy and S.-F. Chang "Vdeo search rerankng va nformaton bottleneck prncple", Proc.ACM Multmeda, [5] M. Frtz and B. Schele "Decomposton, dscovery and detecton of vsual categores usng topc models", Proc. CVPR, [6] W. H. Hsu, L. S. Kennedy and S.-F. Chang "Vdeo search rerankng through random walk over 79 IJDCST

10 VOLUME-1, ISSUE-V (Aug-Sep 2013) IS NOW AVAILABLE AT: document-level context graph", Proc. ACM Multmeda, [7] Y. Jng and S. Balua "Vsualrank: Applyng pagerank to large-scale mage search", IEEE Trans. Pattern Anal. Mach. Intell, vol. 30, no. 11, pp [8] X. Tan, L. Yang, J. Wang, Y. Yang, X. Wu and X.-S. Hua "Bayesan vdeo search rerankng", Proc. ACM Multmeda, [9] Y. Lu, T. Me, X.-S. Hua, J. Tang, X. Wu and S. L "Learnng to vdeo search rerank va pseudo preference feedback", Proc. ICME, [10] F. Schroff, A. Crmns and A. Zsserman "Harvestng mage databases from the web", Proc. ICCV, IJDCST

A Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems

A Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems A Unfed Framework for Semantcs and Feature Based Relevance Feedback n Image Retreval Systems Ye Lu *, Chunhu Hu 2, Xngquan Zhu 3*, HongJang Zhang 2, Qang Yang * School of Computng Scence Smon Fraser Unversty

More information

Machine Learning: Algorithms and Applications

Machine Learning: Algorithms and Applications 14/05/1 Machne Learnng: Algorthms and Applcatons Florano Zn Free Unversty of Bozen-Bolzano Faculty of Computer Scence Academc Year 011-01 Lecture 10: 14 May 01 Unsupervsed Learnng cont Sldes courtesy of

More information

Outline. Discriminative classifiers for image recognition. Where in the World? A nearest neighbor recognition example 4/14/2011. CS 376 Lecture 22 1

Outline. Discriminative classifiers for image recognition. Where in the World? A nearest neighbor recognition example 4/14/2011. CS 376 Lecture 22 1 4/14/011 Outlne Dscrmnatve classfers for mage recognton Wednesday, Aprl 13 Krsten Grauman UT-Austn Last tme: wndow-based generc obect detecton basc ppelne face detecton wth boostng as case study Today:

More information

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers IOSR Journal of Electroncs and Communcaton Engneerng (IOSR-JECE) e-issn: 78-834,p- ISSN: 78-8735.Volume 9, Issue, Ver. IV (Mar - Apr. 04), PP 0-07 Content Based Image Retreval Usng -D Dscrete Wavelet wth

More information

Support Vector Machines

Support Vector Machines /9/207 MIST.6060 Busness Intellgence and Data Mnng What are Support Vector Machnes? Support Vector Machnes Support Vector Machnes (SVMs) are supervsed learnng technques that analyze data and recognze patterns.

More information

Learning the Kernel Parameters in Kernel Minimum Distance Classifier

Learning the Kernel Parameters in Kernel Minimum Distance Classifier Learnng the Kernel Parameters n Kernel Mnmum Dstance Classfer Daoqang Zhang 1,, Songcan Chen and Zh-Hua Zhou 1* 1 Natonal Laboratory for Novel Software Technology Nanjng Unversty, Nanjng 193, Chna Department

More information

Cluster Analysis of Electrical Behavior

Cluster Analysis of Electrical Behavior Journal of Computer and Communcatons, 205, 3, 88-93 Publshed Onlne May 205 n ScRes. http://www.scrp.org/ournal/cc http://dx.do.org/0.4236/cc.205.350 Cluster Analyss of Electrcal Behavor Ln Lu Ln Lu, School

More information

Semantic Image Retrieval Using Region Based Inverted File

Semantic Image Retrieval Using Region Based Inverted File Semantc Image Retreval Usng Regon Based Inverted Fle Dengsheng Zhang, Md Monrul Islam, Guoun Lu and Jn Hou 2 Gppsland School of Informaton Technology, Monash Unversty Churchll, VIC 3842, Australa E-mal:

More information

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task Proceedngs of NTCIR-6 Workshop Meetng, May 15-18, 2007, Tokyo, Japan Term Weghtng Classfcaton System Usng the Ch-square Statstc for the Classfcaton Subtask at NTCIR-6 Patent Retreval Task Kotaro Hashmoto

More information

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data A Fast Content-Based Multmeda Retreval Technque Usng Compressed Data Borko Furht and Pornvt Saksobhavvat NSF Multmeda Laboratory Florda Atlantc Unversty, Boca Raton, Florda 3343 ABSTRACT In ths paper,

More information

Lecture 5: Multilayer Perceptrons

Lecture 5: Multilayer Perceptrons Lecture 5: Multlayer Perceptrons Roger Grosse 1 Introducton So far, we ve only talked about lnear models: lnear regresson and lnear bnary classfers. We noted that there are functons that can t be represented

More information

TN348: Openlab Module - Colocalization

TN348: Openlab Module - Colocalization TN348: Openlab Module - Colocalzaton Topc The Colocalzaton module provdes the faclty to vsualze and quantfy colocalzaton between pars of mages. The Colocalzaton wndow contans a prevew of the two mages

More information

Problem Set 3 Solutions

Problem Set 3 Solutions Introducton to Algorthms October 4, 2002 Massachusetts Insttute of Technology 6046J/18410J Professors Erk Demane and Shaf Goldwasser Handout 14 Problem Set 3 Solutons (Exercses were not to be turned n,

More information

Query Clustering Using a Hybrid Query Similarity Measure

Query Clustering Using a Hybrid Query Similarity Measure Query clusterng usng a hybrd query smlarty measure Fu. L., Goh, D.H., & Foo, S. (2004). WSEAS Transacton on Computers, 3(3), 700-705. Query Clusterng Usng a Hybrd Query Smlarty Measure Ln Fu, Don Hoe-Lan

More information

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points;

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points; Subspace clusterng Clusterng Fundamental to all clusterng technques s the choce of dstance measure between data ponts; D q ( ) ( ) 2 x x = x x, j k = 1 k jk Squared Eucldean dstance Assumpton: All features

More information

Relevance Feedback for Image Retrieval

Relevance Feedback for Image Retrieval Vashal D Dhale et al, / (IJCSIT Internatonal Journal of Computer Scence and Informaton Technologes, Vol 4 (2, 203, 39-323 Relevance Feedback for Image Retreval Vashal D Dhale, Dr A R Mahaan, Prof Uma Thakur

More information

Machine Learning 9. week

Machine Learning 9. week Machne Learnng 9. week Mappng Concept Radal Bass Functons (RBF) RBF Networks 1 Mappng It s probably the best scenaro for the classfcaton of two dataset s to separate them lnearly. As you see n the below

More information

UB at GeoCLEF Department of Geography Abstract

UB at GeoCLEF Department of Geography   Abstract UB at GeoCLEF 2006 Mguel E. Ruz (1), Stuart Shapro (2), June Abbas (1), Slva B. Southwck (1) and Davd Mark (3) State Unversty of New York at Buffalo (1) Department of Lbrary and Informaton Studes (2) Department

More information

Parallelism for Nested Loops with Non-uniform and Flow Dependences

Parallelism for Nested Loops with Non-uniform and Flow Dependences Parallelsm for Nested Loops wth Non-unform and Flow Dependences Sam-Jn Jeong Dept. of Informaton & Communcaton Engneerng, Cheonan Unversty, 5, Anseo-dong, Cheonan, Chungnam, 330-80, Korea. seong@cheonan.ac.kr

More information

Available online at Available online at Advanced in Control Engineering and Information Science

Available online at   Available online at   Advanced in Control Engineering and Information Science Avalable onlne at wwwscencedrectcom Avalable onlne at wwwscencedrectcom Proceda Proceda Engneerng Engneerng 00 (2011) 15000 000 (2011) 1642 1646 Proceda Engneerng wwwelsevercom/locate/proceda Advanced

More information

Performance Evaluation of Information Retrieval Systems

Performance Evaluation of Information Retrieval Systems Why System Evaluaton? Performance Evaluaton of Informaton Retreval Systems Many sldes n ths secton are adapted from Prof. Joydeep Ghosh (UT ECE) who n turn adapted them from Prof. Dk Lee (Unv. of Scence

More information

CMPS 10 Introduction to Computer Science Lecture Notes

CMPS 10 Introduction to Computer Science Lecture Notes CPS 0 Introducton to Computer Scence Lecture Notes Chapter : Algorthm Desgn How should we present algorthms? Natural languages lke Englsh, Spansh, or French whch are rch n nterpretaton and meanng are not

More information

Keyword-based Document Clustering

Keyword-based Document Clustering Keyword-based ocument lusterng Seung-Shk Kang School of omputer Scence Kookmn Unversty & AIrc hungnung-dong Songbuk-gu Seoul 36-72 Korea sskang@kookmn.ac.kr Abstract ocument clusterng s an aggregaton of

More information

Manifold-Ranking Based Keyword Propagation for Image Retrieval *

Manifold-Ranking Based Keyword Propagation for Image Retrieval * Manfold-Rankng Based Keyword Propagaton for Image Retreval * Hanghang Tong,, Jngru He,, Mngjng L 2, We-Yng Ma 2, Hong-Jang Zhang 2 and Changshu Zhang 3,3 Department of Automaton, Tsnghua Unversty, Bejng

More information

A Binarization Algorithm specialized on Document Images and Photos

A Binarization Algorithm specialized on Document Images and Photos A Bnarzaton Algorthm specalzed on Document mages and Photos Ergna Kavalleratou Dept. of nformaton and Communcaton Systems Engneerng Unversty of the Aegean kavalleratou@aegean.gr Abstract n ths paper, a

More information

Collaboratively Regularized Nearest Points for Set Based Recognition

Collaboratively Regularized Nearest Points for Set Based Recognition Academc Center for Computng and Meda Studes, Kyoto Unversty Collaboratvely Regularzed Nearest Ponts for Set Based Recognton Yang Wu, Mchhko Mnoh, Masayuk Mukunok Kyoto Unversty 9/1/013 BMVC 013 @ Brstol,

More information

Local Quaternary Patterns and Feature Local Quaternary Patterns

Local Quaternary Patterns and Feature Local Quaternary Patterns Local Quaternary Patterns and Feature Local Quaternary Patterns Jayu Gu and Chengjun Lu The Department of Computer Scence, New Jersey Insttute of Technology, Newark, NJ 0102, USA Abstract - Ths paper presents

More information

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 1. SSDH: Semi-supervised Deep Hashing for Large Scale Image Retrieval

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 1. SSDH: Semi-supervised Deep Hashing for Large Scale Image Retrieval IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY SSDH: Sem-supervsed Deep Hashng for Large Scale Image Retreval Jan Zhang, and Yuxn Peng arxv:607.08477v2 [cs.cv] 8 Jun 207 Abstract Hashng

More information

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur FEATURE EXTRACTION Dr. K.Vjayarekha Assocate Dean School of Electrcal and Electroncs Engneerng SASTRA Unversty, Thanjavur613 41 Jont Intatve of IITs and IISc Funded by MHRD Page 1 of 8 Table of Contents

More information

An Image Fusion Approach Based on Segmentation Region

An Image Fusion Approach Based on Segmentation Region Rong Wang, L-Qun Gao, Shu Yang, Yu-Hua Cha, and Yan-Chun Lu An Image Fuson Approach Based On Segmentaton Regon An Image Fuson Approach Based on Segmentaton Regon Rong Wang, L-Qun Gao, Shu Yang 3, Yu-Hua

More information

User Authentication Based On Behavioral Mouse Dynamics Biometrics

User Authentication Based On Behavioral Mouse Dynamics Biometrics User Authentcaton Based On Behavoral Mouse Dynamcs Bometrcs Chee-Hyung Yoon Danel Donghyun Km Department of Computer Scence Department of Computer Scence Stanford Unversty Stanford Unversty Stanford, CA

More information

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION 1 THE PUBLISHING HOUSE PROCEEDINGS OF THE ROMANIAN ACADEMY, Seres A, OF THE ROMANIAN ACADEMY Volume 4, Number 2/2003, pp.000-000 A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION Tudor BARBU Insttute

More information

Image Alignment CSC 767

Image Alignment CSC 767 Image Algnment CSC 767 Image algnment Image from http://graphcs.cs.cmu.edu/courses/15-463/2010_fall/ Image algnment: Applcatons Panorama sttchng Image algnment: Applcatons Recognton of object nstances

More information

A Modified Median Filter for the Removal of Impulse Noise Based on the Support Vector Machines

A Modified Median Filter for the Removal of Impulse Noise Based on the Support Vector Machines A Modfed Medan Flter for the Removal of Impulse Nose Based on the Support Vector Machnes H. GOMEZ-MORENO, S. MALDONADO-BASCON, F. LOPEZ-FERRERAS, M. UTRILLA- MANSO AND P. GIL-JIMENEZ Departamento de Teoría

More information

The Research of Support Vector Machine in Agricultural Data Classification

The Research of Support Vector Machine in Agricultural Data Classification The Research of Support Vector Machne n Agrcultural Data Classfcaton Le Sh, Qguo Duan, Xnmng Ma, Me Weng College of Informaton and Management Scence, HeNan Agrcultural Unversty, Zhengzhou 45000 Chna Zhengzhou

More information

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance Tsnghua Unversty at TAC 2009: Summarzng Mult-documents by Informaton Dstance Chong Long, Mnle Huang, Xaoyan Zhu State Key Laboratory of Intellgent Technology and Systems, Tsnghua Natonal Laboratory for

More information

Combining Multiple Resources, Evidence and Criteria for Genomic Information Retrieval

Combining Multiple Resources, Evidence and Criteria for Genomic Information Retrieval Combnng Multple Resources, Evdence and Crtera for Genomc Informaton Retreval Luo S 1, Je Lu 2 and Jame Callan 2 1 Department of Computer Scence, Purdue Unversty, West Lafayette, IN 47907, USA ls@cs.purdue.edu

More information

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,

More information

Course Introduction. Algorithm 8/31/2017. COSC 320 Advanced Data Structures and Algorithms. COSC 320 Advanced Data Structures and Algorithms

Course Introduction. Algorithm 8/31/2017. COSC 320 Advanced Data Structures and Algorithms. COSC 320 Advanced Data Structures and Algorithms Course Introducton Course Topcs Exams, abs, Proects A quc loo at a few algorthms 1 Advanced Data Structures and Algorthms Descrpton: We are gong to dscuss algorthm complexty analyss, algorthm desgn technques

More information

An Optimal Algorithm for Prufer Codes *

An Optimal Algorithm for Prufer Codes * J. Software Engneerng & Applcatons, 2009, 2: 111-115 do:10.4236/jsea.2009.22016 Publshed Onlne July 2009 (www.scrp.org/journal/jsea) An Optmal Algorthm for Prufer Codes * Xaodong Wang 1, 2, Le Wang 3,

More information

Federated Search of Text-Based Digital Libraries in Hierarchical Peer-to-Peer Networks

Federated Search of Text-Based Digital Libraries in Hierarchical Peer-to-Peer Networks Federated Search of Text-Based Dgtal Lbrares n Herarchcal Peer-to-Peer Networks Je Lu School of Computer Scence Carnege Mellon Unversty Pttsburgh, PA 15213 jelu@cs.cmu.edu Jame Callan School of Computer

More information

Classifier Selection Based on Data Complexity Measures *

Classifier Selection Based on Data Complexity Measures * Classfer Selecton Based on Data Complexty Measures * Edth Hernández-Reyes, J.A. Carrasco-Ochoa, and J.Fco. Martínez-Trndad Natonal Insttute for Astrophyscs, Optcs and Electroncs, Lus Enrque Erro No.1 Sta.

More information

SRBIR: Semantic Region Based Image Retrieval by Extracting the Dominant Region and Semantic Learning

SRBIR: Semantic Region Based Image Retrieval by Extracting the Dominant Region and Semantic Learning Journal of Computer Scence 7 (3): 400-408, 2011 ISSN 1549-3636 2011 Scence Publcatons SRBIR: Semantc Regon Based Image Retreval by Extractng the Domnant Regon and Semantc Learnng 1 I. Felc Raam and 2 S.

More information

Edge Detection in Noisy Images Using the Support Vector Machines

Edge Detection in Noisy Images Using the Support Vector Machines Edge Detecton n Nosy Images Usng the Support Vector Machnes Hlaro Gómez-Moreno, Saturnno Maldonado-Bascón, Francsco López-Ferreras Sgnal Theory and Communcatons Department. Unversty of Alcalá Crta. Madrd-Barcelona

More information

An enhanced representation of time series which allows fast and accurate classification, clustering and relevance feedback

An enhanced representation of time series which allows fast and accurate classification, clustering and relevance feedback An enhanced representaton of tme seres whch allows fast and accurate classfcaton, clusterng and relevance feedback Eamonn J. Keogh and Mchael J. Pazzan Department of Informaton and Computer Scence Unversty

More information

Internet Search: Interactive On-Line Image Search Re-Ranking

Internet Search: Interactive On-Line Image Search Re-Ranking ISSN: 2278 0211 (Online) Internet Search: Interactive On-Line Image Search Re-Ranking Atchut Pavan Kumar. P Department Of Computer Science, Arora Technological Research Institute, Parvathapur, Hyderabad,

More information

Compiler Design. Spring Register Allocation. Sample Exercises and Solutions. Prof. Pedro C. Diniz

Compiler Design. Spring Register Allocation. Sample Exercises and Solutions. Prof. Pedro C. Diniz Compler Desgn Sprng 2014 Regster Allocaton Sample Exercses and Solutons Prof. Pedro C. Dnz USC / Informaton Scences Insttute 4676 Admralty Way, Sute 1001 Marna del Rey, Calforna 90292 pedro@s.edu Regster

More information

EECS 730 Introduction to Bioinformatics Sequence Alignment. Luke Huan Electrical Engineering and Computer Science

EECS 730 Introduction to Bioinformatics Sequence Alignment. Luke Huan Electrical Engineering and Computer Science EECS 730 Introducton to Bonformatcs Sequence Algnment Luke Huan Electrcal Engneerng and Computer Scence http://people.eecs.ku.edu/~huan/ HMM Π s a set of states Transton Probabltes a kl Pr( l 1 k Probablty

More information

Unsupervised Content Discovery in Composite Audio Rui Cai Department of Computer Science and Technology, Tsinghua Univ. Beijing, , China

Unsupervised Content Discovery in Composite Audio Rui Cai Department of Computer Science and Technology, Tsinghua Univ. Beijing, , China Unsupervsed Content Dscovery n Composte Audo Ru Ca Department of Computer Scence and Technology, Tsnghua Unv. Bejng, 100084, Chna caru01@mals.tsnghua.edu.cn Le Lu Mcrosoft Research Asa No. 49 Zhchun Road

More information

A Novel Term_Class Relevance Measure for Text Categorization

A Novel Term_Class Relevance Measure for Text Categorization A Novel Term_Class Relevance Measure for Text Categorzaton D S Guru, Mahamad Suhl Department of Studes n Computer Scence, Unversty of Mysore, Mysore, Inda Abstract: In ths paper, we ntroduce a new measure

More information

Module Management Tool in Software Development Organizations

Module Management Tool in Software Development Organizations Journal of Computer Scence (5): 8-, 7 ISSN 59-66 7 Scence Publcatons Management Tool n Software Development Organzatons Ahmad A. Al-Rababah and Mohammad A. Al-Rababah Faculty of IT, Al-Ahlyyah Amman Unversty,

More information

Feature Reduction and Selection

Feature Reduction and Selection Feature Reducton and Selecton Dr. Shuang LIANG School of Software Engneerng TongJ Unversty Fall, 2012 Today s Topcs Introducton Problems of Dmensonalty Feature Reducton Statstc methods Prncpal Components

More information

Optimizing Document Scoring for Query Retrieval

Optimizing Document Scoring for Query Retrieval Optmzng Document Scorng for Query Retreval Brent Ellwen baellwe@cs.stanford.edu Abstract The goal of ths project was to automate the process of tunng a document query engne. Specfcally, I used machne learnng

More information

Feature Selection for Target Detection in SAR Images

Feature Selection for Target Detection in SAR Images Feature Selecton for Detecton n SAR Images Br Bhanu, Yngqang Ln and Shqn Wang Center for Research n Intellgent Systems Unversty of Calforna, Rversde, CA 95, USA Abstract A genetc algorthm (GA) approach

More information

KIDS Lab at ImageCLEF 2012 Personal Photo Retrieval

KIDS Lab at ImageCLEF 2012 Personal Photo Retrieval KD Lab at mageclef 2012 Personal Photo Retreval Cha-We Ku, Been-Chan Chen, Guan-Bn Chen, L-J Gaou, Rong-ng Huang, and ao-en Wang Knowledge, nformaton, and Database ystem Laboratory Department of Computer

More information

Machine Learning. Topic 6: Clustering

Machine Learning. Topic 6: Clustering Machne Learnng Topc 6: lusterng lusterng Groupng data nto (hopefully useful) sets. Thngs on the left Thngs on the rght Applcatons of lusterng Hypothess Generaton lusters mght suggest natural groups. Hypothess

More information

The Codesign Challenge

The Codesign Challenge ECE 4530 Codesgn Challenge Fall 2007 Hardware/Software Codesgn The Codesgn Challenge Objectves In the codesgn challenge, your task s to accelerate a gven software reference mplementaton as fast as possble.

More information

Efficient Segmentation and Classification of Remote Sensing Image Using Local Self Similarity

Efficient Segmentation and Classification of Remote Sensing Image Using Local Self Similarity ISSN(Onlne): 2320-9801 ISSN (Prnt): 2320-9798 Internatonal Journal of Innovatve Research n Computer and Communcaton Engneerng (An ISO 3297: 2007 Certfed Organzaton) Vol.2, Specal Issue 1, March 2014 Proceedngs

More information

Network Intrusion Detection Based on PSO-SVM

Network Intrusion Detection Based on PSO-SVM TELKOMNIKA Indonesan Journal of Electrcal Engneerng Vol.1, No., February 014, pp. 150 ~ 1508 DOI: http://dx.do.org/10.11591/telkomnka.v1.386 150 Network Intruson Detecton Based on PSO-SVM Changsheng Xang*

More information

A Bilinear Model for Sparse Coding

A Bilinear Model for Sparse Coding A Blnear Model for Sparse Codng Davd B. Grmes and Rajesh P. N. Rao Department of Computer Scence and Engneerng Unversty of Washngton Seattle, WA 98195-2350, U.S.A. grmes,rao @cs.washngton.edu Abstract

More information

BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET

BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET 1 BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET TZU-CHENG CHUANG School of Electrcal and Computer Engneerng, Purdue Unversty, West Lafayette, Indana 47907 SAUL B. GELFAND School

More information

Sequential search. Building Java Programs Chapter 13. Sequential search. Sequential search

Sequential search. Building Java Programs Chapter 13. Sequential search. Sequential search Sequental search Buldng Java Programs Chapter 13 Searchng and Sortng sequental search: Locates a target value n an array/lst by examnng each element from start to fnsh. How many elements wll t need to

More information

Load Balancing for Hex-Cell Interconnection Network

Load Balancing for Hex-Cell Interconnection Network Int. J. Communcatons, Network and System Scences,,, - Publshed Onlne Aprl n ScRes. http://www.scrp.org/journal/jcns http://dx.do.org/./jcns.. Load Balancng for Hex-Cell Interconnecton Network Saher Manaseer,

More information

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices Steps for Computng the Dssmlarty, Entropy, Herfndahl-Hrschman and Accessblty (Gravty wth Competton) Indces I. Dssmlarty Index Measurement: The followng formula can be used to measure the evenness between

More information

Research Article A High-Order CFS Algorithm for Clustering Big Data

Research Article A High-Order CFS Algorithm for Clustering Big Data Moble Informaton Systems Volume 26, Artcle ID 435627, 8 pages http://dx.do.org/.55/26/435627 Research Artcle A Hgh-Order Algorthm for Clusterng Bg Data Fanyu Bu,,2 Zhku Chen, Peng L, Tong Tang, 3 andyngzhang

More information

Learning to Classify Documents with Only a Small Positive Training Set

Learning to Classify Documents with Only a Small Positive Training Set Learnng to Classfy Documents wth Only a Small Postve Tranng Set Xao-L L 1, Bng Lu 2, and See-Kong Ng 1 1 Insttute for Infocomm Research, Heng Mu Keng Terrace, 119613, Sngapore 2 Department of Computer

More information

Active Contours/Snakes

Active Contours/Snakes Actve Contours/Snakes Erkut Erdem Acknowledgement: The sldes are adapted from the sldes prepared by K. Grauman of Unversty of Texas at Austn Fttng: Edges vs. boundares Edges useful sgnal to ndcate occludng

More information

12/2/2009. Announcements. Parametric / Non-parametric. Case-Based Reasoning. Nearest-Neighbor on Images. Nearest-Neighbor Classification

12/2/2009. Announcements. Parametric / Non-parametric. Case-Based Reasoning. Nearest-Neighbor on Images. Nearest-Neighbor Classification Introducton to Artfcal Intellgence V22.0472-001 Fall 2009 Lecture 24: Nearest-Neghbors & Support Vector Machnes Rob Fergus Dept of Computer Scence, Courant Insttute, NYU Sldes from Danel Yeung, John DeNero

More information

Private Information Retrieval (PIR)

Private Information Retrieval (PIR) 2 Levente Buttyán Problem formulaton Alce wants to obtan nformaton from a database, but she does not want the database to learn whch nformaton she wanted e.g., Alce s an nvestor queryng a stock-market

More information

HIGH-LEVEL SEMANTICS OF IMAGES IN WEB DOCUMENTS USING WEIGHTED TAGS AND STRENGTH MATRIX

HIGH-LEVEL SEMANTICS OF IMAGES IN WEB DOCUMENTS USING WEIGHTED TAGS AND STRENGTH MATRIX HIGH-LEVEL SEMANTICS OF IMAGES IN WEB DOCUMENTS USING WEIGHTED TAGS AND STRENGTH MATRIX P.Shanmugavadvu 1, P.Sumathy 2, A.Vadvel 3 12 Department of Computer Scence and Applcatons, Gandhgram Rural Insttute,

More information

CS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 15

CS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 15 CS434a/541a: Pattern Recognton Prof. Olga Veksler Lecture 15 Today New Topc: Unsupervsed Learnng Supervsed vs. unsupervsed learnng Unsupervsed learnng Net Tme: parametrc unsupervsed learnng Today: nonparametrc

More information

Programming in Fortran 90 : 2017/2018

Programming in Fortran 90 : 2017/2018 Programmng n Fortran 90 : 2017/2018 Programmng n Fortran 90 : 2017/2018 Exercse 1 : Evaluaton of functon dependng on nput Wrte a program who evaluate the functon f (x,y) for any two user specfed values

More information

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching A Fast Vsual Trackng Algorthm Based on Crcle Pxels Matchng Zhqang Hou hou_zhq@sohu.com Chongzhao Han czhan@mal.xjtu.edu.cn Ln Zheng Abstract: A fast vsual trackng algorthm based on crcle pxels matchng

More information

Description of NTU Approach to NTCIR3 Multilingual Information Retrieval

Description of NTU Approach to NTCIR3 Multilingual Information Retrieval Proceedngs of the Thrd NTCIR Workshop Descrpton of NTU Approach to NTCIR3 Multlngual Informaton Retreval Wen-Cheng Ln and Hsn-Hs Chen Department of Computer Scence and Informaton Engneerng Natonal Tawan

More information

Unsupervised object segmentation in video by efficient selection of highly probable positive features

Unsupervised object segmentation in video by efficient selection of highly probable positive features Unsupervsed object segmentaton n vdeo by effcent selecton of hghly probable postve features Emanuela Haller 1,2 and Marus Leordeanu 1,2 1 Unversty Poltehnca of Bucharest, Romana 2 Insttute of Mathematcs

More information

CSCI 5417 Information Retrieval Systems Jim Martin!

CSCI 5417 Information Retrieval Systems Jim Martin! CSCI 5417 Informaton Retreval Systems Jm Martn! Lecture 11 9/29/2011 Today 9/29 Classfcaton Naïve Bayes classfcaton Ungram LM 1 Where we are... Bascs of ad hoc retreval Indexng Term weghtng/scorng Cosne

More information

Fuzzy C-Means Initialized by Fixed Threshold Clustering for Improving Image Retrieval

Fuzzy C-Means Initialized by Fixed Threshold Clustering for Improving Image Retrieval Fuzzy -Means Intalzed by Fxed Threshold lusterng for Improvng Image Retreval NAWARA HANSIRI, SIRIPORN SUPRATID,HOM KIMPAN 3 Faculty of Informaton Technology Rangst Unversty Muang-Ake, Paholyotn Road, Patumtan,

More information

Petri Net Based Software Dependability Engineering

Petri Net Based Software Dependability Engineering Proc. RELECTRONIC 95, Budapest, pp. 181-186; October 1995 Petr Net Based Software Dependablty Engneerng Monka Hener Brandenburg Unversty of Technology Cottbus Computer Scence Insttute Postbox 101344 D-03013

More information

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision SLAM Summer School 2006 Practcal 2: SLAM usng Monocular Vson Javer Cvera, Unversty of Zaragoza Andrew J. Davson, Imperal College London J.M.M Montel, Unversty of Zaragoza. josemar@unzar.es, jcvera@unzar.es,

More information

BAYESIAN MULTI-SOURCE DOMAIN ADAPTATION

BAYESIAN MULTI-SOURCE DOMAIN ADAPTATION BAYESIAN MULTI-SOURCE DOMAIN ADAPTATION SHI-LIANG SUN, HONG-LEI SHI Department of Computer Scence and Technology, East Chna Normal Unversty 500 Dongchuan Road, Shangha 200241, P. R. Chna E-MAIL: slsun@cs.ecnu.edu.cn,

More information

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION Paulo Quntlano 1 & Antono Santa-Rosa 1 Federal Polce Department, Brasla, Brazl. E-mals: quntlano.pqs@dpf.gov.br and

More information

TPL-Aware Displacement-driven Detailed Placement Refinement with Coloring Constraints

TPL-Aware Displacement-driven Detailed Placement Refinement with Coloring Constraints TPL-ware Dsplacement-drven Detaled Placement Refnement wth Colorng Constrants Tao Ln Iowa State Unversty tln@astate.edu Chrs Chu Iowa State Unversty cnchu@astate.edu BSTRCT To mnmze the effect of process

More information

Pruning Training Corpus to Speedup Text Classification 1

Pruning Training Corpus to Speedup Text Classification 1 Prunng Tranng Corpus to Speedup Text Classfcaton Jhong Guan and Shugeng Zhou School of Computer Scence, Wuhan Unversty, Wuhan, 430079, Chna hguan@wtusm.edu.cn State Key Lab of Software Engneerng, Wuhan

More information

6.854 Advanced Algorithms Petar Maymounkov Problem Set 11 (November 23, 2005) With: Benjamin Rossman, Oren Weimann, and Pouya Kheradpour

6.854 Advanced Algorithms Petar Maymounkov Problem Set 11 (November 23, 2005) With: Benjamin Rossman, Oren Weimann, and Pouya Kheradpour 6.854 Advanced Algorthms Petar Maymounkov Problem Set 11 (November 23, 2005) Wth: Benjamn Rossman, Oren Wemann, and Pouya Kheradpour Problem 1. We reduce vertex cover to MAX-SAT wth weghts, such that the

More information

A Novel Video Retrieval Method Based on Web Community Extraction Using Features of Video Materials

A Novel Video Retrieval Method Based on Web Community Extraction Using Features of Video Materials IEICE TRANS. FUNDAMENTALS, VOL.E92 A, NO.8 AUGUST 2009 1961 PAPER Specal Secton on Sgnal Processng A Novel Vdeo Retreval Method Based on Web Communty Extracton Usng Features of Vdeo Materals Yasutaka HATAKEYAMA

More information

General Regression and Representation Model for Face Recognition

General Regression and Representation Model for Face Recognition 013 IEEE Conference on Computer Vson and Pattern Recognton Workshops General Regresson and Representaton Model for Face Recognton Janjun Qan, Jan Yang School of Computer Scence and Engneerng Nanjng Unversty

More information

Incremental Multiple Kernel Learning for Object Recognition

Incremental Multiple Kernel Learning for Object Recognition Incremental Multple Kernel Learnng for Obect Recognton Anruddha Kembhav, Behat Sddque, Roland Mezano, Scott McClosey, Larry S. Davs Unversty of Maryland, College Par Honeywell Labs Abstract A good tranng

More information

Personalized Concept-Based Clustering of Search Engine Queries

Personalized Concept-Based Clustering of Search Engine Queries IEEE TRANSACTIONS ON JOURNAL NAME, MANUSCRIPT ID 1 Personalzed Concept-Based Clusterng of Search Engne Queres Kenneth Wa-Tng Leung, Wlfred Ng, and Dk Lun Lee Abstract The exponental growth of nformaton

More information

Fitting: Deformable contours April 26 th, 2018

Fitting: Deformable contours April 26 th, 2018 4/6/08 Fttng: Deformable contours Aprl 6 th, 08 Yong Jae Lee UC Davs Recap so far: Groupng and Fttng Goal: move from array of pxel values (or flter outputs) to a collecton of regons, objects, and shapes.

More information

Fast Feature Value Searching for Face Detection

Fast Feature Value Searching for Face Detection Vol., No. 2 Computer and Informaton Scence Fast Feature Value Searchng for Face Detecton Yunyang Yan Department of Computer Engneerng Huayn Insttute of Technology Hua an 22300, Chna E-mal: areyyyke@63.com

More information

Backpropagation: In Search of Performance Parameters

Backpropagation: In Search of Performance Parameters Bacpropagaton: In Search of Performance Parameters ANIL KUMAR ENUMULAPALLY, LINGGUO BU, and KHOSROW KAIKHAH, Ph.D. Computer Scence Department Texas State Unversty-San Marcos San Marcos, TX-78666 USA ae049@txstate.edu,

More information

A Deflected Grid-based Algorithm for Clustering Analysis

A Deflected Grid-based Algorithm for Clustering Analysis A Deflected Grd-based Algorthm for Clusterng Analyss NANCY P. LIN, CHUNG-I CHANG, HAO-EN CHUEH, HUNG-JEN CHEN, WEI-HUA HAO Department of Computer Scence and Informaton Engneerng Tamkang Unversty 5 Yng-chuan

More information

IMAGE FUSION TECHNIQUES

IMAGE FUSION TECHNIQUES Int. J. Chem. Sc.: 14(S3), 2016, 812-816 ISSN 0972-768X www.sadgurupublcatons.com IMAGE FUSION TECHNIQUES A Short Note P. SUBRAMANIAN *, M. SOWNDARIYA, S. SWATHI and SAINTA MONICA ECE Department, Aarupada

More information

Computer Animation and Visualisation. Lecture 4. Rigging / Skinning

Computer Animation and Visualisation. Lecture 4. Rigging / Skinning Computer Anmaton and Vsualsaton Lecture 4. Rggng / Sknnng Taku Komura Overvew Sknnng / Rggng Background knowledge Lnear Blendng How to decde weghts? Example-based Method Anatomcal models Sknnng Assume

More information

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation Intellgent Informaton Management, 013, 5, 191-195 Publshed Onlne November 013 (http://www.scrp.org/journal/m) http://dx.do.org/10.36/m.013.5601 Qualty Improvement Algorthm for Tetrahedral Mesh Based on

More information

Orthogonal Complement Component Analysis for Positive Samples in SVM Based Relevance Feedback Image Retrieval

Orthogonal Complement Component Analysis for Positive Samples in SVM Based Relevance Feedback Image Retrieval Orthogonal Complement Component Analyss for ostve Samples n SVM Based Relevance Feedback Image Retreval Dacheng Tao and Xaoou Tang Department of Informaton Engneerng The Chnese Unversty of Hong Kong {dctao2,

More information

Parallel matrix-vector multiplication

Parallel matrix-vector multiplication Appendx A Parallel matrx-vector multplcaton The reduced transton matrx of the three-dmensonal cage model for gel electrophoress, descrbed n secton 3.2, becomes excessvely large for polymer lengths more

More information

Learning to Name Faces: A Multimodal Learning Scheme for Search-Based Face Annotation

Learning to Name Faces: A Multimodal Learning Scheme for Search-Based Face Annotation Learnng to Name Faces: A Multmodal Learnng Scheme for Search-Based Face Annotaton Dayong Wang, Steven C.H. Ho, Pengcheng Wu, Janke Zhu, Yng He, Chunyan Mao School of Computer Engneerng, Nanyang Technologcal

More information

Circuit Analysis I (ENGR 2405) Chapter 3 Method of Analysis Nodal(KCL) and Mesh(KVL)

Circuit Analysis I (ENGR 2405) Chapter 3 Method of Analysis Nodal(KCL) and Mesh(KVL) Crcut Analyss I (ENG 405) Chapter Method of Analyss Nodal(KCL) and Mesh(KVL) Nodal Analyss If nstead of focusng on the oltages of the crcut elements, one looks at the oltages at the nodes of the crcut,

More information

Font Recognition in Natural Images via Transfer Learning

Font Recognition in Natural Images via Transfer Learning Font Recognton n Natural Images va Transfer Learnng Yzh Wang, Zhouhu Lan, Yngmn Tang, and Janguo Xao Insttute of Computer Scence and Technology, Pekng Unversty Abstract. Font recognton s an mportant and

More information