Using Spatial Pyramids with Compacted VLAT for Image Categorization

Size: px
Start display at page:

Download "Using Spatial Pyramids with Compacted VLAT for Image Categorization"

Transcription

1 Usng Spatal Pyramds wth Compacted VLAT for Image Categorzaton Roman Negrel, Davd Pcard, Phlppe-Henr Gosseln To cte ths verson: Roman Negrel, Davd Pcard, Phlppe-Henr Gosseln. Usng Spatal Pyramds wth Compacted VLAT for Image Categorzaton. Internatonal Conference on Pattern Recognton, Nov 2012, Tsukuba, Japan <hal > HAL Id: hal Submtted on 17 Nov 2012 HAL s a mult-dscplnary open access archve for the depost and dssemnaton of scentfc research documents, whether they are publshed or not. The documents may come from teachng and research nsttutons n France or abroad, or from publc or prvate research centers. L archve ouverte plurdscplnare HAL, est destnée au dépôt et à la dffuson de documents scentfques de nveau recherche, publés ou non, émanant des établssements d ensegnement et de recherche franças ou étrangers, des laboratores publcs ou prvés.

2 Usng Spatal Pyramds wth Compacted VLAT for Image Categorzaton Roman Negrel, Davd Pcard and Phlppe-Henr Gosseln ETIS/ENSEA - Unversty of Cergy-Pontose - CNRS, UMR , avenue du Ponceau, BP44, F95014 Cergy-Pontose, France {roman.negrel,pcard,gosseln}@ensea.fr Abstract In ths paper, we propose a compact mage sgnature based on VLAT. Our method ntegrates spatal nformaton whle sgnfcantly reducng the sze of orgnal VLAT by usng two pojecton steps. we carry out experments showng our approach s compettve wth state of the art sgnatures. 1. Introducton Content Based Image Categorzaton s a research feld that has known a rapd development n the last years. The typcal scheme s composed of the followng steps: extracton of local mage descrptors, aggregaton of the descrptors n an mage sgnature, and learnng a classfer n sgnatures space. The most recent and successful methods are Codng/poolng [9], Fsher Vector [6], VLAD [4], and VLAT [7]. In ths paper we present a new method for aggregatng local descrptors based on VLAT [7]. Our method mproves sgnfcantly the classfcaton results over of VLAT, whle reducng ts sze. Ths paper s organzed as follows: the next secton descrbes recent related work on mage representaton and smlartes. Secton 3 ntroduces our novel approach. Fnally we present successful experments on the well known VOC2007 dataset [3]. 2. State of the art In ths secton we present the most recent and effcent mage sgnatures usng local descrptors Codng/Pollng Schemes Codng/Pollng methods proposed n [9] by J. Wang et al. are a generalzaton of BoW methods[8]. These methods are based on vsual words dctonary. The vsual words are computed usng a clusterng algorthm on a tranng set of descrptors. The Codng/Poolng schemes dvde the problem nto two steps. The frst step maps each descrptor of the mage on the codebook ( codng step). The second step aggregates the mapped descrptors nto a sngle sgnature ( poolng step). For the Codng step n [9], they compute a mapped vector α as the result of the followng reconstructon problem: α = argmn b Wα 2 + d α 2, (1) α wth b beng a descrptor, W the codebook matrx, α the projecton coeffcents and d a localty constrant. The output vector α s thus optmzed wth respect to the reconstructon error and constraned to the projecton on few nearby codewords. For the Poolng step, they propose 2 methods: Sum Poolng (sum of all codes) or Max Poolng (maxmum value for each codng coeffcent). Compared to BoW, the codng/poolng schemes gve good performance wth lnear smlartes, whle retanng a small sgnature sze. However ths method s more complex to mplement and requres a fne tunng of the parameters to obtan good results [2] Fsher Vector Recently, Perronnn et al.[6] presented a new method called Fsher Vectors. The authors hypothesze the descrptors can be modeled by a probablty densty functon denoted as u λ of parameters λ. To descrbe the mage, they use the dervatve of the log-lkelhood of all mage descrptors to the model. The key dea s to descrbe the contrbuton of the descrptors to the devaton of the model parameters. The model used s a GMM of parameters µ c and σ c. The elements of the Fsher Vector for each Gaussanccan be wrtten as: G B µ,c = 1 T ω c r γ c(b r ) G B σ,c = 1 T ω c r γ c(b r ) ( ) br µ c σ c [ (br µ c ) 2 σ 2 c, (2) ] 1, (3) Where b r are the descrptors of mage, (ω c,µ c,σ c ) are the weght, mean and standard devaton of Gaussan c, and γ c (b r ) the normalzed lkelhood of b r to

3 Gaussan c. The fnal descrptor s obtaned by concatenaton of Gµ,c B and Gσ,c B for all Gaussans. The Fsher Vector method acheve very good results [2]. However, Fsher Vectors are lmted to the smple model of mxtures of Gaussans wth dagonal matrces. Moreover, the GMM algorthm s computatonally very ntensve Vector of Locally Aggregated Tensors In [7], Pcard et al. proposed an extenson of Fsher vectors, called VLAT for Vector of Locally Aggregated Tensors. Ths method uses a codebook of vsual words, computed wth a clusterng algorthm (typcally: k- mean). They compute the 1st and 2nd order moments for each vsual word (cluster): T c = 1 c µ c = 1 c b rc, (4) r (b rc µ c )(b rc µ c ), (5) r wth c the number of descrptors n cluster c and b rc the descrptors of mage belongng to cluster c. For each mage, the dfference between mage 2nd order moment and the cluster 2nd order moment s computed for each clusterc: T,c = r (b rc µ c )(b rc µ c ) T c. (6) Each T,c s flattened nto a vector v,c. The VLAT sgnature v for mage conssts n the concatenaton of v,c for all clustersc: v = (v,1...v,c ). (7) It s advsable to perform a normalzaton step for best performance. j, v [j] = sgn(v [j]) v [j] α, (8) x = v v (9), wthα = 0.5 typcally. VLAT gves very good results n smlarty search and automatc ndexng of mages wth lnear metrc, but leads to large feature vectors. The sze of the VLAT sgnature sc D D, wthc the number of clusters andd the sze of descrptors Spatal pyramd bnnng The spatal pyramd method [5] allows the ntroducton of spatal nformaton n mage sgnatures. The process conssts n computng a set of p sgnatures for dfferent regons of the mage. To compute the smlarty between mages, the weghted sum of smlartes for all regons s performed. It can be wrtten as the followng kernel functon: K(X,X j ) = p m=1 α m k(x (m),x (m) j ), (10) wth k(, ) the mnor kernel functon and X (m) the sgnatures of mageandj for regon m. 3. Proposed method,x (m) j We propose a new VLAT based sgnature that sgnfcantly reduces the sze of the sgnature, whle ncreasng ther dscrmnatve power. Our scheme s as follows: 1. We perform a Prncpal Component Analyss (PCA) wthn each cluster (We project the descrptors n the space of the egenvectors of ther cluster). 2. We compute VLAT sgnatures for dfferent part of the spatal pyramd. 3. For some tranng set of mages, we then compute the Gram matrx usng Eq. (10) wth a lnear mnor kernel. 4. We then perform a low rank approxmaton of the gram matrx and compute the set of projecton vectors assocated wth the generated subspace. The fnal sgnatures are the projectons of normalzed pyramd VLAT usng the obtaned projecton vectors Pre-projecton: descrptors PCA by cluster As for standard VLAT, we compute the 1st and 2nd order moments (Eq. 4 and 5) of each cluster. We perform a Takag factorzaton oft c matrx: T c = V c D c V c, (11) where D c s a dagonal matrx formed from the egenvalues of T c and V c s a matrx of egenvectors of T c. We denote byd c,pc the matrx wth thep c largest egenvalues on the dagonal: D c,pc = dag(λ c,1...λ c,pc ), (12) wth λ 1,pc λ 2,pc λ c,pc and we denote by V c,pc the matrx of the frstp c egenvectors: V c,pc = [v c,1...v c,pc ]. (13) We perform an approxmaton of the mage descrptors by projecton on the subspace spanned by thep c largest egenvectors oft c : We can thus rewrte Eq. (6): b rc = V c,p c (b rc µ c ). (14) T,c = V c,p c T,c V c,pc. (15)

4 aeroplane bcycle brd boat bottle bus car cat char cow table dog horse bke person plant sheep sofa tran tv Fgure 1. Images from PASCAL Vsual Object Classes Challenge Lke n VLAT, we concatenate each cluster sgnature and do proper normalzaton. Due to the tensor product, the sze of the new sgnature depends on the square of the ( number of egenvector selected n each cluster C ) c=1 p2 c. We propose 2 strateges for selectng the egenvectors n each cluster. The fxed dmenson method s to arbtrarly set the number of egenvalue that s kept for each cluster : p 1 = = p C. The error threshold method s to set a threshold ε on the error ntroduced by the subspace projecton: p c = mn p p s.t Spatal pyramd p =1 1 λ c, D =1 λ ε. (16) c, To add spatal nformaton, we compute the sgnature of Eq.(15) for dfferent regon of spatal pyramd. The spatal regons are obtaned by dvdng mage usng 1 1, 3 1, and 2 2 grds, for a total of 8 regons lke n most mage categorzaton setups [3, 2]. We use a lnear metrc for classfcaton (e.g. the mnor kernel of Eq. (10) s the dot product). Hence, the global sgnature for the mage s the concatenaton of weghted sgnatures for each regon of the pyramd: x = ( α 1 x,1... α m x,m... α 8 x,8 ), (17) wth x,m s the sgnature of the mage computed n the areamof the pyramd Post-projecton: Low rank approxmaton Gven a tranng set S of N mages,we compute the Gram matrxgof sgnatures defned n Eq. (17): G,j = x x j, x S,x j S. (18) Then, we perform the Takag factorzaton ofg: G = ULU, (19) L = dag(λ 1...λ...λ N ), (20) U = (u 1...u...u N ), (21) wth λ 1 λ 2 λ N and u the egenvector assocated wth the egenvalue λ. We want to compute a low rank approxmaton of the Gram matrx. We denote by L t the matrx wth the t largest egenvalues on the dagonal: L t = dag(λ 1...λ t ), (22) and we denote by U t the matrx of the frst t egenvectors: U t = [u 1...u t ]. (23) Then, we compute the projectors n the approxmated subspace: P t = XU t L 1/2 t, (24) wthx = [x 1...x N ] s the matrx of sgnatures for the tranng set S. Ths method akn to Kernel-PCA usng the Spatal Pyramdal Kernel wth a lnear mnor kernel Projecton vectors For some mage, we compute the projected sgnature n the approxmated space: y = P t x, (25) y contans an approxmate and compressed verson of x (from eq.(17)). Ths method selects the most energy drectons of sgnature space. The sze of y s very small compared to the sze of x, as t drectly depends on t (varyng from 1 to N). The fnal step s a l 2 normalzaton ofy : 4. Experments z = y y. (26) In ths secton we descrbe our expermental setup and some results on the PASCAL-VOC 2007 dataset [3]. Ths dataset conssts n about 10,000 mages and 20 categores, and s dvded nto 3 parts : tran, val and test. We used an 1-vs-rest lnear SVM classfer traned on tran + val sets and tested on the test set. We used a fast stochastc gradent descent algorthm wth C =

5 map aeroplane bcycle brd boat bottle bus car cat char cow Our method FV LLC Sze table dog horse bke person plant sheep sofa tran tv Our method 10k FV 320k LLC 200k Table 1. Image classfcaton results on Pascal VOC 2007 dataset compared to [2] map(%) Error threshold method Fxed dmenson method VLAT Sgnature sze Fgure 2. Effect of pre-projecton 10 [1]. We used Mean Average Precson (map) over the 20 classes for performance measurement. We extracted HOG features wth 4 dfferent scales (4px, 6px, 8px and 10px cell sze), every 3 or 6 pxels, dependng on the test. We used a smple k-means clusterng algorthm n order to obtan the codebook. For the low-order approxmaton of the post-projecton step, we used the full dataset Gram matrx Pre-projecton effect In ths secton we study the acton of the preprojecton (secton 3.1). We used a 6 pxels step for extractng HOG features, a codebook of 64 vsual words, only the frst level of the spatal pyramd (1 1) and no post-projecton. To compare the two strateges for estmatng p c, we measured the classfcaton score aganst the sgnature sze. For the fxed dmenson strategy, we reduced the descrptor sze to 32, 48, 64, 80, 112 and 128 dmensons. For the error threshold strategy, we tested 30%, 25%, 20%, 15%, 10%, 5% and 0% of reconstructon error rate ε. As we can see n Fgure 2 the pre-projecton sgnfcantly ncreases the performance relatve to VLAT even f t greatly reduces the sgnatures sze. We can also see that the thresholdng strategy gves better results, whch s consstent wth the fact t balances the error among clusters Classfcaton results To compare our method to the state of the art, we used a smlar setup to [2]. We used a 3 pxels step for extractng HOG features, a codebook of 256 vsual words, and all levels of the spatal pyramd. We set the thresholdεto 10% of reconstructon error (about 74 dmensons). We used all projectors n post-projecton step (about 10k sgnature sze). We can see from Table 1, our sgnature gves comparatve results to the of state of the art methods. However, our sgnature s much smaller and we used HOG descrptors (smpler than SIFT used n [2]). 5. Concluson In ths paper, we proposed a new mage sgnature based on VLAT. Our representaton ncreases dscrmnatve power of VLAT by ntroducng a spatal nformaton whle reducng ts sze sgnfcantly. Tests on VOC 2007 dataset show that our sgnature gves results smlar to state of the art methods, wth smpler descrptors and smaller sgnature. The results are very promsng, and we are lookng forward to a full nvestgaton of the nfluence of two projecton steps. References [1] L. Bottou. Large-scale machne learnng wth stochastc gradent descent. In Y. Lechevaller and G. Saporta, edtors, ICCS, pages , Pars, France, August [2] K. Chatfeld, V. Lemptsky, A. Vedald, and A. Zsserman. The devl s n the detals: an evaluaton of recent feature encodng methods. In BMVC, volume 76, [3] M. Everngham, L. Van Gool, C. K. I. Wllams, J. Wnn, and A. Zsserman. The PASCAL Vsual Object Classes Challenge 2007 Results, [4] H. Jégou, F. Perronnn, M. Douze, J. Sánchez, P. Pérez, and C. Schmd. Aggregatng local mage descrptors nto compact codes. IEEE PAMI, QUAERO. [5] S. Lazebnk, C. Schmd, and J. Ponce. Beyond bags of features: Spatal pyramd matchng for recognzng natural scene categores. In IEEE CVPR, pages , Washngton, DC, USA, IEEE Computer Socety. [6] F. Perronnn, J. Sánchez, and T. Mensnk. Improvng the fsher kernel for large-scale mage classfcaton. In ECCV, pages , [7] D. Pcard and P. Gosseln. Improvng mage smlarty wth vectors of locally aggregated tensors. In ICIP, Brussels, Belgque, September [8] J. Svc and A. Zsserman. Vdeo google: A text retreval approach to object matchng n vdeos. In ICCV, [9] J. Wang, J. Yang, K. Yu, F. Lv, T. Huang, and Y. Gong. Localty-constraned lnear codng for mage classfcaton. In IEEE CVPR, pages , 2010.

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

Large-scale Web Video Event Classification by use of Fisher Vectors

Large-scale Web Video Event Classification by use of Fisher Vectors Large-scale Web Vdeo Event Classfcaton by use of Fsher Vectors Chen Sun and Ram Nevata Unversty of Southern Calforna, Insttute for Robotcs and Intellgent Systems Los Angeles, CA 90089, USA {chensun nevata}@usc.org

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

Face Recognition University at Buffalo CSE666 Lecture Slides Resources:

Face Recognition University at Buffalo CSE666 Lecture Slides Resources: Face Recognton Unversty at Buffalo CSE666 Lecture Sldes Resources: http://www.face-rec.org/algorthms/ Overvew of face recognton algorthms Correlaton - Pxel based correspondence between two face mages Structural

More information

Discriminative Dictionary Learning with Pairwise Constraints

Discriminative Dictionary Learning with Pairwise Constraints Dscrmnatve Dctonary Learnng wth Parwse Constrants Humn Guo Zhuoln Jang LARRY S. DAVIS UNIVERSITY OF MARYLAND Nov. 6 th, Outlne Introducton/motvaton Dctonary Learnng Dscrmnatve Dctonary Learnng wth Parwse

More information

WIRELESS CAPSULE ENDOSCOPY IMAGE CLASSIFICATION BASED ON VECTOR SPARSE CODING.

WIRELESS CAPSULE ENDOSCOPY IMAGE CLASSIFICATION BASED ON VECTOR SPARSE CODING. WIRELESS CAPSULE ENDOSCOPY IMAGE CLASSIFICATION BASED ON VECTOR SPARSE CODING Tao Ma 1, Yuexan Zou 1 *, Zhqang Xang 1, Le L 1 and Y L 1 ADSPLAB/ELIP, School of ECE, Pekng Unversty, Shenzhen 518055, Chna

More information

Viewpoints combined classification method in imagebased plant identification task

Viewpoints combined classification method in imagebased plant identification task Vewponts combned classfcaton method n magebased plant dentfcaton task Gábor Szűcs, Dávd Papp 2, Dánel Lovas 2 Inter-Unversty Centre for Telecommuncatons and Informatcs, Kassa str. 26., H-4028, Debrecen,

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

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

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

Recognizing Faces. Outline

Recognizing Faces. Outline Recognzng Faces Drk Colbry Outlne Introducton and Motvaton Defnng a feature vector Prncpal Component Analyss Lnear Dscrmnate Analyss !"" #$""% http://www.nfotech.oulu.f/annual/2004 + &'()*) '+)* 2 ! &

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

Detection of an Object by using Principal Component Analysis

Detection of an Object by using Principal Component Analysis Detecton of an Object by usng Prncpal Component Analyss 1. G. Nagaven, 2. Dr. T. Sreenvasulu Reddy 1. M.Tech, Department of EEE, SVUCE, Trupath, Inda. 2. Assoc. Professor, Department of ECE, SVUCE, Trupath,

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

Motion Boundary Trajectory for Human Action Recognition

Motion Boundary Trajectory for Human Action Recognition Moton Boundary Trajectory for Human Acton Recognton So-Long Lo and Ah-Chung Tso Faculty of Informaton Technology, Macau Unversty of Scence and Technology Abstract. In ths paper, we propose a novel approach

More information

Human Violence Recognition and Detection in Surveillance Videos

Human Violence Recognition and Detection in Surveillance Videos Human Volence Recognton and Detecton n Survellance Vdeos Potr Blnsk and Francos Bremond INRIA Sopha Antpols, STARS team 2004 Route des Lucoles, BP93, 06902 Sopha Antpols, France {Potr.Blnsk,Francos.Bremond}@nra.fr

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

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

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

EYE CENTER LOCALIZATION ON A FACIAL IMAGE BASED ON MULTI-BLOCK LOCAL BINARY PATTERNS

EYE CENTER LOCALIZATION ON A FACIAL IMAGE BASED ON MULTI-BLOCK LOCAL BINARY PATTERNS P.G. Demdov Yaroslavl State Unversty Anatoly Ntn, Vladmr Khryashchev, Olga Stepanova, Igor Kostern EYE CENTER LOCALIZATION ON A FACIAL IMAGE BASED ON MULTI-BLOCK LOCAL BINARY PATTERNS Yaroslavl, 2015 Eye

More information

Corner-Based Image Alignment using Pyramid Structure with Gradient Vector Similarity

Corner-Based Image Alignment using Pyramid Structure with Gradient Vector Similarity Journal of Sgnal and Informaton Processng, 013, 4, 114-119 do:10.436/jsp.013.43b00 Publshed Onlne August 013 (http://www.scrp.org/journal/jsp) Corner-Based Image Algnment usng Pyramd Structure wth Gradent

More information

Learning Semantic Visual Dictionaries: A new Method For Local Feature Encoding

Learning Semantic Visual Dictionaries: A new Method For Local Feature Encoding Learnng Semantc Vsual Dctonares: A new Method For Local Feature Encodng Bng Shua, Zhen Zuo, Gang Wang School of Electrcal and Electronc Engneerng, Nanyang Technologcal Unversty, Sngapore. Emal: {bshua001,

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

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

Fusion of Deep Features and Weighted VLAD Vectors based on Multiple Features for Image Retrieval

Fusion of Deep Features and Weighted VLAD Vectors based on Multiple Features for Image Retrieval MATEC Web of Conferences, 0500 (07) DTS-07 DO: 005/matecconf/070500 Fuson of Deep Features and Weghted VLAD Vectors based on Multple Features for mage Retreval Yanhong Wang,, Ygang Cen,, Lequan Lang,*,

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

Searching in one billion vectors: re-rank with source coding

Searching in one billion vectors: re-rank with source coding Searchng n one bllon vectors: re-rank wth source codng Hervé Jégou, Roman Tavenard, Matthjs Douze, Laurent Amsaleg To cte ths verson: Hervé Jégou, Roman Tavenard, Matthjs Douze, Laurent Amsaleg. Searchng

More information

High Dimensional Data Clustering

High Dimensional Data Clustering Hgh Dmensonal Data Clusterng Charles Bouveyron 1,2, Stéphane Grard 1, and Cordela Schmd 2 1 LMC-IMAG, BP 53, Unversté Grenoble 1, 38041 Grenoble Cede 9, France charles.bouveyron@mag.fr, stephane.grard@mag.fr

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

A Probability Distribution Kernel based on Whitening. Transformation

A Probability Distribution Kernel based on Whitening. Transformation AMSE JOURNALS-AMSE IIETA publcaton-2017-seres: Advances B; Vol. 60; N 1; pp 93-109 Submtted Jan. 2017; Revsed March 15, 2017, Accepted Aprl 15, 2017 A Probablty Dstrbuton Kernel based on htenng Transformaton

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

Hierarchical Image Retrieval by Multi-Feature Fusion

Hierarchical Image Retrieval by Multi-Feature Fusion Preprnts (www.preprnts.org) NOT PEER-REVIEWED Posted: 26 Aprl 207 do:0.20944/preprnts20704.074.v Artcle Herarchcal Image Retreval by Mult- Fuson Xaojun Lu, Jaojuan Wang,Yngq Hou, Me Yang, Q Wang* and Xangde

More information

A fast algorithm for color image segmentation

A fast algorithm for color image segmentation Unersty of Wollongong Research Onlne Faculty of Informatcs - Papers (Arche) Faculty of Engneerng and Informaton Scences 006 A fast algorthm for color mage segmentaton L. Dong Unersty of Wollongong, lju@uow.edu.au

More information

Face Recognition Based on SVM and 2DPCA

Face Recognition Based on SVM and 2DPCA Vol. 4, o. 3, September, 2011 Face Recognton Based on SVM and 2DPCA Tha Hoang Le, Len Bu Faculty of Informaton Technology, HCMC Unversty of Scence Faculty of Informaton Scences and Engneerng, Unversty

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

Modeling Inter-cluster and Intra-cluster Discrimination Among Triphones

Modeling Inter-cluster and Intra-cluster Discrimination Among Triphones Modelng Inter-cluster and Intra-cluster Dscrmnaton Among Trphones Tom Ko, Bran Mak and Dongpeng Chen Department of Computer Scence and Engneerng The Hong Kong Unversty of Scence and Technology Clear Water

More information

Comparison Study of Textural Descriptors for Training Neural Network Classifiers

Comparison Study of Textural Descriptors for Training Neural Network Classifiers Comparson Study of Textural Descrptors for Tranng Neural Network Classfers G.D. MAGOULAS (1) S.A. KARKANIS (1) D.A. KARRAS () and M.N. VRAHATIS (3) (1) Department of Informatcs Unversty of Athens GR-157.84

More information

High-Boost Mesh Filtering for 3-D Shape Enhancement

High-Boost Mesh Filtering for 3-D Shape Enhancement Hgh-Boost Mesh Flterng for 3-D Shape Enhancement Hrokazu Yagou Λ Alexander Belyaev y Damng We z Λ y z ; ; Shape Modelng Laboratory, Unversty of Azu, Azu-Wakamatsu 965-8580 Japan y Computer Graphcs Group,

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

Human Face Recognition Using Generalized. Kernel Fisher Discriminant

Human Face Recognition Using Generalized. Kernel Fisher Discriminant Human Face Recognton Usng Generalzed Kernel Fsher Dscrmnant ng-yu Sun,2 De-Shuang Huang Ln Guo. Insttute of Intellgent Machnes, Chnese Academy of Scences, P.O.ox 30, Hefe, Anhu, Chna. 2. Department of

More information

Partial Restreaming Approach for Massive Graph Partitioning.

Partial Restreaming Approach for Massive Graph Partitioning. Partal Restreamng Approach for Massve Graph Parttonng. Ghzlane Echbarth, Hamamache Kheddouc To cte ths verson: Ghzlane Echbarth, Hamamache Kheddouc. Partal Restreamng Approach for Massve Graph Parttonng..

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

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

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

A Robust Method for Estimating the Fundamental Matrix

A Robust Method for Estimating the Fundamental Matrix Proc. VIIth Dgtal Image Computng: Technques and Applcatons, Sun C., Talbot H., Ourseln S. and Adraansen T. (Eds.), 0- Dec. 003, Sydney A Robust Method for Estmatng the Fundamental Matrx C.L. Feng and Y.S.

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

PCA Based Gait Segmentation

PCA Based Gait Segmentation Honggu L, Cupng Sh & Xngguo L PCA Based Gat Segmentaton PCA Based Gat Segmentaton Honggu L, Cupng Sh, and Xngguo L 2 Electronc Department, Physcs College, Yangzhou Unversty, 225002 Yangzhou, Chna 2 Department

More information

Semantic Pooling for Image Categorization using Multiple Kernel Learning

Semantic Pooling for Image Categorization using Multiple Kernel Learning Semantic Pooling for Image Categorization using Multiple Kernel Learning Thibaut Durand (1,2), Nicolas Thome (1), Matthieu Cord (1), David Picard (2) (1) Sorbonne Universités, UPMC Univ Paris 06, UMR 7606,

More information

IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 25, NO. 4, APRIL

IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 25, NO. 4, APRIL IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 25, NO. 4, APRIL 2016 1713 Weakly Supervsed Fne-Graned Categorzaton Wth Part-Based Image Representaton Yu Zhang, Xu-Shen We, Janxn Wu, Member, IEEE, Janfe Ca,

More information

Image Representation & Visualization Basic Imaging Algorithms Shape Representation and Analysis. outline

Image Representation & Visualization Basic Imaging Algorithms Shape Representation and Analysis. outline mage Vsualzaton mage Vsualzaton mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and Analyss outlne mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and

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

MULTI-VIEW ANCHOR GRAPH HASHING

MULTI-VIEW ANCHOR GRAPH HASHING MULTI-VIEW ANCHOR GRAPH HASHING Saehoon Km 1 and Seungjn Cho 1,2 1 Department of Computer Scence and Engneerng, POSTECH, Korea 2 Dvson of IT Convergence Engneerng, POSTECH, Korea {kshkawa, seungjn}@postech.ac.kr

More information

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning Outlne Artfcal Intellgence and ts applcatons Lecture 8 Unsupervsed Learnng Professor Danel Yeung danyeung@eee.org Dr. Patrck Chan patrckchan@eee.org South Chna Unversty of Technology, Chna Introducton

More information

What Is the Most Efficient Way to Select Nearest Neighbor Candidates for Fast Approximate Nearest Neighbor Search?

What Is the Most Efficient Way to Select Nearest Neighbor Candidates for Fast Approximate Nearest Neighbor Search? IEEE Internatonal Conference on Computer Vson What Is the Most Effcent Way to Select Nearest Neghbor Canddates for Fast Approxmate Nearest Neghbor Search? Masakazu Iwamura, Tomokazu Sato and Koch Kse Graduate

More information

Brushlet Features for Texture Image Retrieval

Brushlet Features for Texture Image Retrieval DICTA00: Dgtal Image Computng Technques and Applcatons, 1 January 00, Melbourne, Australa 1 Brushlet Features for Texture Image Retreval Chbao Chen and Kap Luk Chan Informaton System Research Lab, School

More information

Online Detection and Classification of Moving Objects Using Progressively Improving Detectors

Online Detection and Classification of Moving Objects Using Progressively Improving Detectors Onlne Detecton and Classfcaton of Movng Objects Usng Progressvely Improvng Detectors Omar Javed Saad Al Mubarak Shah Computer Vson Lab School of Computer Scence Unversty of Central Florda Orlando, FL 32816

More information

Development of an Active Shape Model. Using the Discrete Cosine Transform

Development of an Active Shape Model. Using the Discrete Cosine Transform Development of an Actve Shape Model Usng the Dscrete Cosne Transform Kotaro Yasuda A Thess n The Department of Electrcal and Computer Engneerng Presented n Partal Fulfllment of the Requrements for the

More information

Support Vector Machines

Support Vector Machines Support Vector Machnes Decson surface s a hyperplane (lne n 2D) n feature space (smlar to the Perceptron) Arguably, the most mportant recent dscovery n machne learnng In a nutshell: map the data to a predetermned

More information

Scale Selective Extended Local Binary Pattern For Texture Classification

Scale Selective Extended Local Binary Pattern For Texture Classification Scale Selectve Extended Local Bnary Pattern For Texture Classfcaton Yutng Hu, Zhlng Long, and Ghassan AlRegb Multmeda & Sensors Lab (MSL) Georga Insttute of Technology 03/09/017 Outlne Texture Representaton

More information

Lecture #15 Lecture Notes

Lecture #15 Lecture Notes Lecture #15 Lecture Notes The ocean water column s very much a 3-D spatal entt and we need to represent that structure n an economcal way to deal wth t n calculatons. We wll dscuss one way to do so, emprcal

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

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

Gender Classification using Interlaced Derivative Patterns

Gender Classification using Interlaced Derivative Patterns Gender Classfcaton usng Interlaced Dervatve Patterns Author Shobernejad, Ameneh, Gao, Yongsheng Publshed 2 Conference Ttle Proceedngs of the 2th Internatonal Conference on Pattern Recognton (ICPR 2) DOI

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

Incremental MQDF Learning for Writer Adaptive Handwriting Recognition 1

Incremental MQDF Learning for Writer Adaptive Handwriting Recognition 1 200 2th Internatonal Conference on Fronters n Handwrtng Recognton Incremental MQDF Learnng for Wrter Adaptve Handwrtng Recognton Ka Dng, Lanwen Jn * School of Electronc and Informaton Engneerng, South

More information

An Empirical Comparative Study of Online Handwriting Chinese Character Recognition:Simplified v.s.traditional

An Empirical Comparative Study of Online Handwriting Chinese Character Recognition:Simplified v.s.traditional 2013 12th Internatonal Conference on Document Analyss and Recognton An Emprcal Comparatve Study of Onlne Handwrtng Chnese Recognton:Smplfed v.s.tradtonal Yan Gao, Lanwen Jn +, Wexn Yang School of Electronc

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

Fitting & Matching. Lecture 4 Prof. Bregler. Slides from: S. Lazebnik, S. Seitz, M. Pollefeys, A. Effros.

Fitting & Matching. Lecture 4 Prof. Bregler. Slides from: S. Lazebnik, S. Seitz, M. Pollefeys, A. Effros. Fttng & Matchng Lecture 4 Prof. Bregler Sldes from: S. Lazebnk, S. Setz, M. Pollefeys, A. Effros. How do we buld panorama? We need to match (algn) mages Matchng wth Features Detect feature ponts n both

More information

Shape Representation Robust to the Sketching Order Using Distance Map and Direction Histogram

Shape Representation Robust to the Sketching Order Using Distance Map and Direction Histogram Shape Representaton Robust to the Sketchng Order Usng Dstance Map and Drecton Hstogram Department of Computer Scence Yonse Unversty Kwon Yun CONTENTS Revew Topc Proposed Method System Overvew Sketch Normalzaton

More information

Classification of Face Images Based on Gender using Dimensionality Reduction Techniques and SVM

Classification of Face Images Based on Gender using Dimensionality Reduction Techniques and SVM Classfcaton of Face Images Based on Gender usng Dmensonalty Reducton Technques and SVM Fahm Mannan 260 266 294 School of Computer Scence McGll Unversty Abstract Ths report presents gender classfcaton based

More information

Title: A Novel Protocol for Accuracy Assessment in Classification of Very High Resolution Images

Title: A Novel Protocol for Accuracy Assessment in Classification of Very High Resolution Images 2009 IEEE. Personal use of ths materal s permtted. Permsson from IEEE must be obtaned for all other uses, n any current or future meda, ncludng reprntng/republshng ths materal for advertsng or promotonal

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

High Five: Recognising human interactions in TV shows

High Five: Recognising human interactions in TV shows PATRON-PEREZ ET AL.: RECOGNISING INTERACTIONS IN TV SHOWS 1 Hgh Fve: Recognsng human nteractons n TV shows Alonso Patron-Perez alonso@robots.ox.ac.uk Marcn Marszalek marcn@robots.ox.ac.uk Andrew Zsserman

More information

Comparing Image Representations for Training a Convolutional Neural Network to Classify Gender

Comparing Image Representations for Training a Convolutional Neural Network to Classify Gender 2013 Frst Internatonal Conference on Artfcal Intellgence, Modellng & Smulaton Comparng Image Representatons for Tranng a Convolutonal Neural Network to Classfy Gender Choon-Boon Ng, Yong-Haur Tay, Bok-Mn

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

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

Detection of Human Actions from a Single Example

Detection of Human Actions from a Single Example Detecton of Human Actons from a Sngle Example Hae Jong Seo and Peyman Mlanfar Electrcal Engneerng Department Unversty of Calforna at Santa Cruz 1156 Hgh Street, Santa Cruz, CA, 95064 {rokaf,mlanfar}@soe.ucsc.edu

More information

Outline. Self-Organizing Maps (SOM) US Hebbian Learning, Cntd. The learning rule is Hebbian like:

Outline. Self-Organizing Maps (SOM) US Hebbian Learning, Cntd. The learning rule is Hebbian like: Self-Organzng Maps (SOM) Turgay İBRİKÇİ, PhD. Outlne Introducton Structures of SOM SOM Archtecture Neghborhoods SOM Algorthm Examples Summary 1 2 Unsupervsed Hebban Learnng US Hebban Learnng, Cntd 3 A

More information

Feature Extraction and Test Algorithm for Speaker Verification

Feature Extraction and Test Algorithm for Speaker Verification Feature Extracton and Test Algorthm for Speaker Verfcaton Wu Guo, Renhua Wang and Lrong Da Unversty of Scence and Technology of Chna, Hefe guowu@mal.ustc.edu.cn,{rhw, lrda}@ustc,edu.cn Abstract. In ths

More information

Hermite Splines in Lie Groups as Products of Geodesics

Hermite Splines in Lie Groups as Products of Geodesics Hermte Splnes n Le Groups as Products of Geodescs Ethan Eade Updated May 28, 2017 1 Introducton 1.1 Goal Ths document defnes a curve n the Le group G parametrzed by tme and by structural parameters n the

More information

Lobachevsky State University of Nizhni Novgorod. Polyhedron. Quick Start Guide

Lobachevsky State University of Nizhni Novgorod. Polyhedron. Quick Start Guide Lobachevsky State Unversty of Nzhn Novgorod Polyhedron Quck Start Gude Nzhn Novgorod 2016 Contents Specfcaton of Polyhedron software... 3 Theoretcal background... 4 1. Interface of Polyhedron... 6 1.1.

More information

Inverse-Polar Ray Projection for Recovering Projective Transformations

Inverse-Polar Ray Projection for Recovering Projective Transformations nverse-polar Ray Projecton for Recoverng Projectve Transformatons Yun Zhang The Center for Advanced Computer Studes Unversty of Lousana at Lafayette yxz646@lousana.edu Henry Chu The Center for Advanced

More information

Determining the Optimal Bandwidth Based on Multi-criterion Fusion

Determining the Optimal Bandwidth Based on Multi-criterion Fusion Proceedngs of 01 4th Internatonal Conference on Machne Learnng and Computng IPCSIT vol. 5 (01) (01) IACSIT Press, Sngapore Determnng the Optmal Bandwdth Based on Mult-crteron Fuson Ha-L Lang 1+, Xan-Mn

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

Object-Based Techniques for Image Retrieval

Object-Based Techniques for Image Retrieval 54 Zhang, Gao, & Luo Chapter VII Object-Based Technques for Image Retreval Y. J. Zhang, Tsnghua Unversty, Chna Y. Y. Gao, Tsnghua Unversty, Chna Y. Luo, Tsnghua Unversty, Chna ABSTRACT To overcome the

More information

Keywords - Wep page classification; bag of words model; topic model; hierarchical classification; Support Vector Machines

Keywords - Wep page classification; bag of words model; topic model; hierarchical classification; Support Vector Machines (IJCSIS) Internatonal Journal of Computer Scence and Informaton Securty, Herarchcal Web Page Classfcaton Based on a Topc Model and Neghborng Pages Integraton Wongkot Srura Phayung Meesad Choochart Haruechayasak

More information

Face Detection with Deep Learning

Face Detection with Deep Learning Face Detecton wth Deep Learnng Yu Shen Yus122@ucsd.edu A13227146 Kuan-We Chen kuc010@ucsd.edu A99045121 Yzhou Hao y3hao@ucsd.edu A98017773 Mn Hsuan Wu mhwu@ucsd.edu A92424998 Abstract The project here

More information

Dynamic wetting property investigation of AFM tips in micro/nanoscale

Dynamic wetting property investigation of AFM tips in micro/nanoscale Dynamc wettng property nvestgaton of AFM tps n mcro/nanoscale The wettng propertes of AFM probe tps are of concern n AFM tp related force measurement, fabrcaton, and manpulaton technques, such as dp-pen

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

RECOGNIZING GENDER THROUGH FACIAL IMAGE USING SUPPORT VECTOR MACHINE

RECOGNIZING GENDER THROUGH FACIAL IMAGE USING SUPPORT VECTOR MACHINE Journal of Theoretcal and Appled Informaton Technology 30 th June 06. Vol.88. No.3 005-06 JATIT & LLS. All rghts reserved. ISSN: 99-8645 www.jatt.org E-ISSN: 87-395 RECOGNIZING GENDER THROUGH FACIAL IMAGE

More information

SIGGRAPH Interactive Image Cutout. Interactive Graph Cut. Interactive Graph Cut. Interactive Graph Cut. Hard Constraints. Lazy Snapping.

SIGGRAPH Interactive Image Cutout. Interactive Graph Cut. Interactive Graph Cut. Interactive Graph Cut. Hard Constraints. Lazy Snapping. SIGGRAPH 004 Interactve Image Cutout Lazy Snappng Yn L Jan Sun Ch-Keung Tang Heung-Yeung Shum Mcrosoft Research Asa Hong Kong Unversty Separate an object from ts background Compose the object on another

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

Palmprint Feature Extraction Using 2-D Gabor Filters

Palmprint Feature Extraction Using 2-D Gabor Filters Palmprnt Feature Extracton Usng 2-D Gabor Flters Wa Kn Kong Davd Zhang and Wenxn L Bometrcs Research Centre Department of Computng The Hong Kong Polytechnc Unversty Kowloon Hong Kong Correspondng author:

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

Combining Appearance Models and Markov Random Fields for Category Level Object Segmentation

Combining Appearance Models and Markov Random Fields for Category Level Object Segmentation Combnng Appearance Models and Markov Random Felds for Category Level Object Segmentaton Dane Larlus LEAR - INRIA, INPG Fre de rc Jure LEAR - INRIA, Caen Unversty dane.larlus@nralpes.fr frederc.jure@uncaen.fr

More information

IMAGE MATCHING WITH SIFT FEATURES A PROBABILISTIC APPROACH

IMAGE MATCHING WITH SIFT FEATURES A PROBABILISTIC APPROACH IMAGE MATCHING WITH SIFT FEATURES A PROBABILISTIC APPROACH Jyot Joglekar a, *, Shrsh S. Gedam b a CSRE, IIT Bombay, Doctoral Student, Mumba, Inda jyotj@tb.ac.n b Centre of Studes n Resources Engneerng,

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

An Evaluation of Divide-and-Combine Strategies for Image Categorization by Multi-Class Support Vector Machines

An Evaluation of Divide-and-Combine Strategies for Image Categorization by Multi-Class Support Vector Machines An Evaluaton of Dvde-and-Combne Strateges for Image Categorzaton by Mult-Class Support Vector Machnes C. Demrkesen¹ and H. Cherf¹, ² 1: Insttue of Scence and Engneerng 2: Faculté des Scences Mrande Galatasaray

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

Manifold Regularized Slow Feature Analysis for Dynamic Texture Recognition

Manifold Regularized Slow Feature Analysis for Dynamic Texture Recognition 1 Manfold Regularzed Slow Feature Analyss for Dynamc Texture Recognton Je Mao, Xangmn Xu, Member, IEEE, Xaofen Xng, and Dacheng Tao, Fellow, IEEE arxv:1706.03015v1 [cs.cv] 9 Jun 2017 Abstract Dynamc textures

More information