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

Size: px
Start display at page:

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

Transcription

1 MATEC Web of Conferences, 0500 (07) DTS-07 DO: 005/matecconf/ Fuson of Deep Features and Weghted VLAD Vectors based on Multple Features for mage Retreval Yanhong Wang,, Ygang Cen,, Lequan Lang,*, Lnna Zhang 4, Vacheslav Voronn 5, Vladmr Mladenovc 6 School of Computer and nformaton Technology, Bejng Jaotong Unversty, 0008, Bejng, Chna Key Laboratory of Advanced nformaton Scence and Network Technology of Bejng, 0008, Bejng, Chna nsttute of Electronc Commerce, Guangdong Unversty of Fnance & Economcs, 500, Guangzhou, Chna 4 College of Mechancal Engneerng, Guzhou Unversty, 55005, Guyang, Chna 5 Department of Rado-electronc systems, Don State Techncal Unversty, 46500, Rostov-on-Don, Russa 6 Faculty of Techncal Scences Unversty of Kragujevac, 000, Cacak, Serba Abstract n tradtonal vector of locally aggregated descrptors (VLAD) method, the fnal VLAD vector s reshaped by summng up the resduals between each descrptor and ts correspondng vsual word The norm of the resduals vares sgnfcantly, and t can make vsual burst Ths s caused by a fact that the contrbuton of each descrptor to VLAD vector s not the same To address ths problem, we add a dfferent weght to each resdual such that the contrbuton of each descrptor to the VLAD vector becomes even to a certan degree Also, tradtonal VLAD method only uses the local gradent features of mages Thus t has a low dscrmnaton n ths paper, local color features are extracted and used to the VLAD method Moreover, we fuse deep features and the multple VLAD vectors based on local gradent and color nformaton Also, n order to reduce runnng tme and mprove retreval accuracy, PCA and whtenng operatons are used for VLAD vectors Our proposed method s evaluated on three benchmark datasets, e, Holdays, Ukbench and Oxford5k Expermental results show that our proposed method acheves good performance ntroducton n ths paper we consder the task of large-scale mage retreval n the past few years, Bag-of-Vsual-Words (BOW) [] [] method has acheved great effect n mage retreval area Generally, n order to ensure retreval recall, a relatvely large vocabulary wll be requred Thus, t wll lead to a low effcency of retreval tme and hgh memory consumpton Recently, Jégou et al [] proposed vector of locally aggregated descrptors (VLAD) model, whch aggregates descrptors based on a localty crteron n feature space n fact, VLAD s a knd of representaton of Fsher vector wthout probablty ts mplementaton s very smlar to the BOW model Also, VLAD s very cheap n consumptons of tme and memory n tradtonal VLAD method, the fnal VLAD vector s reshaped by summng up the resduals between each descrptor and ts correspondng vsual word The norm of the resduals vares sgnfcantly, thus t can make vsual burst [4] To address ths problem, we add a weght to each resdual such that the contrbuton of each descrptor to the VLAD vector becomes even to a certan degree Orgnally, the SFT [5] descrptors are adopted n VLAD method, and has shown good performance As we all known, the descrptor [6] s faster than the SFT descrptor Moreover, the performance of and SFT s comparatve n most cases [7] verfed that the descrptor was not only more effcent but also leadng to hgher accuracy than SFT and rootsft descrptors However, both the SFT and descrptors represent only local gradent nformaton, whch mss mportant color nformaton n order to solve ths problem, many works combne the gradent and color nformaton For examples, n [7] C feature was proposed, whch are -based color nformaton; n [8], the author fused the CLOG [9] features and the features at the stage of smlarty measurement; n [0] the author proposed color- descrptors whch combned wth the approxmate color local kernel hstograms n ths paper, Color names () [] and features are used n VLAD method n recent years, deep features are popular for mage processng, such as mage classfcaton [], object detecton [] and speech recognton [4] etc n ths paper, we adopt the pre-traned networks to obtan the deep features of mages Also, n order to mprove retreval accuracy, multple VLAD vectors and mage representaton based on deep features are fused * Correspondng author: langlq@gdufeeducn The Authors, publshed by EDP Scences Ths s an open access artcle dstrbuted under the terms of the Creatve Commons Attrbuton Lcense 40 (

2 MATEC Web of Conferences, 0500 (07) DTS-07 DO: 005/matecconf/ Methodology Framework of our proposed method The framework of our proposed method s shown n Fg Vocabulary based on local features ( or ) are traned from an ndependent tranng dataset For an mage, and features are extracted and quantzed on correspondng vocabulary respectvely Here, we mprove the tradtonal VLAD method by addng a weght for each resdual, called as weghted VLAD The and features are adopted to weghted VLAD method, respectvely Then, weghted VLAD vectors based on the two features are obtaned Moreover, the deep features are extracted from the mage, and mage representaton based on deep features s computed Then the vectors are fused nto a vector to represent the mage Fnally, smlarty scores of the query mage and dataset mages are measured, and the retreval results are returned Fg The framework of our proposed retreval method Weghted VLAD For an mage, the generaton process of VLAD vector s as follows: () Detect nterest regons of the mage and extract local descrptors, denoted as d n x x, x, x n () The local descrptors are quantzed on the vocabulary C c, c, ck wth K vsual words ( L K), denoted as NN( x ) arg mn x c () The resduals of a vsual k k word and the descrptors that are quantzed to ths word are computed, formulated asvk x ck Then, : NN () k the resduals are summed A vector of length L K* d s obtaned, whch s called as the VLAD vector (4) Power-law normalzaton s adopted for the vector obtaned at the step () t contans two steps: frstly, there s the square root wth symbol, formula as V V sgn( V),0 ; secondly, the vector s normalzed by the L norm, denoted as V V / V Accordng to above step (), t may cause vsual burst phenomenon because contrbuton of each descrptor for the VLAD vector s not same, e, the closer from center of the cluster, the greater the contrbuton s, and vce versa n the smlarty measurement stage, ths resdual wll be reflected n the contrbuton snce the Eucldean dstance s used To address the problem, we add a dfferent weght for each resdual Here, the weght s set to be the normalzed dstance of the descrptor and ts nearest vsual word, denoted as Eq () and Eq (), e, the smaller (greater) s the dstance between the descrptor and ts nearest vsual word, the smaller (greater) s the weght The valdty s verfed n the expermental secton (Secton ) t should be noted that a same weght s added to the resduals correspondng to each vsual word n [4] But n our algorthm, dfferent weghts are added to the resduals respectvely Ths makes our algorthm become more flexble and adaptve for mage retreval () V x c k k : NN () k d( x, ck) x c : NN () k where s a weght coeffcent Also, d( x, c k) represents the dstance of the descrptor x and the vsual word c k - For a gven mage, descrptors are extracted, denoted as x x, x, x n For the based vocabulary C c, c, c K, SRUF accordng to Secton, a -based VLAD vector can be obtaned, denoted as V ts length s L K* d n addton, each descrptor s extracted from an mage patch of sze p p, denoted as x Specfcally, for each pxel of a patch, an -D descrptor s extracted Then, the average of all descrptors n the patch s regarded as the color descrptor of the patch Thus, a set of descrptors for the mage are obtaned, denoted x x, x, x n For the -based as k ()

3 MATEC Web of Conferences, 0500 (07) DTS-07 vocabulary C c, c,, c K, smlarly, the - based VLAD vector s computed, denoted asv Also, the length s L K* d n order to mprove retreval accuracy, deep features are extracted by usng pretraned deep convolutonal neural networks (N) models, and the length s L Feature fuson and smlarty measurement For an mage, the three mage representatons are fused to a vector, denoted as: V [ V V V ] N where are the weght parameters, and The best values fttng are selected by loop teraton Eucldean dstance s used to compute smlartes between the query mage and the dataset mages To reduce runnng tme, we adopt PCA and whtenng method whch suppressed the co-occurrence problem wth the dmensonalty reducton [5] Our proposed algorthm s summarzed as follows: Algorthm Fuson of deep features and weghted VLAD vectors based on multple features ) Off-lne Tran vocabulares C, C on the tranng dataset Extract the dense and descrptors from each mage of the dataset Compute weghted VLAD vectors V, V N and extract deep feature V for each mage n the dataset N Fuse V, V and V by Eq (), denoted asv Reduce dmensonalty of V, and the result s denoted asv R ) On-lne Extract the dense and descrptors from a query Compute weghted VLAD vectors V, V N and extract deep feature V for the query mage N Fuse V, V and V by Eq (), denoted asv Reduce dmensonalty ofv, and the result s denoted asv R Compute smlarty score Return mages of the dataset wth the hgh smlarty scores () Expermental results DO: 005/matecconf/ n ths secton we verfed our proposed method on three benchmark datasets, e, Holdays [6], Ukbench [7] and oxford5k [8] n addton, Pars60k [9] s used to tran vocabulares for Oxford5k Vocabulares are traned from Mrflckr5k [0] for other datasets All experments are mplemented on a computer wth 8GB memory and GHz CPU (ntel(r) Core(TM) ) Selecton of parameters n our experments, the dense descrptors are extracted for each mage Moreover, each descrptor s obtaned n an mage patch of sze 4 4 Also, the based and -based vocabulares of sze 64 are used Moreover, N features of mages are obtaned by the VGG-f model [] Here, a N-based representaton s obtaned from the second fully-connected layer of convolutonal networks for each mage, t s a 4096-D vector s a power of the absolute value of VLAD vectors matrx However, we fnd that the best value of s between 0 and 06 The accuraces wth dfferent by usng weghted VLAD based on dfferent features on three datasets are shown n Fg (a)holdays (b) UKbench (C) Oxford5k Fg The comparson wth dfferent values of by usng N-based vectors and VLAD vectors based on features and features n (a) and (c), the maps are

4 MATEC Web of Conferences, 0500 (07) DTS-07 DO: 005/matecconf/ shown on the Holdays and Oxford5k dataset n (b), the N-S scores on the Ukbench dataset are shown Here, weghted VLAD vectors based on and features are denoted as,, respectvely On Holdays, we select =09 for =05 for, and =0 for N-based vectors On UKbench datasets s set to be 09, 05, 05 for, and N-based vectors, respectvely Moreover, s set to be 0, 05, 0 on Oxford5k, respectvely n Eq () are the weght parameters of -based and -based VLAD vectors and Nbased vectors for feature fuson On Holdays they are respectvely set to be 0, 0, 04 Also, they are set to be 0, 05, 045 and 06, 005, 05 on the UKbench and Oxford5k Effectveness of weghted VLAD n ths subsecton, we verfed the effectveness of proposed weghted VLAD model n Fg, two examples on UKbench dataset are shown t can be seen that the results of are better than tradtonal VLAD- n addton, we compare our weghted VLAD wth [4] (VLAD-LCR-RN) n Table On Holdays, t can be seen that the results are the same, but the length of our vector s only about a half of VLAD-LCR-RN On Oxford5k when vectors are reduced to 8D, acheves a better result Fg Two examples by usng the VLAD vectors based on features on the UKbench dataset The left mages are queres, and the frst row represents the results obtaned by the tradtonal VLAD based on descrptors, where those wth green boxes are the correct results Also, the second row s the results obtaned by usng our proposed weghted VLAD based on the Table Comparson between VLAD-LCR-RN and weghted VLAD- Methods VLAD-LCR-RN[4] Holdays 0658/ /4096 Oxford5k 057/ /4096 Oxford5k 0/ /8 Fuson of multple features n experments, and are fused, denoted as + The multple weghted VLAD vectors and deep features are fused nto a vector, denoted as ++N n Table, the retreval accuraces on dfferent datasets are lsted, where L 8 denotes the length of VLAD vectors obtaned by PCA and whtenng operatons When L 8, on Holdays, t can be seen that the map obtaned by + ncreased by nearly % compared to and respectvely Also, the map acheves 0806 for + +N Also, On UKbench and Oxford5k, the N-S score and the maps reach respectvely 696 and 04 for ++N Thus, feature fuson make retreval accuraces obvously mproved Table Comparson of results obtaned by usng dfferent features and by reducton on Holdays, Oxford5k and UKbench datasets Methods N[] + + +N L Holdays Ukbench (N-S score) Oxford 5k Table Comparson between varous methods and our proposed method Methods VLAD-C [6] Trangulaton embeddng [] + L Holdays Oxford 5k Ukbench (N-S score) Deep fully conneted+vlad [] OUR OUR

5 MATEC Web of Conferences, 0500 (07) DTS-07 DO: 005/matecconf/ We compare our method wth varous methods n Table Specally, n reference [], the authors consttuted hand-crafted features lke SFT whch s called trangular embeddng t can be seen that the map of + s hgher than the maps of other methods on Holdays We fuse VLAD vectors and deep features n reference [], they proposed the mult-scale orderless poolng (MOP-N) scheme whch combned the deep features and VLAD The results compared wth [] are lsted n Table t can be seen that our method acheves the better results on three datasets 4 Concluson Snce the contrbuton of each descrptor to the VLAD vector s not the same n tradtonal VLAD method, t wll result n vsual burst phenomenon To address the problem, we added a dfferent weght for every resdual to balance the contrbuton of each descrptor for the VLAD vector The features descrbe local gradent nformaton of an mage, whle the features represent local color nformaton Thus, to mprove the mage retreval accuracy, we proposed a smple and effectve method that fused our proposed weghted VLAD vectors based on local texture features and local color features Moreover, n order to mprove the accuracy further, deep features are extracted and fused wth the multple weghted VLAD vectors n order to reduce runnng tme, the PCA and whtenng operatons were adopted n ths paper Fnally, our experments obtan the better results when compared wth other methods Ths work was supported by Natonal Natural Scence Foundaton of Chna (657067); nternatonal (Regonal) Project Cooperaton and Exchanges of Natonal Nature Scence Foundaton of Chna (665070); Bejng Muncpal Natural Scence Foundaton (46050); The Natural Scence Foundaton of Guangdong Provnce (06A00708) and the Fundamental Research Funds for the Central Unverstes (07JBZ08) References J Svc, A Zsserman, Proceedngs Nnth EEE nternatonal Conference on Computer Vson,, (00) J Phlbn, M sard, EEE Conference on Computer Vson and Pattern Recognton, CVPR, -8 (007) H Jégou, M Douze, C Schmd, EEE n Proc CVPR, 04-(00) 4 J Delhumeau, P H Gosseln, ACM nternatonal Conference on Multmeda, (0) 5 D Lowe, nternatonal Journal of Computer Vson, JCV, no, 9-0 (004) 6 H Bay, A Ess, T Tuytelaars, LV Gool, Computer vson and mage understandng, no, (008) 7 E Spyromtros-Xoufs, S Papadopoulos, Y Kompatsars, EEE Transactons on Multmeda, no6, 7-78(04) 8 S Chen, Y Y Dng, H L, J Wang, X Deng, EEE nternatonal Conference on System, Man, and Cybernetcs, 9-96(04) 9 D A R Vgo, F S Khan, J V D Wejer, 0th nternatonal Conference on Pattern Recognton, (00) 0 P Fan, A Men, M Chen, EEE nternatonal Conference on Network nfrastructure and Dgtal Content, 76-70(009) J V D Wejer, C Schmd, J Verbeek, EEE Transactons on mage Processng a Publcaton of the EEE Sgnal Processng Socety, no7, 5- (009) A Krzhevsky, Sutskever, G E Hnton, Advances n Neural nformaton Processng Systems, 5, (0) M D Zeler, R Fergus, n Proc ECCV, 8689, 88-8(04) 4 AS Razavan, H Azzpour, J Sullvan, S Carlsson, n Proc CVPR Workshops, (04) 5 H Jégou, O Chum, n Proc ECCV, (0) 6 H Jégou, M Douze, C Schmd, n Proc ECCV, 04-7 (008) 7 D Nster, H Stewenus, n Proc CVPR'06, 6-68 (006) 8 J Phlbn, O Chum, M sard, n Proc CVPR (007) 9 J Phlbn, O Chum, M sard, J Svc, A Zsserman, n Proc CVPR(008) 0 MJ Huskes, MS Lew Proceedng MR '08 Proceedngs of the st ACM nternatonal conference on Multmeda nformaton retreval, 9-4 (008) K Chatfeld, K Smonyan, A Vedald, A Zsserman, n proc BMVC(04) H Jégou and A Zsserman, n Proc CVPR, 0 7 (04) Y Gong, L Wang, R Guo, and S, Lazebnk n Proc ECCV, 9 407(04) 5

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

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

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

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

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 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

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

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

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

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

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

Shape-adaptive DCT and Its Application in Region-based Image Coding

Shape-adaptive DCT and Its Application in Region-based Image Coding Internatonal Journal of Sgnal Processng, Image Processng and Pattern Recognton, pp.99-108 http://dx.do.org/10.14257/sp.2014.7.1.10 Shape-adaptve DCT and Its Applcaton n Regon-based Image Codng Yamn Zheng,

More information

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1 A New Feature of Unformty of Image Texture Drectons Concdng wth the Human Eyes Percepton Xng-Jan He, De-Shuang Huang, Yue Zhang, Tat-Mng Lo 2, and Mchael R. Lyu 3 Intellgent Computng Lab, Insttute of Intellgent

More information

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images Internatonal Journal of Informaton and Electroncs Engneerng Vol. 5 No. 6 November 015 Usng Fuzzy Logc to Enhance the Large Sze Remote Sensng Images Trung Nguyen Tu Huy Ngo Hoang and Thoa Vu Van Abstract

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

ALEXNET FEATURE EXTRACTION AND MULTI-KERNEL LEARNING FOR OBJECT- ORIENTED CLASSIFICATION

ALEXNET FEATURE EXTRACTION AND MULTI-KERNEL LEARNING FOR OBJECT- ORIENTED CLASSIFICATION ALEXNET FEATURE EXTRACTION AND MULTI-KERNEL LEARNING FOR OBJECT- ORIENTED CLASSIFICATION Lng Dng 1, Hongy L 2, *, Changmao Hu 2, We Zhang 2, Shumn Wang 1 1 Insttute of Earthquake Forecastng, Chna Earthquake

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

The Shortest Path of Touring Lines given in the Plane

The Shortest Path of Touring Lines given in the Plane Send Orders for Reprnts to reprnts@benthamscence.ae 262 The Open Cybernetcs & Systemcs Journal, 2015, 9, 262-267 The Shortest Path of Tourng Lnes gven n the Plane Open Access Ljuan Wang 1,2, Dandan He

More information

A Novel Adaptive Descriptor Algorithm for Ternary Pattern Textures

A Novel Adaptive Descriptor Algorithm for Ternary Pattern Textures A Novel Adaptve Descrptor Algorthm for Ternary Pattern Textures Fahuan Hu 1,2, Guopng Lu 1 *, Zengwen Dong 1 1.School of Mechancal & Electrcal Engneerng, Nanchang Unversty, Nanchang, 330031, Chna; 2. School

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

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

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

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

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

Maximum Variance Combined with Adaptive Genetic Algorithm for Infrared Image Segmentation

Maximum Variance Combined with Adaptive Genetic Algorithm for Infrared Image Segmentation Internatonal Conference on Logstcs Engneerng, Management and Computer Scence (LEMCS 5) Maxmum Varance Combned wth Adaptve Genetc Algorthm for Infrared Image Segmentaton Huxuan Fu College of Automaton Harbn

More information

Fast Computation of Shortest Path for Visiting Segments in the Plane

Fast Computation of Shortest Path for Visiting Segments in the Plane Send Orders for Reprnts to reprnts@benthamscence.ae 4 The Open Cybernetcs & Systemcs Journal, 04, 8, 4-9 Open Access Fast Computaton of Shortest Path for Vstng Segments n the Plane Ljuan Wang,, Bo Jang

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

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

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

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

Learning a Class-Specific Dictionary for Facial Expression Recognition

Learning a Class-Specific Dictionary for Facial Expression Recognition BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 16, No 4 Sofa 016 Prnt ISSN: 1311-970; Onlne ISSN: 1314-4081 DOI: 10.1515/cat-016-0067 Learnng a Class-Specfc Dctonary for

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

Image Matching Algorithm based on Feature-point and DAISY Descriptor

Image Matching Algorithm based on Feature-point and DAISY Descriptor JOURNAL OF MULTIMEDIA, VOL. 9, NO. 6, JUNE 2014 829 Image Matchng Algorthm based on Feature-pont and DAISY Descrptor L L School of Busness, Schuan Agrcultural Unversty, Schuan Dujanyan 611830, Chna Abstract

More information

A high precision collaborative vision measurement of gear chamfering profile

A high precision collaborative vision measurement of gear chamfering profile Internatonal Conference on Advances n Mechancal Engneerng and Industral Informatcs (AMEII 05) A hgh precson collaboratve vson measurement of gear chamferng profle Conglng Zhou, a, Zengpu Xu, b, Chunmng

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

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

CS 534: Computer Vision Model Fitting

CS 534: Computer Vision Model Fitting CS 534: Computer Vson Model Fttng Sprng 004 Ahmed Elgammal Dept of Computer Scence CS 534 Model Fttng - 1 Outlnes Model fttng s mportant Least-squares fttng Maxmum lkelhood estmaton MAP estmaton Robust

More information

Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch

Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch Deep learnng s a good steganalyss tool when embeddng key s reused for dfferent mages, even f there s a cover source-msmatch Lonel PIBRE 2,3, Jérôme PASQUET 2,3, Dno IENCO 2,3, Marc CHAUMONT 1,2,3 (1) Unversty

More information

A CALCULATION METHOD OF DEEP WEB ENTITIES RECOGNITION

A CALCULATION METHOD OF DEEP WEB ENTITIES RECOGNITION A CALCULATION METHOD OF DEEP WEB ENTITIES RECOGNITION 1 FENG YONG, DANG XIAO-WAN, 3 XU HONG-YAN School of Informaton, Laonng Unversty, Shenyang Laonng E-mal: 1 fyxuhy@163.com, dangxaowan@163.com, 3 xuhongyan_lndx@163.com

More information

College of Information & Computer, Anhui Agricultural University, Hefei, Anhui, , China

College of Information & Computer, Anhui Agricultural University, Hefei, Anhui, , China 4th Internatonal Conference on Mechatroncs Materals Chemstry and Computer Engneerng (ICMMCCE 15) Improved retnex mage enhancement algorthm based on blateral flterng Ya nan Yang 1 a Zhaohu Jang 1 b * Chunhe

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

Novel Pattern-based Fingerprint Recognition Technique Using 2D Wavelet Decomposition

Novel Pattern-based Fingerprint Recognition Technique Using 2D Wavelet Decomposition Mathematcal Methods for Informaton Scence and Economcs Novel Pattern-based Fngerprnt Recognton Technque Usng D Wavelet Decomposton TUDOR BARBU Insttute of Computer Scence of the Romanan Academy T. Codrescu,,

More information

A new segmentation algorithm for medical volume image based on K-means clustering

A new segmentation algorithm for medical volume image based on K-means clustering Avalable onlne www.jocpr.com Journal of Chemcal and harmaceutcal Research, 2013, 5(12):113-117 Research Artcle ISSN : 0975-7384 CODEN(USA) : JCRC5 A new segmentaton algorthm for medcal volume mage based

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

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

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

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

Modular PCA Face Recognition Based on Weighted Average

Modular PCA Face Recognition Based on Weighted Average odern Appled Scence odular PCA Face Recognton Based on Weghted Average Chengmao Han (Correspondng author) Department of athematcs, Lny Normal Unversty Lny 76005, Chna E-mal: hanchengmao@163.com Abstract

More information

Enhanced AMBTC for Image Compression using Block Classification and Interpolation

Enhanced AMBTC for Image Compression using Block Classification and Interpolation Internatonal Journal of Computer Applcatons (0975 8887) Volume 5 No.0, August 0 Enhanced AMBTC for Image Compresson usng Block Classfcaton and Interpolaton S. Vmala Dept. of Comp. Scence Mother Teresa

More information

A Simple Methodology for Database Clustering. Hao Tang 12 Guangdong University of Technology, Guangdong, , China

A Simple Methodology for Database Clustering. Hao Tang 12 Guangdong University of Technology, Guangdong, , China for Database Clusterng Guangdong Unversty of Technology, Guangdong, 0503, Chna E-mal: 6085@qq.com Me Zhang Guangdong Unversty of Technology, Guangdong, 0503, Chna E-mal:64605455@qq.com Database clusterng

More information

Kernel Collaborative Representation Classification Based on Adaptive Dictionary Learning

Kernel Collaborative Representation Classification Based on Adaptive Dictionary Learning Internatonal Journal of Intellgent Informaton Systems 2018; 7(2): 15-22 http://www.scencepublshnggroup.com/j/js do: 10.11648/j.js.20180702.11 ISSN: 2328-7675 (Prnt); ISSN: 2328-7683 (Onlne) Kernel Collaboratve

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

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

SIFT Match Verification by Geometric Coding for Large-Scale Partial-Duplicate Web Image Search

SIFT Match Verification by Geometric Coding for Large-Scale Partial-Duplicate Web Image Search SIFT Match Verfcaton by Geometrc Codng for Large-Scale Partal-Duplcate Web Image Search WENGANG ZHOU and HOUQIANG LI, Unversty of Scence and Technology of Chna YIJUAN LU, Texas State Unversty QI TIAN,

More information

Person re-identification with content and context re-ranking

Person re-identification with content and context re-ranking DOI.7/s42-4-949-7 Person re-dentfcaton wth content and context re-rankng Qngmng Leng Rumn Hu Chao Lang Ymn Wang Jun Chen Sprnger Scence+Busness Meda New York 24 Abstract Ths paper proposes a novel and

More information

Analysis on the Workspace of Six-degrees-of-freedom Industrial Robot Based on AutoCAD

Analysis on the Workspace of Six-degrees-of-freedom Industrial Robot Based on AutoCAD Analyss on the Workspace of Sx-degrees-of-freedom Industral Robot Based on AutoCAD Jn-quan L 1, Ru Zhang 1,a, Fang Cu 1, Q Guan 1 and Yang Zhang 1 1 School of Automaton, Bejng Unversty of Posts and Telecommuncatons,

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

Robust Shot Boundary Detection from Video Using Dynamic Texture

Robust Shot Boundary Detection from Video Using Dynamic Texture Sensors & Transducers 204 by IFSA Publshng, S. L. http://www.sensorsportal.com Robust Shot Boundary Detecton from Vdeo Usng Dynamc Teture, 3 Peng Tale, 2 Zhang Wenjun School of Communcaton & Informaton

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

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

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

BioTechnology. An Indian Journal FULL PAPER. Trade Science Inc.

BioTechnology. An Indian Journal FULL PAPER. Trade Science Inc. [Type text] [Type text] [Type text] ISSN : 0974-74 Volume 0 Issue BoTechnology 04 An Indan Journal FULL PAPER BTAIJ 0() 04 [684-689] Revew on Chna s sports ndustry fnancng market based on market -orented

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 Image Compression Algorithm based on Wavelet Transform and LZW

An Image Compression Algorithm based on Wavelet Transform and LZW An Image Compresson Algorthm based on Wavelet Transform and LZW Png Luo a, Janyong Yu b School of Chongqng Unversty of Posts and Telecommuncatons, Chongqng, 400065, Chna Abstract a cylpng@63.com, b y27769864@sna.cn

More information

Hybrid Non-Blind Color Image Watermarking

Hybrid Non-Blind Color Image Watermarking Hybrd Non-Blnd Color Image Watermarkng Ms C.N.Sujatha 1, Dr. P. Satyanarayana 2 1 Assocate Professor, Dept. of ECE, SNIST, Yamnampet, Ghatkesar Hyderabad-501301, Telangana 2 Professor, Dept. of ECE, AITS,

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

A Clustering Algorithm for Key Frame Extraction Based on Density Peak

A Clustering Algorithm for Key Frame Extraction Based on Density Peak Journal of Computer and Communcatons, 2018, 6, 118-128 http://www.scrp.org/ournal/cc ISSN Onlne: 2327-5227 ISSN Prnt: 2327-5219 A Clusterng Algorthm for Key Frame Extracton Based on Densty Peak Hong Zhao

More information

Clustering Algorithm Combining CPSO with K-Means Chunqin Gu 1, a, Qian Tao 2, b

Clustering Algorithm Combining CPSO with K-Means Chunqin Gu 1, a, Qian Tao 2, b Internatonal Conference on Advances n Mechancal Engneerng and Industral Informatcs (AMEII 05) Clusterng Algorthm Combnng CPSO wth K-Means Chunqn Gu, a, Qan Tao, b Department of Informaton Scence, Zhongka

More information

Grading Image Retrieval Based on DCT and DWT Compressed Domains Using Low-Level Features

Grading Image Retrieval Based on DCT and DWT Compressed Domains Using Low-Level Features Journal of Communcatons Vol. 0 No. January 0 Gradng Image Retreval Based on DCT and DWT Compressed Domans Usng Low-Level Features Chengyou Wang Xnyue Zhang Rongyang Shan and Xao Zhou School of echancal

More information

Robust Mean Shift Tracking with Corrected Background-Weighted Histogram

Robust Mean Shift Tracking with Corrected Background-Weighted Histogram Robust Mean Shft Trackng wth Corrected Background-Weghted Hstogram Jfeng Nng, Le Zhang, Davd Zhang and Chengke Wu Abstract: The background-weghted hstogram (BWH) algorthm proposed n [] attempts to reduce

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

Feature-Area Optimization: A Novel SAR Image Registration Method

Feature-Area Optimization: A Novel SAR Image Registration Method Feature-Area Optmzaton: A Novel SAR Image Regstraton Method Fuqang Lu, Fukun B, Lang Chen, Hao Sh and We Lu Abstract Ths letter proposes a synthetc aperture radar (SAR) mage regstraton method named Feature-Area

More information

Learning-Based Top-N Selection Query Evaluation over Relational Databases

Learning-Based Top-N Selection Query Evaluation over Relational Databases Learnng-Based Top-N Selecton Query Evaluaton over Relatonal Databases Lang Zhu *, Wey Meng ** * School of Mathematcs and Computer Scence, Hebe Unversty, Baodng, Hebe 071002, Chna, zhu@mal.hbu.edu.cn **

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

Robust visual tracking based on Informative random fern

Robust visual tracking based on Informative random fern 5th Internatonal Conference on Computer Scences and Automaton Engneerng (ICCSAE 205) Robust vsual trackng based on Informatve random fern Hao Dong, a, Ru Wang, b School of Instrumentaton Scence and Opto-electroncs

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

Computer Aided Drafting, Design and Manufacturing Volume 25, Number 2, June 2015, Page 14

Computer Aided Drafting, Design and Manufacturing Volume 25, Number 2, June 2015, Page 14 Computer Aded Draftng, Desgn and Manufacturng Volume 5, Number, June 015, Page 14 CADDM Face Recognton Algorthm Fusng Monogenc Bnary Codng and Collaboratve Representaton FU Yu-xan, PENG Lang-yu College

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

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

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

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

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

Image Emotional Semantic Retrieval Based on ELM

Image Emotional Semantic Retrieval Based on ELM Internatonal Conference on Logstcs Engneerng, Management and Computer Scence (LEMCS 2014) Image Emotonal Semantc Retreval Based on ELM Pele Zhang, Mn Yao, Shenzhang La College of computer scence & Technology

More information

Palmprint Recognition Using Directional Representation and Compresses Sensing

Palmprint Recognition Using Directional Representation and Compresses Sensing Research Journal of Appled Scences, Engneerng and echnology 4(22): 4724-4728, 2012 ISSN: 2040-7467 Maxwell Scentfc Organzaton, 2012 Submtted: March 31, 2012 Accepted: Aprl 30, 2012 Publshed: November 15,

More information

An Approach for Crowd Density and Crowd Size Estimation

An Approach for Crowd Density and Crowd Size Estimation JOURNAL OF SOFTWARE, VOL. 9, NO. 3, MARCH 2014 757 An Approach for Crowd Densty and Crowd Sze Estmaton Mng Jang 1,2, Jngcheng Huang 1,2, Xngq Wang 1,2, Jngfan Tang 1,2, Chunmng Wu 3 (1. Insttute of Software

More information

Research on Categorization of Animation Effect Based on Data Mining

Research on Categorization of Animation Effect Based on Data Mining MATEC Web of Conferences 22, 0102 0 ( 2015) DOI: 10.1051/ matecconf/ 2015220102 0 C Owned by the authors, publshed by EDP Scences, 2015 Research on Categorzaton of Anmaton Effect Based on Data Mnng Na

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

Performance Assessment and Fault Diagnosis for Hydraulic Pump Based on WPT and SOM

Performance Assessment and Fault Diagnosis for Hydraulic Pump Based on WPT and SOM Performance Assessment and Fault Dagnoss for Hydraulc Pump Based on WPT and SOM Be Jkun, Lu Chen and Wang Zl PERFORMANCE ASSESSMENT AND FAULT DIAGNOSIS FOR HYDRAULIC PUMP BASED ON WPT AND SOM. Be Jkun,

More information

Integrated Expression-Invariant Face Recognition with Constrained Optical Flow

Integrated Expression-Invariant Face Recognition with Constrained Optical Flow Integrated Expresson-Invarant Face Recognton wth Constraned Optcal Flow Chao-Kue Hseh, Shang-Hong La 2, and Yung-Chang Chen Department of Electrcal Engneerng, Natonal Tsng Hua Unversty, Tawan 2 Department

More information

Joint Example-based Depth Map Super-Resolution

Joint Example-based Depth Map Super-Resolution Jont Example-based Depth Map Super-Resoluton Yanje L 1, Tanfan Xue,3, Lfeng Sun 1, Janzhuang Lu,3,4 1 Informaton Scence and Technology Department, Tsnghua Unversty, Bejng, Chna Department of Informaton

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

Research of Image Recognition Algorithm Based on Depth Learning

Research of Image Recognition Algorithm Based on Depth Learning 208 4th World Conference on Control, Electroncs and Computer Engneerng (WCCECE 208) Research of Image Recognton Algorthm Based on Depth Learnng Zhang Jan, J Xnhao Zhejang Busness College, Hangzhou, Chna,

More information

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization Problem efntons and Evaluaton Crtera for Computatonal Expensve Optmzaton B. Lu 1, Q. Chen and Q. Zhang 3, J. J. Lang 4, P. N. Suganthan, B. Y. Qu 6 1 epartment of Computng, Glyndwr Unversty, UK Faclty

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

(a) Input data X n. (b) VersNet. (c) Output data Y n. (d) Supervsed data D n. Fg. 2 Illustraton of tranng for proposed CNN. 2. Related Work In segment

(a) Input data X n. (b) VersNet. (c) Output data Y n. (d) Supervsed data D n. Fg. 2 Illustraton of tranng for proposed CNN. 2. Related Work In segment 一般社団法人電子情報通信学会 THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS 信学技報 IEICE Techncal Report SANE2017-92 (2018-01) Deep Learnng for End-to-End Automatc Target Recognton from Synthetc

More information

Classifying Acoustic Transient Signals Using Artificial Intelligence

Classifying Acoustic Transient Signals Using Artificial Intelligence Classfyng Acoustc Transent Sgnals Usng Artfcal Intellgence Steve Sutton, Unversty of North Carolna At Wlmngton (suttons@charter.net) Greg Huff, Unversty of North Carolna At Wlmngton (jgh7476@uncwl.edu)

More information

Smoothing Spline ANOVA for variable screening

Smoothing Spline ANOVA for variable screening Smoothng Splne ANOVA for varable screenng a useful tool for metamodels tranng and mult-objectve optmzaton L. Rcco, E. Rgon, A. Turco Outlne RSM Introducton Possble couplng Test case MOO MOO wth Game Theory

More information

CO-SPARSITY REGULARIZED DEEP HASHING FOR IMAGE INSTANCE RETRIEVAL I2R 1, UPMC 2

CO-SPARSITY REGULARIZED DEEP HASHING FOR IMAGE INSTANCE RETRIEVAL I2R 1, UPMC 2 CO-SPARSITY REGULARIZED DEEP HASHING FOR IMAGE INSTANCE RETRIEVAL Je Ln,1, Olver Morère,1,2, Vjay Chandrasekhar,1, Antone Vellard,2, Hanln Goh 1 I2R 1, UPMC 2 ABSTRACT In ths work, we tackle the problem

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

Straight Line Detection Based on Particle Swarm Optimization

Straight Line Detection Based on Particle Swarm Optimization Sensors & ransducers 013 b IFSA http://www.sensorsportal.com Straght Lne Detecton Based on Partcle Swarm Optmzaton Shengzhou XU, Jun IE College of computer scence, South-Central Unverst for Natonaltes,

More information