Duplicate Near Duplicate Intact Partial Copy Original Image Near Partial Copy Near Partial Copy with a background (a) (b) 2 1 [6] SIFT SIFT SIF

Similar documents
(MIRU2008) HOG Histograms of Oriented Gradients (HOG)

本文6(599) (Page 601)

3: 2: 2. 2 Semi-supervised learning Semi-supervised learning [5,6] Semi-supervised learning Self-training [13] [14] Self-training Self-training Semi-s


THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE. TRECVID2012 Instance Search {sak

IPSJ SIG Technical Report Vol.2010-CVIM-170 No /1/ Visual Recognition of Wire Harnesses for Automated Wiring Masaki Yoneda, 1 Ta

IPSJ SIG Technical Report Vol.2009-CVIM-167 No /6/10 Real AdaBoost HOG 1 1 1, 2 1 Real AdaBoost HOG HOG Real AdaBoost HOG A Method for Reducing

IPSJ SIG Technical Report Vol.2012-CG-149 No.13 Vol.2012-CVIM-184 No /12/4 3 1,a) ( ) DB 3D DB 2D,,,, PnP(Perspective n-point), Ransa

Convolutional Neural Network A Graduation Thesis of College of Engineering, Chubu University Investigation of feature extraction by Convolution

BDH Cao BDH BDH Cao Cao Cao BDH ()*$ +,-+.)*$!%&'$!"#$ 2. 1 Weng [4] Metric Learning Weng DB DB Yang [5] John [6] Sparse Coding sparse coding DB [7] K

IPSJ SIG Technical Report 1,a) 1,b) 1,c) 1,d) 2,e) 2,f) 2,g) 1. [1] [2] 2 [3] Osaka Prefecture University 1 1, Gakuencho, Naka, Sakai,

情報処理学会研究報告 IPSJ SIG Technical Report Vol.2013-CVIM-186 No /3/15 EMD 1,a) SIFT. SIFT Bag-of-keypoints. SIFT SIFT.. Earth Mover s Distance

4. C i k = 2 k-means C 1 i, C 2 i 5. C i x i p [ f(θ i ; x) = (2π) p 2 Vi 1 2 exp (x µ ] i) t V 1 i (x µ i ) 2 BIC BIC = 2 log L( ˆθ i ; x i C i ) + q

Microsoft PowerPoint - SSII_harada pptx

IPSJ SIG Technical Report Vol.2014-DBS-159 No.6 Vol.2014-IFAT-115 No /8/1 1,a) 1 1 1,, 1. ([1]) ([2], [3]) A B 1 ([4]) 1 Graduate School of Info

(MIRU2009) cuboid cuboid SURF 6 85% Web. Web Abstract Extracting Spatio-te

IPSJ SIG Technical Report iphone iphone,,., OpenGl ES 2.0 GLSL(OpenGL Shading Language), iphone GPGPU(General-Purpose Computing on Graphics Proc

yoo_graduation_thesis.dvi

Microsoft Word - toyoshima-deim2011.doc

(MIRU2010) Geometric Context Randomized Trees Geometric Context Rand

paper.dvi

,,.,.,,.,.,.,.,,.,..,,,, i

IS1-09 第 回画像センシングシンポジウム, 横浜,14 年 6 月 2 Hough Forest Hough Forest[6] Random Forest( [5]) Random Forest Hough Forest Hough Forest 2.1 Hough Forest 1 2.2

HOG HOG LBP LBP 4) LBP LBP Wang LBP HOG LBP 5) LBP LBP 1 r n 1 n, 1

2.2 6).,.,.,. Yang, 7).,,.,,. 2.3 SIFT SIFT (Scale-Invariant Feature Transform) 8).,. SIFT,,. SIFT, Mean-Shift 9)., SIFT,., SIFT,. 3.,.,,,,,.,,,., 1,

IPSJ SIG Technical Report Vol.2010-MPS-77 No /3/5 VR SIFT Virtual View Generation in Hallway of Cybercity Buildings from Video Sequen


bag-of-words bag-of-keypoints Web bagof-keypoints Nearest Neighbor SVM Nearest Neighbor SIFT Nearest Neighbor bag-of-keypoints Nearest Neighbor SVM 84

258 5) GPS 1 GPS 6) GPS DP 7) 8) 10) GPS GPS ) GPS Global Positioning System

一般社団法人電子情報通信学会 THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGIN

A Graduation Thesis of College of Engineering, Chubu University Pose Estimation by Regression Analysis with Depth Information Yoshiki Agata

RANSAC RANSAC Amerini [8] RANSAC LO-RANSAC(Locally Optimized RANSAC)[9] LO-RANSAC 2.2 SIFT SIFT SIFT 128 SIFT SIFT SIFT SIFT p i p j d ij SIF

第25回信号処理シンポジウム 2010年11月24日 26日(奈良) 高精度な画像マッチング手法の検討 A Study of a High-Accuracy Image Matching Method 伊藤 康一 東北大学 高橋 徹 青木 孝文 大学院情報科学研究科 Koichi ITO Toru

2014/3 Vol. J97 D No. 3 Recognition-based segmentation [7] 1 DP 1 Conditional random field; CRF [8] [10] CRF / OCR OCR [11], [1

3 2 2 (1) (2) (3) (4) 4 4 AdaBoost 2. [11] Onishi&Yoda [8] Iwashita&Stoica [5] 4 [3] 3. 3 (1) (2) (3)

& Vol.5 No (Oct. 2015) TV 1,2,a) , Augmented TV TV AR Augmented Reality 3DCG TV Estimation of TV Screen Position and Ro

Sobel Canny i

[2] 2. [3 5] 3D [6 8] Morishima [9] N n 24 24FPS k k = 1, 2,..., N i i = 1, 2,..., n Algorithm 1 N io user-specified number of inbetween omis

28 TCG SURF Card recognition using SURF in TCG play video

IPSJ SIG Technical Report Vol.2013-CVIM-187 No /5/30 1,a) 1,b), 1,,,,,,, (DNN),,,, 2 (CNN),, 1.,,,,,,,,,,,,,,,,,, [1], [6], [7], [12], [13]., [

SICE東北支部研究集会資料（2017年）

[1] SBS [2] SBS Random Forests[3] Random Forests ii

LBP 2 LBP 2. 2 Local Binary Pattern Local Binary pattern(lbp) [6] R

1., 1 COOKPAD 2, Web.,,,,,,.,, [1]., 5.,, [2].,,.,.,, 5, [3].,,,.,, [4], 33,.,,.,,.. 2.,, 3.., 4., 5., ,. 1.,,., 2.,. 1,,

28 Horizontal angle correction using straight line detection in an equirectangular image

光学

1 Fig. 1 Extraction of motion,.,,, 4,,, 3., 1, 2. 2.,. CHLAC,. 2.1,. (256 ).,., CHLAC. CHLAC, HLAC. 2.3 (HLAC ) r,.,. HLAC. N. 2 HLAC Fig. 2

5D1 SY0004/14/ SICE 1, 2 Dynamically Consistent Motion Design of Humanoid Robots even at the Limit of Kinematics Kenya TANAKA 1 and Tomo

DBSJ Journal論文のスタイルファイル（MS Word版）-16ポイント

(a) 1 (b) 3. Gilbert Pernicka[2] Treibitz Schechner[3] Narasimhan [4] Kim [5] Nayar [6] [7][8][9] 2. X X X [10] [11] L L t L s L = L t + L s

IPSJ SIG Technical Report Vol.2012-CVIM-182 No /5/23 1,a) 2,b) 3,c) , Structure from Motion,, Visual localization in libraries using i

THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE.

35_3_9.dvi

IPSJ SIG Technical Report Vol.2010-CVIM-171 No /3/19 1. Web 1 1 Web Web Web Multiple Kernel Learning(MKL) Web ( ) % MKL 68.8% Extractin

2 Fig D human model. 1 Fig. 1 The flow of proposed method )9)10) 2.2 3)4)7) 5)11)12)13)14) TOF 1 3 TOF 3 2 c 2011 Information

[2] OCR [3], [4] [5] [6] [4], [7] [8], [9] 1 [10] Fig. 1 Current arrangement and size of ruby. 2 Fig. 2 Typography combined with printing

Spin Image [3] 3D Shape Context [4] Spin Image 2 3D Shape Context Shape Index[5] Local Surface Patch[6] DAI [7], [8] [9], [10] Reference Frame SHO[11]

Vol.8 No (Mar. 2015) 1,a) , Anomaly Detection Based on Density Estimation of Normal Data in Cone-restr

SICE東北支部研究集会資料(2013年)

Input image Initialize variables Loop for period of oscillation Update height map Make shade image Change property of image Output image Change time L

2. 30 Visual Words TF-IDF Lowe [4] Scale-Invarient Feature Transform (SIFT) Bay [1] Speeded Up Robust Features (SURF) SIFT 128 SURF 64 Visual Words Ni

IPSJ SIG Technical Report Vol.2011-CVIM-177 No /5/ TRECVID2010 SURF Bag-of-Features 1 TRECVID SVM 700% MKL-SVM 883% TRECVID2010 MKL-SVM A

知能と情報, Vol.30, No.5, pp

1 (PCA) 3 2 P.Viola 2) Viola AdaBoost 1 Viola OpenCV 3) Web OpenCV T.L.Berg PCA kpca LDA k-means 4) Berg 95% Berg Web k-means k-means

2007/8 Vol. J90 D No. 8 Stauffer [7] 2 2 I 1 I 2 2 (I 1(x),I 2(x)) 2 [13] I 2 = CI 1 (C >0) (I 1,I 2) (I 1,I 2) Field Monitoring Server

(MIRU2005) ( ) Radim Šára Globally Optimal Range Image Registration by G

(VKIR) VKIR VKIR DCT (R) (G) (B) Ward DCT i

Vol.55 No (Jan. 2014) saccess 6 saccess 7 saccess 2. [3] p.33 * B (A) (B) (C) (D) (E) (F) *1 [3], [4] Web PDF a m

untitled

kut-paper-template.dvi

,,,,,,,,,,,,,,,,,,, 976%, i

IPSJ SIG Technical Report GPS LAN GPS LAN GPS LAN Location Identification by sphere image and hybrid sensing Takayuki Katahira, 1 Yoshio Iwai 1

(3.6 ) (4.6 ) 2. [3], [6], [12] [7] [2], [5], [11] [14] [9] [8] [10] (1) Voodoo 3 : 3 Voodoo[1] 3 ( 3D ) (2) : Voodoo 3D (3) : 3D (Welc

Silhouette on Image Object Silhouette on Images Object 1 Fig. 1 Visual cone Fig. 2 2 Volume intersection method Fig. 3 3 Background subtraction Fig. 4

情報処理学会研究報告 い認識率を示す事が出来なかったと報告している 視覚特徴量としては SIFT や SURF のような局所的な 領域から特徴量を抽出する方法がある [4] [5] これらの 特徴量とフローベクトルを使いダイナミックなシーンの分 類を行う手法が提案されている しかし これらの画像特

xx/xx Vol. Jxx A No. xx 1 Fig. 1 PAL(Panoramic Annular Lens) PAL(Panoramic Annular Lens) PAL (2) PAL PAL 2 PAL 3 2 PAL 1 PAL 3 PAL PAL 2. 1 PAL

The copyright of this material is retained by the Information Processing Society of Japan (IPSJ). The material has been made available on the website

,4) 1 P% P%P=2.5 5%!%! (1) = (2) l l Figure 1 A compilation flow of the proposing sampling based architecture simulation

VRSJ-SIG-MR_okada_79dce8c8.pdf

paper.dvi

FoodLog [3] TADAproject [4] Google Goggles 1 Kumar [5] () Leaf snap Maruyama [6] 3 Lee [7] Yu [8] Gist SVM Active Query Sensing(AQS)

Computer Security Symposium October ,a) 1,b) Microsoft Kinect Kinect, Takafumi Mori 1,a) Hiroaki Kikuchi 1,b) [1] 1 Meiji U

Web Stamps 96 KJ Stamps Web Vol 8, No 1, 2004

2.R R R R Pan-Tompkins(PT) [8] R 2 SQRS[9] PT Q R WQRS[10] Quad Level Vector(QLV)[11] QRS R Continuous Wavelet Transform(CWT)[12] Mexican hat 4

23 Fig. 2: hwmodulev2 3. Reconfigurable HPC 3.1 hw/sw hw/sw hw/sw FPGA PC FPGA PC FPGA HPC FPGA FPGA hw/sw hw/sw hw- Module FPGA hwmodule hw/sw FPGA h

11) 13) 11),12) 13) Y c Z c Image plane Y m iy O m Z m Marker coordinate system T, d X m f O c X c Camera coordinate system 1 Coordinates and problem

顔画像を用いた個人認証システムの性能検討に関する研究

色の類似性に基づいた形状特徴量CS-HOGの提案

Optical Flow t t + δt 1 Motion Field 3 3 1) 2) 3) Lucas-Kanade 4) 1 t (x, y) I(x, y, t)

Microsoft PowerPoint - descriptor.ppt [互換モード]

情報処理学会研究報告 IPSJ SIG Technical Report Vol.2011-MBL-57 No.27 Vol.2011-UBI-29 No /3/ A Consideration of Features for Fatigue Es

情報処理学会研究報告 IPSJ SIG Technical Report Vol.2017-CG-166 No /3/ HUNTEXHUNTER1 NARUTO44 Dr.SLUMP1,,, Jito Hiroki Satoru MORITA The

DEIM Forum 2009 B4-6, Str

5b_08.dvi

Microsoft PowerPoint - cvim_harada pptx

1 Table 1: Identification by color of voxel Voxel Mode of expression Nothing Other 1 Orange 2 Blue 3 Yellow 4 SSL Humanoid SSL-Vision 3 3 [, 21] 8 325

人工知能学会研究会資料 SIG-KBS-B Analysis of Voting Behavior in One Night Werewolf 1 2 Ema Nishizaki 1 Tomonobu Ozaki Graduate School of Integrated B

(a) (b) 2 2 (Bosch, IR Illuminator 850 nm, UFLED30-8BD) ( 7[m] 6[m]) 3 (PointGrey Research Inc.Grasshopper2 M/C) Hz (a) (b

27 AR

23 Study on Generation of Sudoku Problems with Fewer Clues

Transcription:

Partial Copy Detection of Line Drawings from a Large-Scale Database Weihan Sun, Koichi Kise Graduate School of Engineering, Osaka Prefecture University E-mail: sunweihan@m.cs.osakafu-u.ac.jp, kise@cs.osakafu-u.ac.jp Abstract MSER HOG 11,603 1 2 Bas [1] SIFT(Scale-Invariant Feature Transform) [2] Ke SIFT PCA- SIFT(Principal Component Analysis SIFT)[4] [3] Kise PCA-SIFT [5] [6] MSER (Maximally Stable Extremal Region) [7] HOG (Histogram of Oriented Gradients) [8] 2 [6]

Duplicate Near Duplicate Intact Partial Copy Original Image Near Partial Copy Near Partial Copy with a background (a) (b) 2 1 [6] 2916 1 SIFT SIFT SIFT 2 1 5 (duplicate) (near duplicate) partial copy( ) intact partial copy near partial copy duplicate 1 near partial copy 2 3 1 3.1 3 2 (region detector) (feature descriptor) ID

Illegal Images with Copy Copyright Region Region Detector Detector Feature Feature Descriptor Descriptor Feature vectors Query Processing Matching Voting Copied Feature vector Database Database Processing (a) MSER Images 3 MSER HOG ANN(Approximate Nearest Neighbor search)[9] (Matching) (Voting) 3.2 : MSER Matas wide-baseline MSER [7] (Extremal region) MSER MSER 4 MSER MSER (b) MSER 4 MSER MSER MSER MSER ( 6 ) y 5 MSER 3.3 HOG HOG (Histogram of Oriented Gradients) Dalal [8]

(a) MSER (b) 5 one cell One block (a) (b) (c) 6 HOG MSER HOG 6(b) 9 9 6(c) 3 3 9 1 9 6 6 9 3 3 6 6 = 2916 3.4 [6] 6 3.5 ANN(Approximate Nearest Neighbor)[9] ANN k-d q k-d p q p r q r ANN ε r/(1 + ε) q p 1, 2 p 2 d(q, p 1 ) d(q, p 2 ) < T (1) 2 T R 4 4.1 10 11603

101 1/5 near partial copy 2 ( ) ( ) 3/4 7 2, 4, 10 3 4 ANN ε 5 CPU Opteron 2.8GHz, 64GB 4.2 1 SIFT [2] SIFT T 0.85 8 9 R R ( ) 8 SIFT 2 9 SIFT SIFT 5 89%, 10 75% MSER+HOG 10 (a) (b) 11 10 2 11(a) 11(b)

(a) (b) 2x (c) 4x (d) 10x 7 1. size of background 1x 2x 4x 10x method using SIFT 2, 376ms 4, 386ms 9, 476ms 18, 361ms proposed method 382ms 1, 021ms 2, 730ms 5, 615ms 2. (a) (b) rotation cumulative detection rate (R = 5) degree printed handwritten 0 99% 89% 30 99% 90% 45 99% % 12 12(a) SIFT 17GB 8.2GB 1 SIFT 1/6 1/3 4.3 2 30,45 2 ( 3/2 ) 5 2 3 2 0, 3 3/4 1 4.4 3 4

95 90 85 95 90 85 (a) (b) 2x 95 90 85 95 90 85 (c) 4x (d) 10x 8 3. scale cumulative detection rate (R = 5) printed handwritten 3/4 99% 89% 3/2 99% 98% ε 5 MSER HOG 4 ε R = 5. ε cumulative detection detection time rate (R = 5) 1 93% 64, 995ms 5 89% 336ms 10 84% 84ms SIFT 1. SIFT 2. SIFT 5 75 89%

60 40 20 60 40 20 0 0 (a) (b) 2x 60 40 20 60 40 20 0 0 (c) 4x (d) 10x 9 3. 4. SIFT [1] P. Bas, J-M Chassery, and B. Macq, Geometrically invariant watermarking using feature points, IEEE Trans. Antennas Propag., Vol.11, No.9, pp.1014-1028, 2002. [2] D. G. Lowe, Distinctive image features from scale-invariant key-points, Int. J. Comput. Vis. 60(2), pp.91 110, 2004. [3] Y. Ke, R.Sukthankar, and L. Hustion, Efficient near-duplicate detection and sub-image retrieval, MM, pp. 869 876, 2004. [4] Y. Ke and R. Sukthankar, PCA-SIFT: A more distinctive representation for local image descriptors, Proc. CVPR, Vol. 2, pp.506 513, 2004. [5] K. Kise, K. Noguchi and M. Iwamura, Simple Representation and Approximate Search of Feature Vectors for Large-Scale Object Recognition, Proc. BMVC, pp.182 191, 2007. [6],,,, PRMU2008-228, pp.121-126, 2009. [7] J. Matas, O. Chum, M. Urban and T. Pajdla, Robust Wide Baseline Stereo from Maximally Stable Extremal Regions, Proc. BMVC, pp.384 393, 2002. [8] N. Dalal and B. Triggs, Histograms of Oriented Gradients for Human Detection, Proc. IEEE CVPR, vol.1, pp.88 893, 2005. [9] S. Arya, D. Mount, R. Silverman and A. Y. Wu, An optimal algorithm for approximate nearest neighbor searching, Journal of the ACM, 45, 6, pp.891 923, 1998.

2024 © docsplayer.net プライバシー | 利用規約 | フィードバック