(JBE Vol. 24, No. 2, March 2019) (Special Paper) 24 2, (JBE Vol. 24, No. 2, March 2019) ISSN

Similar documents
2 : 3 (Myeongah Cho et al.: Three-Dimensional Rotation Angle Preprocessing and Weighted Blending for Fast Panoramic Image Method) (Special Paper) 23 2

(JBE Vol. 21, No. 1, January 2016) (Regular Paper) 21 1, (JBE Vol. 21, No. 1, January 2016) ISSN 228

(JBE Vol. 22, No. 2, March 2017) (Regular Paper) 22 2, (JBE Vol. 22, No. 2, March 2017) ISSN

02( ) SAV12-19.hwp

09권오설_ok.hwp

(JBE Vol. 23, No. 2, March 2018) (Special Paper) 23 2, (JBE Vol. 23, No. 2, March 2018) ISSN

2 : (Seungsoo Lee et al.: Generating a Reflectance Image from a Low-Light Image Using Convolutional Neural Network) (Regular Paper) 24 4, (JBE

(JBE Vol. 23, No. 2, March 2018) (Special Paper) 23 2, (JBE Vol. 23, No. 2, March 2018) ISSN

1 : 360 VR (Da-yoon Nam et al.: Color and Illumination Compensation Algorithm for 360 VR Panorama Image) (Special Paper) 24 1, (JBE Vol. 24, No

(JBE Vol. 23, No. 6, November 2018) (Regular Paper) 23 6, (JBE Vol. 23, No. 6, November 2018) ISSN 2

(JBE Vol. 23, No. 5, September 2018) (Regular Paper) 23 5, (JBE Vol. 23, No. 5, September 2018) ISSN

<30312DC1A4BAB8C5EBBDC5C7E0C1A4B9D7C1A4C3A52DC1A4BFB5C3B62E687770>

3 : OpenCL Embedded GPU (Seung Heon Kang et al. : Parallelization of Feature Detection and Panorama Image Generation using OpenCL and Embedded GPU). e

2 : (Juhyeok Mun et al.: Visual Object Tracking by Using Multiple Random Walkers) (Special Paper) 21 6, (JBE Vol. 21, No. 6, November 2016) ht

(JBE Vol. 24, No. 1, January 2019) (Regular Paper) 24 1, (JBE Vol. 24, No. 1, January 2019) ISSN 2287

08김현휘_ok.hwp

High Resolution Disparity Map Generation Using TOF Depth Camera In this paper, we propose a high-resolution disparity map generation method using a lo

1 : (Sunmin Lee et al.: Design and Implementation of Indoor Location Recognition System based on Fingerprint and Random Forest)., [1][2]. GPS(Global P

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE. vol. 29, no. 10, Oct ,,. 0.5 %.., cm mm FR4 (ε r =4.4)

2 : (JEM) QTBT (Yong-Uk Yoon et al.: A Fast Decision Method of Quadtree plus Binary Tree (QTBT) Depth in JEM) (Special Paper) 22 5, (JBE Vol. 2

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE. vol. 29, no. 6, Jun Rate). STAP(Space-Time Adaptive Processing)., -

19_9_767.hwp

04 최진규.hwp

2 : HEVC (Young-Ho Seo et al.: H.265/HEVC Video Watermarking Method with High Image Quality) (Regular Paper) 24 1, (JBE Vol. 24, No. 1, January

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE Nov.; 26(11),

3 : 3D (Seunggi Kim et. al.: 3D Depth Estimation by a Single Camera) (Regular Paper) 24 2, (JBE Vol. 24, No. 2, March 2019)

(JBE Vol. 23, No. 5, September 2018) (Regular Paper) 23 5, (JBE Vol. 23, No. 5, September 2018) ISSN

(JBE Vol. 21, No. 1, January 2016) (Special Paper) 21 1, (JBE Vol. 21, No. 1, January 2016) ISSN 228

DBPIA-NURIMEDIA

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE Dec.; 27(12),

DBPIA-NURIMEDIA

(JBE Vol. 20, No. 5, September 2015) (Special Paper) 20 5, (JBE Vol. 20, No. 5, September 2015) ISS

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE Sep.; 30(9),

<353420B1C7B9CCB6F52DC1F5B0ADC7F6BDC7C0BB20C0CCBFEBC7D120BEC6B5BFB1B3C0B0C7C1B7CEB1D7B7A52E687770>

(JBE Vol. 23, No. 1, January 2018) (Special Paper) 23 1, (JBE Vol. 23, No. 1, January 2018) ISSN 2287-

3 : (Won Jang et al.: Musical Instrument Conversion based Music Ensemble Application Development for Smartphone) (Special Paper) 22 2, (JBE Vol

(JBE Vol. 24, No. 4, July 2019) (Special Paper) 24 4, (JBE Vol. 24, No. 4, July 2019) ISSN

(JBE Vol. 23, No. 4, July 2018) (Special Paper) 23 4, (JBE Vol. 23, No. 4, July 2018) ISSN

26 이경승(394~400).hwp

1. 서 론

(JBE Vol. 23, No. 1, January 2018). (VR),. IT (Facebook) (Oculus) VR Gear IT [1].,.,,,,..,,.. ( ) 3,,..,,. [2].,,,.,,. HMD,. HMD,,. TV.....,,,,, 3 3,,

2 : (Jaeyoung Kim et al.: A Statistical Approach for Improving the Embedding Capacity of Block Matching based Image Steganography) (Regular Paper) 22

<4D F736F F D20B1E2C8B9BDC3B8AEC1EE2DC0E5C7F5>

1 : UHD (Heekwang Kim et al.: Segment Scheduling Scheme for Efficient Bandwidth Utilization of UHD Contents Streaming in Wireless Environment) (Specia

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE Jun.; 27(6),

<30345F D F FC0CCB5BFC8F15FB5B5B7CEC5CDB3CEC0C720B0BBB1B8BACE20B0E6B0FCBCB3B0E8B0A120C5CDB3CE20B3BBBACEC1B6B8ED2E687770>

6 : (Gicheol Kim et al.: Object Tracking Method using Deep Learing and Kalman Filter) (Regular Paper) 24 3, (JBE Vol. 24, No. 3, May 2019) http

4 : (Hyo-Jin Cho et al.: Audio High-Band Coding based on Autoencoder with Side Information) (Special Paper) 24 3, (JBE Vol. 24, No. 3, May 2019

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE Jul.; 27(7),

09È«¼®¿µ 5~152s

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE Jul.; 29(7),

2 : (EunJu Lee et al.: Speed-limit Sign Recognition Using Convolutional Neural Network Based on Random Forest). (Advanced Driver Assistant System, ADA

03-서연옥.hwp

À±½Â¿í Ãâ·Â

(JBE Vol. 23, No. 6, November 2018) (Special Paper) 23 6, (JBE Vol. 23, No. 6, November 2018) ISSN 2

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE Mar.; 25(3),

04김호걸(39~50)ok

07.045~051(D04_신상욱).fm

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE Feb.; 29(2), IS

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE Mar.; 28(3),

4 : CNN (Sangwon Suh et al.: Dual CNN Structured Sound Event Detection Algorithm Based on Real Life Acoustic Dataset) (Regular Paper) 23 6, (J

(JBE Vol. 7, No. 4, July 0)., [].,,. [4,5,6] [7,8,9]., (bilateral filter, BF) [4,5]. BF., BF,. (joint bilateral filter, JBF) [7,8]. JBF,., BF., JBF,.

디지털포렌식학회 논문양식

인문사회과학기술융합학회

6.24-9년 6월

DBPIA-NURIMEDIA

<C7A5C1F620BEE7BDC4>

<5B D B3E220C1A634B1C720C1A632C8A320B3EDB9AEC1F628C3D6C1BE292E687770>

03-16-김용일.indd

05( ) CPLV12-04.hwp

4 : WebRTC P2P DASH (Ju Ho Seo et al.: A transport-history-based peer selection algorithm for P2P-assisted DASH systems based on WebRTC) (Special Pape

(JBE Vol. 23, No. 1, January 2018) (Regular Paper) 23 1, (JBE Vol. 23, No. 1, January 2018) ISSN 2287

<B1B3B9DFBFF83330B1C7C1A631C8A35FC6EDC1FDBABB5FC7D5BABB362E687770>

<30362E20C6EDC1FD2DB0EDBFB5B4EBB4D420BCF6C1A42E687770>

°í¼®ÁÖ Ãâ·Â

融合先验信息到三维重建 组会报 告[2]

표지

232 도시행정학보 제25집 제4호 I. 서 론 1. 연구의 배경 및 목적 사회가 다원화될수록 다양성과 복합성의 요소는 증가하게 된다. 도시의 발달은 사회의 다원 화와 밀접하게 관련되어 있기 때문에 현대화된 도시는 경제, 사회, 정치 등이 복합적으로 연 계되어 있어 특

DBPIA-NURIMEDIA

[ReadyToCameral]RUF¹öÆÛ(CSTA02-29).hwp

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE Jan.; 26(1),

(JBE Vol. 23, No. 5, September 2018) (Regular Paper) 23 5, (JBE Vol. 23, No. 5, September 2018) ISSN

... K-vision Fig.. K-vision camera tracking screen Drummond [3] 3. 3 (lines), (edge) 3. (target). (homography perspective transform) [4]. (drifting).

14.531~539(08-037).fm

(JBE Vol. 23, No. 5, September 2018) (Special Paper) 23 5, (JBE Vol. 23, No. 5, September 2018) ISSN

30이지은.hwp

<313120C0AFC0FCC0DA5FBECBB0EDB8AEC1F2C0BB5FC0CCBFEBC7D15FB1E8C0BAC5C25FBCF6C1A42E687770>

Software Requirrment Analysis를 위한 정보 검색 기술의 응용

<B8F1C2F72E687770>

04_이근원_21~27.hwp

5 : HEVC GOP R-lambda (Dae-Eun Kim et al.: R-lambda Model based Rate Control for GOP Parallel Coding in A Real-Time HEVC Software Encoder) (Special Pa

2 : CNN (Jaeyoung Kim et al.: Experimental Comparison of CNN-based Steganalysis Methods with Structural Differences) (Regular Paper) 24 2, (JBE

06_ÀÌÀçÈÆ¿Ü0926

2 : (Rahoon Kang et al.: Image Filtering Method for an Effective Inverse Tone-mapping) (Special Paper) 24 2, (JBE Vol. 24, No. 2, March 2019) h

Delving Deeper into Convolutional Networks for Learning Video Representations - Nicolas Ballas, Li Yao, Chris Pal, Aaron Courville arXiv:

Journal of Educational Innovation Research 2017, Vol. 27, No. 3, pp DOI: (NCS) Method of Con

DBPIA-NURIMEDIA

(JBE Vol. 22, No. 2, March 2017) (Special Paper) 22 2, (JBE Vol. 22, No. 2, March 2017) ISSN

8-VSB (Vestigial Sideband Modulation)., (Carrier Phase Offset, CPO) (Timing Frequency Offset),. VSB, 8-PAM(pulse amplitude modulation,, ) DC 1.25V, [2

(JBE Vol. 22, No. 5, September 2017) (Special Paper) 22 5, (JBE Vol. 22, No. 5, September 2017) ISSN

Transcription:

(Special Paper) 24 2, 2019 3 (JBE Vol. 24, No. 2, March 2019) https://doi.org/10.5909/jbe.2019.24.2.234 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) SIFT a), a), a), a) SIFT Image Feature Extraction based on Deep Learning Jae-Eun Lee a), Won-Jun Moon a), Young-Ho Seo a), and Dong-Wook Kim a) SIFT SIFT (Deep Neural Network). DIV2K 33 33, SIFT RGB. (ground truth) (scale, octave) 0, (sigma) 1.6, (intervals) 3 RobHess SIFT. VGG-16 13 23 33,. (sigmoid) (softmax). 99%. Abstract In this paper, we propose a deep neural network which extracts SIFT feature points by determining whether the center pixel of a cropped image is a SIFT feature point. The data set of this network consists of a DIV2K dataset cut into 33 33 size and uses RGB image unlike SIFT which uses black and white image. The ground truth consists of the RobHess SIFT features extracted by setting the octave (scale) to 0, the sigma to 1.6, and the intervals to 3. Based on the VGG-16, we construct an increasingly deep network of 13 to 23 and 33 convolution layers, and experiment with changing the method of increasing the image scale. The result of using the sigmoid function as the activation function of the output layer is compared with the result using the softmax function. Experimental results show that the proposed network not only has more than 99% extraction accuracy but also has high extraction repeatability for distorted images. Keyword : SIFT Feature extraction, Deep learning, VGG, CNN(Convolutional Neural Network), Repeatability a) (Department of Electronic Materials Engineering, Kwangwoon University) Corresponding Author : (Dong-Wook Kim) E-mail: dwkim@kw.ac.kr Tel: +82-2-940-5167 ORCID: https://orcid.org/0000-0002-4668-743x 2018. This research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(NRF-2016R1D1A1B03930691). The present Research has been conducted by the Research Grant of Kwangwoon University in 2019. Manuscript received January 8, 2019; Revised March 6, 2019; Accepted March 8, 2019. Copyright 2019 Korean Institute of Broadcast and Media Engineers. All rights reserved. This is an Open-Access article distributed under the terms of the Creative Commons BY-NC-ND (http://creativecommons.org/licenses/by-nc-nd/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited and not altered.

3: SIFT (Jae-Eun Lee et al.: SIFT Image Feature Extraction based on Deep Learning). (feature extraction),,.,,. (Harris corner) [1].. (scale). Mikolajczyk (Laplacian) [2].,. Shi Tomasi affine Shi& Tomasi [3]. Lowe SIFT(Scale Invariant Feature Transform) [4]. SIFT DoG(Difference of Gaussian). SIFT. Bay SURF(Speed Up Robust Feature) [5] Rosten FAST(Features from Accelerated Segment Test) [6], Mair AGAST [7]., (stitching) SIFT [8]. Rublee FAST (feature descriptor) BRIEF ORB(Oriented FAST and Rotated BRIEF) [9]. SIFT., (deep learning). GPU(Graphic Process- ing Unit), (big data). SIFT. VGG-16,. (repeatability).. SIFT. SIFT (Deep Neural Network, DNN)., SIFT... SIFT SIFT RGB, (intervals), scale space( ). (Gaussian), (σ), σ. σ,.. (1), ( (2)),.

,. DoG DoG, DoG. 1., DoG., DoG DoG, 8, 9, 26. 2., (contrast) (edge). SIFT. 3. SIFT, (Virtual Reality, VR) (stitching). SIFT,., DNN DNN. DNN. - DNN SIFT. 1. SIFT DoG Fig. 1. The process to form a SIFT DoG pyramid. SIFT DNN(feature extraction DNN) SIFT. SIFT, DNN. 1. 2. SIFT Fig. 2. SIFT extrema extraction process

3: SIFT (Jae-Eun Lee et al.: SIFT Image Feature Extraction based on Deep Learning) DIV2K [10]. 800 RobHess SIFT label [11]. SIFT 0, σ 1.6, interval 3. 3 - (hyper-parameter) SIFT. SIFT RGB, 33 33. 16 DNN. 215k, 2,152k 1:10 2M.,. (test) 1:10,.,. 3. 0 SIFT Fig. 3. SIFT features extracted with octave set to 0 2. 2014 (ImageNet challenge) VGG-16 DNN [12]. 5 5 3 3,. VGG-16. 1. 33 33, RGB 3 (33 33 3). 1 A VGG-16. (Conv) 13, (max pooling) 5 (fully connected, FC) 3. 3 3, (stride) 1 1. 3 3 0-(0 padding), 2 2,. 2, 2, 3, 3, 3 2 2, 64, 128, 256, 512, 512. 3. 2 512 1 1 1. (activation) leaky ReLU, 0 1 (sigmoid). 0.5, 0.5. 1 ConvA-B ConvC- D C C B D D ( ). FC-X X (node). 1 B C A 10, 20. D C 6, 12, 19, 26, 33 2 2.

1. DNN Table 1. Configurations of the proposed DNNs A B C D E 16 weight layers 26 weight layers 36 weight layers 36 weight layers 36 weight layers conv3-64 conv3-64 conv3-128 conv3-128 input (33 33 RGB image) conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-64 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 conv3-128 FC-512 FC-512 FC-512 sigmoid softmax E A~D (softmax)., A~D E 2 --(one-hot-encoding) 01, 10.. (Python), PC Intel(R) Xeon(R) CPU E3-1275 v6 @3.80GHz, 64GB RAM, 64-bit Windows, GPU GTX 1080ti. PC DNN

3: SIFT (Jae-Eun Lee et al.: SIFT Image Feature Extraction based on Deep Learning) 1 2. (mini-batch) 500, 300 (epoch). 2 1 DNN. DNN 99.4%, 99.109%. C, D, E 100%,. A, B, C,.,. E. (a) (c) 4. ; (a) +25, (b) +50, (c) +75, (d) +100 Fig. 4. Image examples with varying brightness level; (a) +25, (b) +50, (c) +75, (d) +100 (b) (d) 2. DNN Table 2. Experimental results for the proposed DNN DNN Train accuracy(%) Test accuracy(%) A 98.100 96.796 B 99.300 99.002 C 99.900 99.083 D 99.900 99.109 E 99.900 99.084 (a) (b) DNN. ( ) (3) (min ), DNN. 1 [13]. min (c) (e) 5. ; (a), (b) 0.5, (c) 1.0, (d) 1.5, (e) 2.0, (f) 2.5 Fig. 5. Example Images with varying blur level; (a) original, (b) radius 0.5, (c) radius 1.0, (d) radius 1.5, (e) radius 2.0, (f) radius 2.5. (d) (f)

, 4 5. 5(a) 4 5, 4 4, 5(b)~(f) 5., SIFT( ) 6. 6(a), DNN. 1, 2 SIFT DNN,. 6(b),. (a) (b) 6. ; (a), (b) Fig. 6. Results of the feature point repeatability measure for the distorted images; (a) change in brightness, (b) change in blur. 2 6, DNN 99%, SIFT.. SIFT DNN. DNN VGG DNN(VGG-16) ( ), 5 DNN. DNN 99%, SIFT. DNN SIFT /. 5 DNN. 2 2.., 2 2,..,.

3: SIFT (Jae-Eun Lee et al.: SIFT Image Feature Extraction based on Deep Learning).. (References) [1] C. Harris, M. Stephens, A combined corner and edge detector, Proceedings of the Alvey Vision Conference, pp.147-151, 1988. [2] K. Mikolajczyk, C. Schmid, Indexing based on scale invariant interest points, ICCV, Vol.1, pp. 525-531, 2001. [3] J. Shi, C. Tomasi, Good features to track, 9th IEEE Conference on Computer Vision and Pattern Recognition, Springer, Heidelberg, 1994. [4] D. G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, Vol.60, No.2, pp.91-110, 2004. [5] H. Bay, T. Tuytelaars, and L. Van Gool, Surf: Speeded up robust features, In European Conference on Computer Vision, Vol.1, No.2, May 2006. [6] E. Rosten, T. Drummond, Machine learning for high-speed corner detection, Proc. 9th European Conference on Computer Vision (ECCV'06), May 2006. [7] E. Mair, G. Hager, D. Burschka, M. Suppa, and G. Hirzinger, Adaptive and generic corner detection based on the accelerated segment test, Computer Vision-ECCV 2010, Vol.2, No.2, pp.183-196, 2010. [8] M. WonJun, S. Youngho, and K. Dongwook, Parameter Analysis for Time Reduction in Extracting SIFT Keypoints in the Aspect of Image Stitching, Journal of Broadcast Engineering, Vol.23, No.4, pp.559-573, July 2018. [9] E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, ORB: an efficient alternative to SIFT or SURF, In Proc. of the IEEE Intl. Conf. on Computer Vision (ICCV), Vol.13, 2011. [10] E. Agustsson, R. Timofte, NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study, In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017. [11] R. Hess, An Open-Source SIFT Library, ACM Multimedia, pp.1493-1496, 2010. [12] K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, In Proc. International Conference on Learning Representations (ICLR), 2015. [13] K. Mikolajczyk, C. Schmid, Scale and affine invariant interest point detectors, IJCV, Vol.1, No.60, pp.63-86, 2004. - 2019 2 : () - 2019 3 ~ : () - ORCID : https://orcid.org/0000-0001-9760-4801 - :,, - 2018 2 : () - 2018 3 ~ : () - ORCID : https://orcid.org/0000-0002-9620-9524 - : Virtual Reality,, 2D,

- 1999 2 : () - 2001 2 : () - 2004 8 : () - 2005 9 ~ 2008 2 : - 2008 3 ~ : - ORCID : http://orcid.org/0000-0003-1046-395x - :, 2D/3D,, SoC - 1983 2 : () - 1985 2 : - 1991 9 : Georgia () - 1992 3 ~ : - ORCID : http://orcid.org/0000-0002-4668-743x - : 3D,, VLSI Testability, VLSI CAD, DSP, Wireless Communication