Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Estimate Saliency map based on Multi Feature Assistance of Learning Algorithm

다중 특징을 지원하는 학습 기반의 saliency map에 관한 연구

  • Han, Hyun-Ho (Dept of Plasma Bio Display, KwangWoon University) ;
  • Lee, Gang-Seong (Ingenium college of liberal arts, Kwangwoon university) ;
  • Park, Young-Soo (Ingenium college of liberal arts, Kwangwoon university) ;
  • Lee, Sang-Hun (Ingenium college of liberal arts, Kwangwoon university)
  • 한현호 (광운대학교 플라즈마 바이오 디스플레이학과) ;
  • 이강성 (광운대학교 인제니움학부대학) ;
  • 박영수 (광운대학교 인제니움학부대학) ;
  • 이상훈 (광운대학교 인제니움학부대학)
  • Published : 2017.06.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a method for generating improved saliency map by learning multiple features to improve the accuracy and reliability of saliency map which has similar result to human visual perception type. In order to overcome the inaccurate result of reverse selection or partial loss in color based salient area estimation in existing salience map generation, the proposed method generates multi feature data based on learning. The features to be considered in the image are analyzed through the process of distinguishing the color pattern and the region having the specificity in the original image, and the learning data is composed by the combination of the similar protrusion area definition and the specificity area using the LAB color space based color analysis. After combining the training data with the extrinsic information obtained from low level features such as frequency, color, and focus information, we reconstructed the final saliency map to minimize the inaccurate saliency area. For the experiment, we compared the ground truth image with the experimental results and obtained the precision-recall value.

본 논문에서는 인간의 시각인지 형태와 유사한 결과를 갖는 Saliency map의 정확성과 신뢰성을 향상시키기 위해 학습한 다중 특징을 기반으로 개선된 saliency map 방법을 제안한다. 기존의 Saliency map 생성에서 색상 기반의 돌출 영역 추정 시 발생하는 역 선택이나 부분손실 등의 부정확한 결과가 나오는 것을 보완하기 위해 제안하는 방법은 학습 기반의 다중 특징 데이터를 생성하였다. 원 영상에서의 색상 패턴과 특이성을 갖는 영역의 구별과정을 거쳐 영상에서 고려될 특성들을 분석하고, LAB 색 공간 기반의 색상 분석을 이용한 유사 돌출 영역 정의와 특이성 영역의 조합으로 학습 데이터를 구성한다. 구성된 학습 데이터와 주파수, 색상, 초점정보 등의 low level feature로 구한 돌출 정보를 결합한 뒤 최종 saliency map을 구하기 위해 재구성 과정을 거쳐 부정확한 saliency 영역을 최소화하도록 하였다. 실험을 위해 Ground truth 이미지를 각 실험 결과와 비교하여 precision-recall 및 F-Measure 값을 구한 결과 기존 알고리즘에 비해 7%, 29%의 향상된 결과를 나타내었다.

Keywords

References

  1. T. H. Yoo, S. H. Lee, "Generation Method of Depth Map based on Vanishing Line using Gabor Filter", Journal of the Korea Convergence Society, Vol. 3, No.1, pp. 13-17, 2012.
  2. J. H. Park, G. S. Lee, S. H. Lee, "A Study on the Convergence Technique enhanced GrabCut Algorithm Using Color Histogram and Modified Sharpening Filter", Journal of the Korea Convergence Society, Vol. 6, No. 6, pp. 1-8, 2015. https://doi.org/10.15207/JKCS.2015.6.6.001
  3. H. H. Han, G. S. Lee, J. Y. Lee, J. S. Kim, S. H. Lee, "A new method to create depth information based on lighting analysis for 2D/3D conversion", Journal of Central South University, Vol. 20, No. 10, pp. 2715-2719, 2013. https://doi.org/10.1007/s11771-013-1788-0
  4. Min-Seok Choi, "Complex Color Model for Efficient Representation of Color-Shape in Content-based Image Retrieval", Journal of digital Convergence , Vol. 15, No. 4, pp. 267-273, 2017. https://doi.org/10.14400/JDC.2017.15.4.267
  5. Eugene Rhee, "Security Algorithm for Vehicle Type Recognition," Journal of Convergence for Information Technology, Vol. 7, No. 2, pp. 77-82, 2017. https://doi.org/10.22156/CS4SMB.2017.7.2.077
  6. Yang, K. F., Li, H., Li, C. Y., Li, Y. J. "A Unified Framework for Salient Structure Detection by Contour-Guided Visual Search", IEEE Transactions on Image Processing, 25.8: 3475-3488, 2016. https://doi.org/10.1109/TIP.2016.2572600
  7. S. H. Han, Y. P. Hong, S. H. Lee, "Saliency Map Creation Method Robust to the Contour of Objects", Journal of digital Convergence, Vol. 10, No. 3, pp. 173-178, 2012. https://doi.org/10.14400/JDPM.2012.10.3.173
  8. S. H. Han, Y. S. Kim, J. Y. Lee, S. H. Lee, "2D/3D conversion method using depth map based on haze and relative height cue", Journal of digital Convergence, Vol. 10, No. 9, pp. 351-356, 2012. https://doi.org/10.14400/JDPM.2012.10.9.351
  9. B. S. Kang, K. H. Lee, "Fire Alarm Solutions Through the Convergence of Image Processing Technology and M2M", Journal of the Korea Convergence Society, Vol. 7, No. 1, pp.37-42, 2016. https://doi.org/10.15207/JKCS.2016.7.1.037
  10. Achanta, R., Susstrunk, S. "Saliency detection using maximum symmetric surround", In: Image Processing (ICIP), 2010 17th IEEE International Conference on. IEEE, p. 2653-2656, 2010.
  11. Cheng, M. M., Mitra, N. J., Huang, X., Torr, P. H., Hu, S. M. "Global contrast based salient region detection", IEEE Transactions on Pattern Analysis and Machine Intelligence, 37.3: 569-582, 2015. https://doi.org/10.1109/TPAMI.2014.2345401
  12. Achanta, R., Hemami, S., Estrada, F., Susstrunk, S., "Frequency-tuned Salient Region Detection," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1597-1604, 2009.
  13. Bruce, N. D., Tsotsos, J. K. "Saliency, attention, and visual search: An information theoretic approach", Journal of vision, 9.3: 5-5, 2009.
  14. Harel, J., Koch, C., & Perona, P. "Graph-based visual saliency", In NIPS, Vol. 1, No. 2, p. 5.
  15. Achanta, R., Estrada, F., Wils, P., Susstrunk, S. "Salient region detection and segmentation", Computer Vision Systems, pp. 66-75, 2008.
  16. Frintrop, S., Werner, T., Martin Garcia, G. "Traditional saliency reloaded: A good old model in new shape", In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 82-90. 2015.
  17. Duan, L., Wu, C., Miao, J., Qing, L., Fu, Y. "Visual saliency detection by spatially weighted dissimilarity", In: Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, p. 473-480. 2011.
  18. Kienzle, W., Wichmann, F. A., Scholkopf, B., Franz, M. O. "A nonparametric approach to bottom-up visual saliency", Advances in neural information processing systems, 19, 689, 2007