Journal of the Korea Academia-Industrial cooperation Society (한국산학기술학회논문지)

The Korea Academia-Industrial cooperation Society (한국산학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Acquisition of Region of Interest through Illumination Correction in Dynamic Image Data

동영상 데이터에서 조명 보정을 사용한 관심 영역의 획득

  • 장석우 (안양대학교 소프트웨어학과)
  • Received : 2021.01.27
  • Accepted : 2021.03.05
  • Published : 2021.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Low-cost, ultra-high-speed cameras, made possible by the development of image sensors and small displays, can be very useful in image processing and pattern recognition. This paper introduces an algorithm that corrects irregular lighting from a high-speed image that is continuously input with a slight time interval, and which then obtains an exposed skin color region that is the area of interest in a person from the corrected image. In this study, the non-uniform lighting effect from a received high-speed image is first corrected using a frame blending technique. Then, the region of interest is robustly obtained from the input high-speed color image by applying an elliptical skin color distribution model generated from iterative learning in advance. Experimental results show that the approach presented in this paper corrects illumination in various types of color images, and then accurately acquires the region of interest. The algorithm proposed in this study is expected to be useful in various types of practical applications related to image recognition, such as face recognition and tracking, lighting correction, and video indexing and retrieval.

영상 센서 및 소형 디스플레이의 발달로 가능해진 저가의 고속 카메라는 영상처리 및 패턴인식 분야에서 유용하게 활용될 수 있다. 본 논문에서는 약간의 시차를 두고 연속적으로 입력되는 고속의 영상으로부터 불규칙적인 조명을 보정한 다음, 조명이 보정된 영상으로부터 사람의 관심 영역인 노출된 피부 색상 영역을 획득하는 알고리즘을 소개한다. 본 연구에서는 먼저 받아들인 고속의 영상으로부터 비 균일하게 발생된 조명적인 효과를 프레임 블렌딩 기법을 사용하여 보정한다. 그런 다음, 사전에 반복적인 학습으로 생성된 타원형의 피부 색상 분포 모델을 적용하여 입력된 고속의 컬러 영상으로부터 관심 영역을 강인하게 획득한다. 실험 결과에서는 본 논문에서 제시된 접근 방법이 입력되는 컬러 영상으로부터 조명을 보정한 다음 관심 영역을 정확하게 획득한다는 것을 보여준다. 본 연구에서 제안된 알고리즘은 얼굴 인식 및 추적, 조명 보정 및 제거, 동영상 색인 및 검색 등과 같은 영상 인식과 연관된 다양한 종류의 실제적인 응용 프로그램에서 매우 유용하게 이용될 것으로 추측된다.

Keywords

References

  1. J. Javh, J. Slavic, and M. Boltezar, "High Frequency Modal Identification on Noisy High-Speed Camera Data," Mechanical Systems and Signal Processing, Vol.98, pp. 344-351, January 2018. DOI: https://doi.org/10.1016/j.ymssp.2017.05.008
  2. W. Jung, C. Hurth, and F. Zenhausern, "Real-Time Monitoring of Viscosity Changes Triggered by Chemical Reactions Using a High-Speed Imaging Method," Sensing and Bio-Sensing Research, Vol.5, pp. 8-12, September 2015. DOI: https://doi.org/10.1016/j.sbsr.2015.05.003
  3. M. H. Yap, M. Goyal, F. Osman, R. Marti, E. Denton, A. Juette, and R. Zwiggelaar, "Breast Ultrasound Region of Interest Detection and Lesion Localisation," Artificial Intelligence in Medicine, Vol.107, pp. 1-8, July 2020. DOI: https://doi.org/10.1016/j.artmed.2020.101880
  4. C.-H. Hu, J. Yu, F. Wu, Y. Zhang, X.-Y. Jing, X.-B. Lu, P. Liu, "Face Illumination Recovery for the Deep Learning Feature under Severe Illumination Variations," Pattern Recognition, Vol. 111, pp. 1-13, March 2021. DOI: https://doi.org/10.1016/j.patcog.2020.107724
  5. B. Liao, J. Hu, and R. O. Gilmore, "Optical Flow Estimation Combining with Illumination Adjustment and Edge Refinement in Livestock UAV Videos," Computers and Electronics in Agriculture, Vol. 180, pp. 1-12, December 2020. DOI: https://doi.org/10.1016/j.compag.2020.10591
  6. U. Saeed, K. Masood, and H. Dawood, "Illumination Normalization Techniques for Makeup-Invariant Face Recognition," Computers and Electrical Engineering, Vol. 89, pp. 1-14, November 2020. DOI: https://doi.org/10.1016/j.compeleceng.2020.106921
  7. S. Goswami and S. K. Singh, "A Simple Deep Learning-Based Image Illumination Correction Method for Paintings," Pattern Recognition Letters, Vol. 138, pp. 392-396, August 2020. DOI: https://doi.org/10.1016/j.patrec.2020.08.013
  8. P. Mishra, S. Lohumi, H. A. Khand, and A. Nordon, "Close-Range Hyperspectral Imaging of Whole Plants for Digital Phenotyping: Recent Applications and Illumination Correction Approaches," Computers and Electronics in Agriculture, Vol. 178, pp. 1-11, September 2020. DOI: https://doi.org/10.1016/j.compag.2020.105780
  9. Z. Zhu, H. Liu, J. Lu, and S.-M. Hu, "A Metric for Video Blending Quality Assessment," IEEE Transactions on Image Processing, Vol.29, pp. 3014-3022, November 2019. DOI: https://doi.org/10.1109/TIP.2019.2955294
  10. K. Muhammad, M. Sajjad, I. Mehmood, S. Rho, and S. W. Baik, "Image Steganography Using Uncorrelated Color Space and Its Application for Security of Visual Contents in Online Social Networks," Future Generation Computer Systems, Vol.86, pp. 951-960, November 2016. DOI: https://doi.org/10.1016/j.future.2016.11.029
  11. R.-L. Hsu, M. Abdel-Mottaleb, and A. K. Jain, "Face Detection in Color Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.24, No.5, pp.696-706, May 2002. DOI: https://doi.org/10.1109/34.1000242