Comparative Study on Illumination Compensation Performance of Retinex model and Illumination-Reflectance model

레티넥스 모델과 조명-반사율 모델의 조명 보상 성능 비교 연구

  • 정지년 (한국과학기술원 전자전산학과) ;
  • 양현승 (한국과학기술원 전자전산학과)
  • Published : 2006.11.15

Abstract

To apply object recognition techniques to real environment, illumination compensation method should be developed. As effective illumination compensation model, we focused our attention on Retinex model and illumination-Reflectance model, implemented them, and experimented on their performance. We implemented Retinex model with Single Scale Retinex, Multi-Scale Retinex, and Retinex Neural Network and Multi-Scale Retinex Neural Network, neural network model of Retinex model. Also, we implemented illumination-Reflectance model with reflectance image calculation by calculating an illumination image by low frequency filtering in frequency domain of Discrete Cosine Transform and Wavelet Transform, and Gaussian blurring. We compare their illumination compensation performance to facial images under nine illumination directions. We also compare their performance after post processing using Principal Component Analysis(PCA). As a result, illumination Reflectance model showed better performance and their overall performance was improved when illumination compensated images were post processed by PCA.

대상인식 기술을 실제 환경에 적용하기 위해서는 조명 보상 기술 개발이 필수적이다. 본 논문은 조명의 방향 변화로 인한 영상의 변화를 보상하는 방법으로써 레티넥스 모델과 조명-반사율 모델에 주목하고, 이를 다양한 방법으로 구현하고 그 성능을 비교함으로써 효과적인 조명 보상방법을 제시하였다. 본 논문에서는 레티넥스 모델을 단일 스케일 레티넥스, 다중 스케일 레티넥스와 이를 신경망으로 재구성한 레티넥스 신경망, 다중 스케일 레티넥스 신경망으로 구현하였다. 조명 반사율 모델은 조명 영상을 이산코사인변환, 웨이블릿변환을 통한 저주파 필터링과 가우시안 블러로 구한 후, 이를 이용하여 반사율 영상을 계산하여 조명 보상을 수행하도록 하였다. 구현된 조명 보상을 9가지 조명 방향 변화가 존재하는 얼굴 영상에 대해 조명 보상을 수행하여, 그 성능을 측정하고 비교하였으며, 더불어 주성분분석 계수를 이용하여 그 성능을 측정하였다. 실험 결과 조명-반사율 모델이 보다 좋은 성능을 보였으며, 주성분분석 계수를 추출한 경우 전반적인 성능향상을 얻을 수 있었다.

Keywords

References

  1. Adini Y., Moses Y. and Ullman S. 'Face recognition: The problem of compensating for changes in illumination direction,' IEEE Transaction on Pattern Analysis and Machine Intelligence 1997. No.19, pp. 721-732 https://doi.org/10.1109/34.598229
  2. D. Jacobs, P. Belhumeur and R. Basri, 'Comparing Images Under Variable Illumination,' IEEE Conference on Computer Vision and Pattern Recognition, pp. 610-617, 1998 https://doi.org/10.1109/CVPR.1998.698668
  3. Shashua, A. and Riklin-Raviv, T., 'The quotient image: class-based re-rendering and recognition with varying illuminations,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume: 23, Issue: 2, Pages:129-139, Feb. 2001 https://doi.org/10.1109/34.908964
  4. A.S. Georghiades, Peter N. Belhumeur and David J. Kriegrnan, 'Illumination-Based Image Synthesis: Creating Novel Images of Human Faces Under Differing Pose and Lighting,' IEEE Workshop on Multi-View Modeling and Analysis of Visual Scenes pp. 47-54, Fort Collins, Colorado, 1999 https://doi.org/10.1109/MVIEW.1999.781082
  5. Ronen Basri and David W. Jacob, 'Larnbertian Reflectance and Linear Subspaces,' IEEE Trans. On PAMI, vol.25, No.2, February 2003, pp. 218-233 https://doi.org/10.1109/TPAMI.2003.1177153
  6. Wen Yi and Rama Chellappa, 'SFS Based View Synthesis for Robust Face Recognition,' Proc. of Fourth IEEE International Conference on Automatic Face and Gesture Recognition, Pages:285-292, March 2000 https://doi.org/10.1109/AFGR.2000.840648
  7. V. lanz, S. Romdhani and T. Vetter, 'Face identification across different poses and illuminations with a 3D morphable model,' Fifth IEEE International Conference on Automatic Face and Gesture Recognition, Pages:192-197, May 2002 https://doi.org/10.1109/AFGR.2002.1004155
  8. Jobson D.J., Rahman Z. and Woodell G.A., 'A multi scale retinex for bridging the gap between color images and the human observation of scenes,' IEEE Trans. on Image Processing, Vol. 6, pp. 965-976, July 1997 https://doi.org/10.1109/83.597272
  9. R. Gross and V. Brajovic, 'An Image Preprocessing Algorithm for Illumination Invariant Face Recognition,' 4th Int. Conf. on A VBPA, June, 2003
  10. Wen Gao, Bo Cao, Shiguang Shan, Delong Zhou, Xiaohua Zhang and Debin Zhao, 'The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations,' JDL-TR-04-FR-001, May 2004
  11. Simon Haykin, 'Neural Networks - A Comprehensive Foundation-2nd Edition,' Prentice Hall