A Variational Framework for Retinex

International Journal of Computer Vision - Tập 52 Số 1 - Trang 7-23 - 2003
Kimmel, Ron1, Elad, Michael2, Shaked, Doron3, Keshet, Renato3, Sobel, Irwin4
1Computer Science Department, Technion—I.I.T., Technion City, Haifa, Israel
2The Computer Science Department, Stanford University, Stanford, USA
3HP Laboratories Israel, Technion City, Haifa, Israel
4HP Laboratories, Palo Alto, USA

Tóm tắt

Retinex theory addresses the problem of separating the illumination from the reflectance in a given image and thereby compensating for non-uniform lighting. This is in general an ill-posed problem. In this paper we propose a variational model for the Retinex problem that unifies previous methods. Similar to previous algorithms, it assumes spatial smoothness of the illumination field. In addition, knowledge of the limited dynamic range of the reflectance is used as a constraint in the recovery process. A penalty term is also included, exploiting a-priori knowledge of the nature of the reflectance image. The proposed formulation adopts a Bayesian view point of the estimation problem, which leads to an algebraic regularization term, that contributes to better conditioning of the reconstruction problem. Based on the proposed variational model, we show that the illumination estimation problem can be formulated as a Quadratic Programming optimization problem. An efficient multi-resolution algorithm is proposed. It exploits the spatial correlation in the reflectance and illumination images. Applications of the algorithm to various color images yield promising results.

Từ khóa


Tài liệu tham khảo

Barnard, K. and Funt, B. 1998. Investigations into multy-scale Retinex, In Proc. Color Imaging in Multimedia 98, Derby.

citation_title=Non-Linear Programming; citation_publication_date=1995; citation_id=CR2; citation_author=D.P. Bertsekas; citation_publisher=Athena Scientific

citation_journal_title=Computer Vision Graphics and Image Processing; citation_title=Boundary conditions of lightness computation in mondrian world; citation_author=A. Blake; citation_volume=32; citation_publication_date=1985; citation_pages=314-327; citation_id=CR3

citation_title=Visual Reconstruction; citation_publication_date=1987; citation_id=CR4; citation_author=A. Blake; citation_author=A. Zisserman; citation_publisher=The MIT Press

citation_journal_title=Numerische Mathematik; citation_title=The cascadic multigrid method for elliptic problems; citation_author=F. Bornemann, P. Deuflhard; citation_volume=75; citation_publication_date=1996; citation_pages=135-152; citation_id=CR5

citation_journal_title=J. Opt. Soc. Am. A; citation_title=Analysis of the Retinex theory of color vision; citation_author=D.H. Brainard, B. Wandell; citation_volume=3; citation_publication_date=1986; citation_pages=1651-1661; citation_id=CR6

citation_journal_title=IEEE Trans. on ASSP; citation_title=Digital image color processing within the framework of a human visual system; citation_author=O.D. Faugeras; citation_volume=27; citation_publication_date=1979; citation_pages=380-393; citation_id=CR7

Frankle, J. and McCann, J. 1983. Method and apparatus for lightness imaging, US Patent no. 4, 384,336.

Funt, B.V., Ciurea, F., and McCann, J. 2000. Retinex in Matlab. In Proc. of IS&T/SID Eighth Color Imaging Conference, pp. 112– 121.

Funt, B.V., Drew, M.S., and Brockington, M. 1992. Recovering shading from color images. In Proc. European Conference on Computer Vision (ECCV'92), pp. 124–132.

citation_journal_title=IEEE Trans. on Pattern Analysis ans Machine; citation_title=Stochastic relaxation, Gibbs distribution, and the Bayesian restoration of images; citation_author=S. Geman, D. Geman; citation_volume=6; citation_publication_date=1984; citation_pages=721-741; citation_id=CR11

citation_journal_title=Computer Graphics and Image Processing; citation_title=Determining lightness from an image; citation_author=B.K.P. Horn; citation_volume=3; citation_publication_date=1974; citation_pages=277-299; citation_id=CR12

citation_journal_title=IEEE Trans. on Image Proc.; citation_title=Properties and performance of the center/surround Retinex; citation_author=D.J. Jobson, Z. Rahman, G.A. Woodell; citation_volume=6; citation_publication_date=1997; citation_pages=451-462; citation_id=CR13

Jobson, D.J., Rahman, Z., and Woodell, G.A. 1997b. A multiscale Retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans. on Image Proc., 6.

Kimmel, R., Elad, M., Shaked, D., Keshet, R., and Sobel, I. 1999. A variational framework for Retinex. Hewlett Packard Laboratories TR no. HPL-1999-151.

citation_title=Iterative Identification and Restoration of Images; citation_publication_date=1991; citation_id=CR16; citation_author=R.L. Lagendijk; citation_author=J. Biemond; citation_publisher=Kluwer Academic Publishing

citation_journal_title=Sci. Amer.; citation_title=The Retinex theory of color vision; citation_author=E.H. Land; citation_volume=237; citation_publication_date=1977; citation_pages=108-128; citation_id=CR17

citation_journal_title=Proc. Nat. Acad. Sci. USA; citation_title=Recent advances in the Retinex theory and some implications for cortical computations: Color vision and the natural image; citation_author=E.H. Land; citation_volume=80; citation_publication_date=1983; citation_pages=5163-5169; citation_id=CR18

citation_journal_title=Proc. Nat. Acad. Sci. USA; citation_title=An alternative technique for the computation of the designator in the Retinex theory of color vision; citation_author=E.H. Land; citation_volume=83; citation_publication_date=1986; citation_pages=3078-3080; citation_id=CR19

citation_journal_title=J. Opt. Soc. Am.; citation_title=Lightness and the retinex theory; citation_author=E.H. Land, J.J. McCann; citation_volume=61; citation_publication_date=1971; citation_pages=1-11; citation_id=CR20

citation_title=Linear and Non-Linear Programming; citation_publication_date=1987; citation_id=CR21; citation_author=D.G. Luenberger; citation_publisher=Addison-Wesley

citation_journal_title=J. of the American Statistical Assoc.; citation_title=Probabilistic solution for ill-posed problems in computational vision; citation_author=J. Marroquin, J. Mitter, T. Poggio; citation_volume=82; citation_publication_date=1987; citation_pages=76-89; citation_id=CR22

McCann, J. 1999. Lessons learned from mondrians applied to real images and color gamuts. In Proc. IS&T/SID 7th Color Imaging Conference, pp. 1–8.

citation_title=Digital Signal Processing; citation_publication_date=1975; citation_id=CR24; citation_author=A.V. Oppenheim; citation_author=R.W. Schafer; citation_publisher=Prentice Hall

citation_title=Probability, Random Variables, and Stochastic Processes; citation_publication_date=1991; citation_id=CR25; citation_author=A. Papoulis; citation_publisher=McGraw-Hill

citation_journal_title=Proc. of the IEEE; citation_title=Image processing in the context of a visual model; citation_author=T.G. Stockham; citation_volume=60; citation_publication_date=1972; citation_pages=828-842; citation_id=CR26

citation_journal_title=IEEE Trans. on PAMI; citation_title=Image analysis using multigrid relaxation methods; citation_author=D. Terzopoulos; citation_volume=8; citation_publication_date=1986; citation_pages=129-139; citation_id=CR27

Thông tin
Thông tin xuất bản

International Journal of Computer Vision

Tập 52 Số 1

7-23

Thông tin tác giả