Recovering shading from color images

Funt, Brian V.; Drew, Mark S.; Brockington, Michael

doi:10.1007/3-540-55426-2_15

Cited by 96 publications

(78 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the re-integration step, application of a curl-correction method [12] to ensure integrability would likely be of benefit. Also, if may be the case that consideration of a separate shadow-edge map for x and y could be useful, since in principle these are different.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Intrinsic Images by Entropy Minimization

Finlayson

Drew

2004

Lecture Notes in Computer Science

Self Cite

194

195

View full text Add to dashboard Cite

Abstract.A method was recently devised for the recovery of an invariant image from a 3-band colour image. The invariant image, originally 1D greyscale but here derived as a 2D chromaticity, is independent of lighting, and also has shading removed: it forms an intrinsic image that may be used as a guide in recovering colour images that are independent of illumination conditions. Invariance to illuminant colour and intensity means that such images are free of shadows, as well, to a good degree. The method devised finds an intrinsic reflectivity image based on assumptions of Lambertian reflectance, approximately Planckian lighting, and fairly narrowband camera sensors. Nevertheless, the method works well when these assumptions do not hold. A crucial piece of information is the angle for an "invariant direction" in a log-chromaticity space. To date, we have gleaned this information via a preliminary calibration routine, using the camera involved to capture images of a colour target under different lights. In this paper, we show that we can in fact dispense with the calibration step, by recognizing a simple but important fact: the correct projection is that which minimizes entropy in the resulting invariant image. To show that this must be the case we first consider synthetic images, and then apply the method to real images. We show that not only does a correct shadow-free image emerge, but also that the angle found agrees with that recovered from a calibration. As a result, we can find shadow-free images for images with unknown camera, and the method is applied successfully to remove shadows from unsourced imagery.

show abstract

Section: Discussionmentioning

confidence: 99%

“…(7), (8), and (10). For each angle, we project the log-chromaticity, and then determine the entropy (12). However, the nature of the data, for real images, presents an inherent problem.…”

Section: Algorithm Stepsmentioning

confidence: 99%

Intrinsic Images by Entropy Minimization

Finlayson

Drew

2004

Lecture Notes in Computer Science

Self Cite

194

195

View full text Add to dashboard Cite

show abstract

“…That is, the three color channels may be written as (1) This means that the different colors capture the change in material via (where stands for ) that multiplies the normalized shading image . The Mondriaan color image formation model [4] was used for color based segmentation [7] and shading extraction from color images [5]. Let us follow the above generalization of this model and assume that the material, and therefore the albedo, are the same within a given object in the image, e.g., , where is a given constant.…”

Section: Simple Color Image Formation Modelmentioning

confidence: 99%

Demosaicing: Image reconstruction from color CCD samples

Kimmel

1998

Computer Vision — ECCV'98

163

View full text Add to dashboard Cite

Abstract-A simplified color image formation model is used to construct an algorithm for image reconstruction from CCD sensors samples. The proposed method involves two successive steps. The first is motivated by Cok's template matching technique, while the second step uses steerable inverse diffusion in color. Classical linear signal processing techniques tend to oversmooth the image and result in noticeable color artifacts along edges and sharp features. The question is how should the different color channels support each other to form the best possible reconstruction. Our answer is to let the edges support the color information, and the color channels support the edges, and thereby achieve better perceptual results than those that are bounded by the sampling theoretical limit.Index Terms-Color enhancement, image reconstruction, multichannel nonlinear image processing, steerable inverse diffusion.

show abstract

“…Another common approach is to use colour as a key for identifying illumination gradients, based on the assumption that hue is illumination invariant (see for example, [5], [6] and [7]). An illumination map can then be derived by reintegrating only those gradients that arise from illumination.…”

Section: Introductionmentioning

confidence: 99%

Correlation-Based Intrinsic Image Extraction from a Single Image

Jiang

Schofield

Wyatt

2010

Computer Vision – ECCV 2010

View full text Add to dashboard Cite

Abstract. Intrinsic images represent the underlying properties of a scene such as illumination (shading) and surface reflectance. Extracting intrinsic images is a challenging, ill-posed problem. Human performance on tasks such as shadow detection and shape-from-shading is improved by adding colour and texture to surfaces. In particular, when a surface is painted with a textured pattern, correlations between local mean luminance and local luminance amplitude promote the interpretation of luminance variations as illumination changes. Based on this finding, we propose a novel feature, local luminance amplitude, to separate illumination and reflectance, and a framework to integrate this cue with hue and texture to extract intrinsic images. The algorithm uses steerable filters to separate images into frequency and orientation components and constructs shading and reflectance images from weighted combinations of these components. Weights are determined by correlations between corresponding variations in local luminance, local amplitude, colour and texture. The intrinsic images are further refined by ensuring the consistency of local texture elements. We test this method on surfaces photographed under different lighting conditions. The effectiveness of the algorithm is demonstrated by the correlation between our intrinsic images and ground truth shading and reflectance data. Luminance amplitude was found to be a useful cue. Results are also presented for natural images.

show abstract

Recovering shading from color images

Cited by 96 publications

References 14 publications

Intrinsic Images by Entropy Minimization

Intrinsic Images by Entropy Minimization

Demosaicing: Image reconstruction from color CCD samples

Correlation-Based Intrinsic Image Extraction from a Single Image

Contact Info

Product

Resources

About