Computing the &amp;#x003B1;-channel with probabilistic segmentation for image colorization

Dalmau, Oscar; Rivera, Mariano; Mayorga, P.

doi:10.1109/iccv.2007.4409120

Cited by 13 publications

(20 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The columns from (b) to (e) are the results of using [13], the proposed method, [3] and [30], respectively. We include the results of using [3,30] for comparison, since they also generate blending weights for colourisation, as mentioned in Section 1. The images for colourisation are, from top to down, 256 × 256 peppers, horses, butterfly, flowers, arches and 300 × 400 taros.…”

Section: Resultsmentioning

confidence: 99%

“…By doing so, our method can respond quickly to the user demand for stroke editing. The concept of generating blending weights for colourisation was also used in [3,30]. They have demonstrated very good colourisation results and shown that it was easy to change colours, extract objects for partial colourisation etc., by virtue of the blending weights.…”

Section: Introductionmentioning

confidence: 98%

“…The information must be gathered from strokes, which are therefore necessary to be across intentionally chosen regions (position sensitive) and of the large size (size sensitive) much exceeding the requirement to indicate an object. Our method is not only free of the above limitations of [3,30], but also capable of fast re-colouring adapting to adding or deleting a stroke.…”

Section: Introductionmentioning

confidence: 99%

“…The technique [3] is distance based and has the limitation as mentioned above. In [30], the blending weights were modelled as Markov random fields and found by optimising an objective function. The optimisation is time-consuming.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Blending-weight diffusion for image colourisation

Chung

2012

IET Image Processing

View full text Add to dashboard Cite

An image colourisation method based on diffusion of colour-blending weights is presented. The authors propose to use reciprocal function for smoothness measurement to determine the priority order of colour propagation in image colourisation. The reciprocal measurement can improve the recent exponential-measurement-based propagation, which has a trend towards being greedy for smooth pixels, and is likely to cause wrong boundaries nearby the object juncture joining the grey levels without significant difference. In addition, the proposed method uses the blending-weight diffusion instead of the direct propagation of chrominance values. By doing so, it can respond quickly to the user demand for stroke editing. Experimental results show that compared with the exponential-measurement-based propagation, the proposed method filled colours more precisely in the positions representing real object surfaces, and saved 85.92% of computation time for adding a stroke and 98.60% for deleting a stroke, to an illustrative image. Compared with two conventional techniques which also implement-blending weights, this method can provide the blending weights for acceptable colourisation by using the economical strokes which positions are less constrained and which sizes are reduced.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Blending-weight diffusion for image colourisation

Chung

2012

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…For a comprehensive introduction to the topic we refer to the recent survey by Nieuwenhuis et al [12]. Circumventing the hardness, several approaches relax the labeling integrality condition, resulting in linear, e.g., in Kleinberg and Tardos [8] and in Werner [20], or quadratic programs, e.g., in DalmauCedeno et al [5] and in Rivera et al [15,16]. Although all relaxations can be solved in c 2013.…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Subdivision Scheme for Quadratic Programming in Multi-Label Image Segmentation

Rak¹,

König²,

Tönnies³

2013

Procedings of the British Machine Vision Conference 2013

View full text Add to dashboard Cite

We address the problem of efficient, globally optimal multi-label image segmentation. Transforming the discrete labeling problem into a [0, 1]-relaxed binary quadratic program we are able to solve arbitrary convex quadratic labeling tasks in polynomial time. Although this guarantees efficiency in a theoretical sense, large-scale quadratic programs that arise from relaxation can rarely be used for image segmentation directly. We treat this issue by an adaptive domain subdivision scheme, reducing the problem to a short sequence of spatially smoothed medium-scale programs, which subsequently better approximate the large-scale program. Our scheme is globally optimal in terms of the approximated problem. It allows for near-interactive multi-label segmentation and is highly accurate even in the presence of strong noise.

show abstract

Recoloring textile fabric images based on improved fuzzy clustering

Zou

Shen

et al. 2016

Color Research & Application

View full text Add to dashboard Cite

This article proposes a new recoloring method for textile fabric images based on improved fuzzy local information c-means (FLICM) clustering. In the clustering algorithm, the fuzzy factor was modified so that it can produce reliable segmentation in areas with rich details. With the obtained cluster labels and pixel-wise memberships, the color of each pixel is modeled as the linear combination of the two most dominant colors. The recoloring process was then conducted by replacing the specified dominant color with user-provided target colors. Experimental results showed that the proposed method can produce natural and faithful color appearance on both printed and yarn-dyed fabric images, and outperforms the state-of-the-art.

show abstract

Computing the α-channel with probabilistic segmentation for image colorization

Cited by 13 publications

References 26 publications

Blending-weight diffusion for image colourisation

Blending-weight diffusion for image colourisation

An Adaptive Subdivision Scheme for Quadratic Programming in Multi-Label Image Segmentation

Recoloring textile fabric images based on improved fuzzy clustering

Contact Info

Product

Resources

About