Weighted Color and Texture Sample Selection for Image Matting

Varnousfaderani, Ehsan Shahrian; Rajan, Dinesh

doi:10.1109/tip.2013.2271549

Cited by 47 publications

(34 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…9(b). The presence of another plant in the background causes the texture to misconstrue the foreground as background in [2], [21] as seen in Fig. 9(c,d) of the plant image.…”

Section: Resultsmentioning

confidence: 99%

“…11 shows the visual quality of the mattes obtained without using pre and post-processing steps. As sampling methods use a pairwise approach and ignore correlation among neighbors during alpha estimation, many discontinuities are present in the initial mattes of [2], [21] (Fig. 11(b,c)).…”

Section: Resultsmentioning

confidence: 99%

“…Such approaches fail to produce a good matte when the F and B samples are nearby in the color space, or when the collected sample set fails to correlate with the actual color at the unknown pixel. Texture is used in addition to color as a feature for matting in [1], [21] to address the problem of overlap in color distributions of F and B. Chen et al [3] formulate the sampling-based alpha estimate in [11], smoothness Laplacian, along with locally linear embedding as a weighted graph and obtain a closedform solution for the matte. Zhang et al [22] treat matting as a supervised learning problem and use support vector regression to learn the alpha-feature model from known samples.…”

Section: Related Workmentioning

confidence: 99%

“…MATLAB implementations were evaluated on a PC running Intel Xeon 3.2 GHz processor. Sparse coding is able to generate faster estimates from the same set of F and B samples as opposed to an exhaustive pair search followed by conventional sampling methods [2], [21] leading to better runtime performance. For the donkey image, the pre-processing and certainty estimation takes 32 seconds, the sparse coded matte estimation is completed in just 41 seconds followed by the graph-based optimization in 9 seconds.…”

Section: Runtime Performancementioning

confidence: 99%

See 3 more Smart Citations

Sparse Coding for Alpha Matting

Johnson

Varnousfaderani

Cholakkal

et al. 2016

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Abstract-Existing color sampling based alpha matting methods use the compositing equation to estimate alpha at a pixel from pairs of foreground (F) and background (B) samples. The quality of the matte depends on the selected (F,B) pairs. In this paper, the matting problem is reinterpreted as a sparse coding of pixel features, wherein the sum of the codes gives the estimate of the alpha matte from a set of unpaired F and B samples. A non-parametric probabilistic segmentation provides a certainty measure on the pixel belonging to foreground or background, based on which a dictionary is formed for use in sparse coding. By removing the restriction to conform to (F,B) pairs, this method allows for better alpha estimation from multiple F and B samples. The same framework is extended to videos, where the requirement of temporal coherence is handled effectively. Here, the dictionary is formed by samples from multiple frames. A multi-frame graph model, as opposed to a single image as for image matting, is proposed that can be solved efficiently in closed form. Quantitative and qualitative evaluations on a benchmark dataset are provided to show that the proposed method outperforms current state-of-the-art in image and video matting.

show abstract

“…9(b). The presence of another plant in the background causes the texture to misconstrue the foreground as background in [2], [21] as seen in Fig. 9(c,d) of the plant image.…”

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Runtime Performancementioning

confidence: 99%

See 2 more Smart Citations

Sparse Coding for Alpha Matting

Johnson

Varnousfaderani

Cholakkal

et al. 2016

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…1.8 shows a group of matting results obtained by five typical matting algorithms-closed-form [25], KNN [26], weighted color [27], comprehensive sampling [28], and learning based [29] matting methods. Although these methods are the state-of-the-art algorithms that solve the matting problem from different aspects, the results presented here are far from perfect.…”

Section: Problem Statementmentioning

confidence: 99%

Chroma keying based on stereo images

Chu¹,

Zhao²

2017

2017 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

View full text Add to dashboard Cite

This thesis proposes a novel chroma keying method based on stereo images, which can be applied to post-process the alpha matte generated by any existing matting approach.Given a pair of stereo images, a new matting Laplacian matrix is constructed based on the affinities between matching pixels and their neighbors from two frames. Based on the new matting Laplacian matrix, a new cost function is also formulated to estimate alpha values of the reference image through the propagation between stereo images.To avoid over-smoothing during propagation, a united window with an adaptive size is used in the Laplacian matrix to overcome the dilemma between the inadequate propagation caused by small size windows and the over-smoothness triggered by large size windows.Moreover, an optional pre-processing is presented. When it comes to the foreground object with strong reflection, based on the histogram statistics, the initial alpha values of the particular unknown pixels can be refined before the proposed post-processing method. In addition, a ground truth generation method is developed for chroma keying.Visual quality comparisons between the original mattes produced by existing approaches and the results post-processed by the proposed method show that our method can effectively enhance the quality of alpha mattes. Also, objective quality comparisons demonstrate that our proposed algorithm can significantly reduce the errors of alpha mattes.ii Acknowledgements I would like to thank my supervisor, Professor Jiying Zhao, for his guidance and providing me the chance to conduct the research on chroma keying. I greatly appreciate his patience and confidence in my research work.

show abstract

Improvement of thin retinal vessel extraction using mean matting method

Sathananthavathi¹,

Indumathi²,

Mahiya³

et al. 2021

Int J Imaging Syst Tech

View full text Add to dashboard Cite

In this paper, a new mean matting method based on mean correlation is proposed to extract thin blood vessels precisely. The proposed algorithm is the combination of both supervised and unsupervised method. The supervised methodology performs well in extracting thick blood vessels; however, thin vessels are not precisely extracted. Even the capability of unsupervised method is better in extracting thin vessels; it has some artifacts in the output. The proposed method combines the advantages of both supervised and unsupervised method to extract vessel regions more precisely irrespective of their thickness.Using supervised methodology, thick blood vessels are extracted by training the classifier with the significant features describing the vessel regions. Trimap is generated on the unsupervised output and mean correlation is computed for all unknown pixels in the trimap to classify those pixels into vessels or background. The proposed matting method has less computational complexity compared to other existing matting methods. The performance of the proposed method is evaluated in detail on DRIVE and STARE datasets.

show abstract

Weighted Color and Texture Sample Selection for Image Matting

Cited by 47 publications

References 12 publications

Sparse Coding for Alpha Matting

Sparse Coding for Alpha Matting

Chroma keying based on stereo images

Improvement of thin retinal vessel extraction using mean matting method

Contact Info

Product

Resources

About