Color Image Segmentation Using Adaptive GrowCut Method

Basavaprasad, B; Hegadi, Ravindra S.

doi:10.1016/j.procs.2015.03.153

Cited by 12 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of pixels associated to each region adjacency graph (RAG) are represented as node, which indicates the size of initial over segmented regions and they must be same as the reference node. RAGbased segmentation approach is hierarchical and the number of final regions are controlled manually according to the segmentation requirements [13][14][15][16][17][18][19][20]. In graph partition problem, objects which are extracted not necessarily connected and the set of edge weights reflects the similarity between each pair of related regions or nodes vi and vj.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…In the past few decades, a variety of methods, such as statistical region merging (SRM), dynamic region merging (DRM), split and merge, similarity based merging, hierarchical merging, boundary based merging etc., have been developed to eliminate the segmentation errors [10][11][12][13][14][15].Here, image regions can be described in terms of shape, size, color, texture etc., and utilization of these kinds of parameters in region based merging techniques will enhance the efficiency of the method and improve the segmentation patterns [17][18][19][20], which are purely based on probabilistic and some logical criteria. In case, to determine the similarity between the two regions depends on pixel mean, variance and gray level, also which is based on Euclidean distance and log-likelihood ratio are wellknown statistics for region evaluation.…”

Section: Segmentation and Region Mergingmentioning

confidence: 99%

“…However, there are many challenging concerns affecting performances of these techniques. Therefore, successful image segmentation depends on reliability and accuracy of segmentation method [11], [14], [20][21][22][23][24][25][26].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Image Segmentation Technique with N-L Means Filter Using Region Merging Strategy

H N,

Jagadale,

2023

Int J Res Rev

View full text Add to dashboard Cite

Image segmentation is a branch of digital image processing which emphases on splitting an image into different fragments according to their features. This work proposes a novel image segmentation technique using fast non local (N-L) means filter with region merging approach. Here, a random noise is added to the original image and discrete wavelet transform (DWT) is applied to separate the low and high frequency bands of the digital image. The low frequency component is subjected to a fast N-L means filter and the filtered image is segmented by graph-based segmentation technique. Here, these segmented image regions are merged to reduce the over segmentation patterns. The detailed coefficients of the image component are treated with soft threshold filter to reduce the residual noise. Finally merged image is combined with preserved edge features at wavelet projection resulting in better segmented image. The results are compared with some of the best methods available in literature and are found to be significantly better. Keywords: Discrete wavelet transform (DWT), fast NL-means filter, graph-based segmentation, boundary based hierarchical region merging, soft-thresholding, peak signal to noise ratio (PSNR).

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Segmentation and Region Mergingmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Image Segmentation Technique with N-L Means Filter Using Region Merging Strategy

H N,

Jagadale,

2023

Int J Res Rev

View full text Add to dashboard Cite

show abstract

“…Nevertheless, minimum cut constantly tries to cut small collection of isolated nodes as the cut which is shown in (3) does not contain any information of intragroup [7]. [7].…”

Section: International Journal Of Computer Applications (0975 -8887) mentioning

confidence: 99%

Image Segmentation using MSNCut Algorithm

Basavaprasad¹

2017

IJCA

View full text Add to dashboard Cite

In this paper a hybrid technique for the segmentation of image has been proposed and it is named as MSNCut technique. Here image segmentation is the process of dividing the given image into number of regions that possess similar properties such as color, texture and intensity which are useful for the image analysis. The image is generic here, in other words image may be tree, river, building, medical or any general image. In this proposed method first the input image is preprocessed by mean shift algorithm to divide it into its constituent regions. Then the resultant image is represented as a bi-partite graph and finally the resultant graph (image) is processed under normalized cut to classify the image into meaningful classes.

show abstract

“…The algorithm stops when all the pixels, which have predefined similarity with seed points, have been marked. An adaptive grow cut [10] method was later proposed as an improved algorithm for 2D general image segmentation which uses the output of GrowCut as the input of a k-means clustering.…”

Section: Introductionmentioning

confidence: 99%

3D Segmentation of Residual Thyroid Tissue Using Constrained Region Growing and Voting Strategies

Bao

Zheng

et al. 2017

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

View full text Add to dashboard Cite

The measurement of residual thyroid tissue after thyroidectomy is crucial for the precise quantification of thyroid cancer treatment. Accurate residual thyroid tissue segmentation from CT images is challenging due to the indistinct tissue boundary. We propose a vote-in & vote-out region propagation model for residual thyroid tissue segmentation which incorporates global and local constraints and two voting strategies. The constraints were initially estimated from the given seeds and adaptively adjusted during the propagation process. The voting strategies were developed to decrease the opportunities of merging unexpected voxels around the uncertain boundaries. The experiment results over clinical patient studies demonstrated that the proposed method significantly improved the segmentation accuracy in terms of spatial overlap and shape similarity. Our method achieved an average Volume Overlap Error of 14.44±7.55 %, Relative Volume Difference of 9.42±20.31 %, Average Surface Distance of 0.12±0.05 mm and Maximum Surface Distance of 1.34±0.62 mm, with an average computation time of 2.68 seconds.

show abstract

Color Image Segmentation Using Adaptive GrowCut Method

Cited by 12 publications

References 7 publications

A Novel Image Segmentation Technique with N-L Means Filter Using Region Merging Strategy

A Novel Image Segmentation Technique with N-L Means Filter Using Region Merging Strategy

Image Segmentation using MSNCut Algorithm

3D Segmentation of Residual Thyroid Tissue Using Constrained Region Growing and Voting Strategies

Contact Info

Product

Resources

About