Efficient graph-based image segmentation via speeded-up turbo pixels

Çığla, Cevahir; Alatan, A. Aydın

doi:10.1109/icip.2010.5653963

Cited by 42 publications

(30 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Speeded-up Turbo Pixels (STP) algorithm is technique for superpixels generation based on K-means grouping algorithm [6]. This algorithm generates uniforms superpixels with low computational cost.…”

Section: Methodsmentioning

confidence: 99%

“…The images segmentation is an efficient area used in this application type, because it allows isolating regions in the image that have characteristics in common, helping to classify them according to the structures that compose them. For example, superpixels extraction techniques, based in k-means clustering algorithm, can be used to segment appropriately medical images with low computational cost [6,7,8].…”

Section: Introductionmentioning

confidence: 99%

“…To aid in the early detection of breast cancer, this paper presents the application of the Speeded-up Turbo Pixel (STP) algorithm [6], based on superpixels extraction, for the segmentation of mammography images, making possible the nodules detection. In this paper, the images are divided into groups of pixels with low computational cost, considering the application in high resolution images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Mammographic Images Segmentation using Superpixel

Botelho¹,

Tadeu²,

Henrique³

2018

IJCA

View full text Add to dashboard Cite

The images segmentation is a very important step for the area of image analysis and has the objective of separating regions of an image according to the objects represented in it. However, this is a challenging step in image processing area, since most traditional segmentation techniques have a high computational cost, which difficult their application in high resolution images. Based in this context, this paper proposes the use of the superpixels extraction technique, known as Speeded-up Turbo Pixels, to segment high resolution mammographic images with satisfactory processing time.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mammographic Images Segmentation using Superpixel

Botelho¹,

Tadeu²,

Henrique³

2018

IJCA

View full text Add to dashboard Cite

show abstract

“…Graph Cut segmentation is then formulated according to the watershed regions graph. Starting from a grid partition, [16] cluster image pixels by an iterative k-means algorithm augmented by color similarity and shape compactness criteria. The cluster graph is then partitioned based on color information yielding a coarse segmentation of the image.…”

Section: A Graph Cut In Segmentation and Its Complexitymentioning

confidence: 99%

Shortest-Path Constraints for 3D Multiobject Semiautomatic Segmentation Via Clustering and Graph Cut

Kéchichian

Valette

Desvignes

et al. 2013

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

To cite this version:Razmig Kéchichian, Sébastien Valette, Michel Desvignes, Rémy Prost. Shortest-path constraints for 3D multiobject semiautomatic segmentation via clustering and Graph Cut. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2013, 22 (11) Abstract-We derive shortest-path constraints from graph models of structure adjacency relations and introduce them in a joint centroidal Voronoi image clustering and Graph Cut multiobject semiautomatic segmentation framework. The vicinity prior model thus defined is a piecewise-constant model incurring multiple levels of penalization capturing the spatial configuration of structures in multiobject segmentation. Qualitative and quantitative analysis and comparison with a Potts prior-based approach and our previous contribution on synthetic, simulated and real medical images show that the vicinity prior allows for the correct segmentation of distinct structures having identical intensity profiles and improves the precision of segmentation boundary placement while being fairly robust to clustering resolution. The clustering approach we take to simplify images prior to segmentation strikes a good balance between boundary adaptivity and cluster compactness criteria furthermore allowing to control the trade-off. Compared to a direct application of segmentation on voxels, the clustering step improves the overall runtime and memory footprint of the segmentation process up to an order of magnitude without compromising the quality of the result.

show abstract

“…Uma vez que os pixels contidos no mesmo superpixel são considerados iguais por definição, primitivas de superpixels têm algumas vantagens sobre as primitivas de pixels, como eficiência computacional, já que o número de primitivas é reduzido no nível de superpixel. Isso traz grandes oportunidades para aliviar a complexidade de sistemas de Visão Computacional (Cuadros et al, 2012;Çigla e Alatan, 2010). Superpixels podem ser usados em uma grande variedade de aplicações: segmentação de imagens médicas (Wu et al, 2014), segmentação do céu em fotos de paisagem (sky segmentation) (Kostolansky, 2016), segmentação de movimento (motion segmentation) (Ayvaci e Soatto, 2009), segmentação de objetos em múltiplas classes (multi-class object segmentation) (Fulkerson et al , 2009a;Yang et al, 2012), detecção de objetos (object detection) (Shu et al, 2013), detecção de saliência espaço-temporal (spatiotemporal saliency detection) (Liu et al, 2014), rastreamento de alvos (target tracking) (Yang et al, 2014), estimativa de modelo corporal (body model estimation) e estimativa de profundidade (depth estimation) (Zitnick e Kang, 2007).…”

unclassified

IFT-SLIC: geração de superpixels com base em agrupamento iterativo linear simples e transformada imagem-floresta

Alexandre¹

View full text Add to dashboard Cite

Efficient graph-based image segmentation via speeded-up turbo pixels

Cited by 42 publications

References 9 publications

Mammographic Images Segmentation using Superpixel

Mammographic Images Segmentation using Superpixel

Shortest-Path Constraints for 3D Multiobject Semiautomatic Segmentation Via Clustering and Graph Cut

IFT-SLIC: geração de superpixels com base em agrupamento iterativo linear simples e transformada imagem-floresta

Contact Info

Product

Resources

About