Unsupervised MRI segmentation of brain tissues using a local linear model and level set

Rivest-Hénault, David; Cheriet, Mohamed

doi:10.1016/j.mri.2010.08.007

Cited by 26 publications

(21 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The derivation of the local linear force is briefly introduced below. For more details, we refer the interested reader to [20]. Table 1 The details of the four scenarios used to evaluate the performance on synthesized degradation…”

Section: Local Linear Regional Forcementioning

confidence: 99%

“…(5) in [42]. Following this scheme, the force that tends to minimize (9) is derived by keeping the local linear models L S and L B fixed and by computing the gradient descent equation of (9) with respect to φ [20,34]:…”

Section: Degradation Typementioning

confidence: 99%

“…Then, the stroke map is eroded by updating the 4 Numerically, this is done by using the function bwdist of Matlab. level set function φ with (4) subject to (20) to propagate the interface. Here, β and ν are positive real numbers that are used to balance the effects of the three forces.…”

Section: Second Step: Stroke Map Erosionmentioning

confidence: 99%

“…Moreover, as a new contribution, and despite a high level of possible dissimilarity in color/intensity, we use the gradient not only for locating the edges, but also to follow the ink along the strokes. Its use, made possible using local linear modeling [20], is the key concept in the recovery of cuts and weak strokes and plays a major role in higher-level processes [6].…”

Section: Introductionmentioning

confidence: 99%

“…1 However, this is the first time that a comprehensive description of the method is published. The local linear regional force used in the proposed model has been introduced by some of us in [20]. However, this work is based on widely different premises.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A local linear level set method for the binarization of degraded historical document images

Rivest-Hénault

Moghaddam

Cheriet

2011

IJDAR

Self Cite

View full text Add to dashboard Cite

Document image binarization is a difficult task, especially for complex document images. Nonuniform background, stains, and variation in the intensity of the printed characters are some examples of challenging document features. In this work, binarization is accomplished by taking advantage of local probabilistic models and of a flexible active contour scheme. More specifically, local linear models are used to estimate both the expected stroke and the background pixel intensities. This information is then used as the main driving force in the propagation of an active contour. In addition, a curvature-based force is used to control the viscosity of the contour and leads to more natural-looking results. The proposed implementation benefits from the level set framework, which is highly successful in other contexts, such as medical image segmentation and road network extraction from satellite images. The validity of the proposed approach is demonstrated on both recent and historical document images of various types and languages. In addition, this method was submitted to the Document Image Binarization Contest (DIBCO'09), at which it placed 3rd.

show abstract

Section: Local Linear Regional Forcementioning

confidence: 99%