Image segmentation and analysis via multiscale gradient watershed hierarchies

Gauch, John M.

doi:10.1109/83.736688

Cited by 249 publications

(116 citation statements)

References 42 publications

Supporting

Mentioning

109

Contrasting

Unclassified

Order By: Relevance

“…Unlike work aimed to segment images, see [15,10] for example our watersheds are computed directly from the intensity image, not from it derivative magnitude. Our grouping method is based on the work of Haris et al [15].…”

Section: Grouping Methodsmentioning

confidence: 99%

“…They adopt a hierarchical agglomerative clustering approach which terminates when the cost of grouping any pair rises above a threshold (which varies from image to image). Gauch [10] also segments by clustering watersheds of the derivative image, filtering the image in scale space to do so. Malpica et al [17] build on the work of Haris et al [15] by introducing multidimensional description for regions, rather than the scalar gray level.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning object classes from structure

Xiao¹,

Song²,

Hall³

2007

Procedings of the British Machine Vision Conference 2007

View full text Add to dashboard Cite

The problem of identifying the class of an object from its visual appearance has received significant attention recently. Most of the work to date is premised on photometric measures, often building codebooks made from interest regions. All of it has been tested only on photographs, so far as we know. Our approach differs in two significant ways. First, we do not build a codebook of interest regions but instead make use of a hierarchical description of an image based on a watershed transform. Root nodes in the hierarchy are putative objects to be classified. Second, we classify these putative objects using a vector of fixed length that represents the structure of the hierarchy below the node. This allows us to classify not just photographs, but also paintings and drawings of visual objects.

show abstract

Section: Grouping Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning object classes from structure

Xiao¹,

Song²,

Hall³

2007

Procedings of the British Machine Vision Conference 2007

View full text Add to dashboard Cite

show abstract

“…[22], used a clustering approach to obtain an initial region, estimates the real boundary extrapolating and linking those detected points.…”

Section: Work On Breast Region Segmentationmentioning

confidence: 99%

A Method For Improve Preprocessing Images Mammography

Dehghani¹,

Dezfooli²

2011

IJIET

View full text Add to dashboard Cite

Abstract-A great volume of mammography images have dark background, these parts are not important in processing of mammography images. We can decrease the picture size and increase the processing speed by deleting these parts. Some parts of images have some notes and labels which consist of information like name, family, hospital's seal, date and…. It is better to omit these labels before processing since they are bright; the same as gray level of some breast tissues and have the same gray level. In the other way it is better to limit processing to the breast region and omit excessive parts. Previous studies over breast tissues show that if the considered region has not been marked clearly, it will influence characteristics and will not give the desired result. For obtaining this aim first find the main breast region, and then omit excessive parts to obtain processing result accurately and rapidly. The work that we do in this paper is introduced in three phases. The first phase is omitting the excessive image parts which are in the two sides of the image; we do this work by the usage of the pixels brightness. The second phase is the distinction of the breast direction and put all images in one direction; we do this work by the usage of threshold limit of gray level of the two halves of the image. The third phase is the breast region segmentation from the background; we do this work by the usage of series of point operations and the growing region method and the result has been reported to 99%.

show abstract

“…To avoid over segmentation a single marker for each object of interest has to be selected [17].The selection of adequate markers on these kinds of images is a painful and sometimes fruitless task. Hence, the experienced observer defines markers in a semiautomatic way [18] [19] [20]. The automatic determination of markers is still a difficult goal to achieve.…”

Section: Introductionmentioning

confidence: 99%

Application of Segmentation Techniques on Atherosclerosis Images

Baldevbhai¹

2013

IOSR-JVSP

View full text Add to dashboard Cite

Image segmentation and analysis via multiscale gradient watershed hierarchies

Cited by 249 publications

References 42 publications

Learning object classes from structure

Learning object classes from structure

A Method For Improve Preprocessing Images Mammography

Application of Segmentation Techniques on Atherosclerosis Images

Contact Info

Product

Resources

About