Segmentation using a region-growing thresholding

Mancaş, Matei; Gosselin, Bernard; Macq, Benoı̂t

doi:10.1117/12.587995

Cited by 89 publications

(45 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By applying further MATLAB algorithms we can detect the size of this tumor. Since the intensity of tumor is much more than background of image that's the only reason tumor can be detected in MRI (Mancas, Gosselin et al 2005).For now we can locate the tumor in image precisely.…”

Section: Figure 5 Final Segmented Imagementioning

confidence: 91%

Brain Tumor Extraction from MRI Images using MATLAB

Ijaz¹,

Jamil

Gilani

2017

IJMUE

View full text Add to dashboard Cite

show abstract

Section: Figure 5 Final Segmented Imagementioning

confidence: 91%

Brain Tumor Extraction from MRI Images using MATLAB

Ijaz¹,

Jamil

Gilani

2017

IJMUE

View full text Add to dashboard Cite

show abstract

“…We also mentioned the road extraction result using aerial RGB images in the last row. The proposed method, IMoRaTa, is compared to other methods, such as HFALs 7) , Region Growing (RG) 11) , Mean-shift and Voronoi Diagram segmentation 8) . For the aerial RGB images, we performed a road extraction based-on Region Growing method.…”

Section: Resultsmentioning

confidence: 99%

[Paper] Urban Road Extraction Based-on Morphological Operations and Radon Transform on DSM Data

Herumurti

Uchimura

Koutaki

et al. 2014

MTA

View full text Add to dashboard Cite

The main problem in extracting a road in an urban area from an aerial photo is the shadow cast by buildings.Because of this, we use Digital Surface Model (DSM) data, which are based-on the elevation of land surfaces. The problems associated with DSM data is non-road area with similar elevations like parking places, parks and so on. In this work, we propose a method to perform road filtering using Radon transform and morphological operations. The initial road is the result of intensity enhancement and instantaneous, simple thresholding. The road filter performs an opening operation on the initial road with a line shape structuring element, where the line orientation is obtained from the Radon Transform. Finally, the road is constructed based on B-Spline from the extracted road skeleton. The experimental result shows that the proposed method improved the quality and the accuracy average within an acceptable time.

show abstract

“…Region-growing segmentation clusters adjacent cells if they have similar attributes. The segmentation process starts with a number of seed points that are randomly sampled, statistically determined or specified by the user (Mancas et al, 2005;Thakur and Anand, 2005). The advantage of using randomly-sampled seed points is that the procedure is autonomous and requires no input from the user.…”

Section: Mrsmentioning

confidence: 99%

A comparison of land unit delineation techniques for land evaluation in the Western Cape, South Africa

Niekerk

2010

Land Use Policy

View full text Add to dashboard Cite

Land evaluation, an integral part of land use planning, has been established as one of the preferred methods to support sustainable land use management. In essence, land evaluation aims to compare and match each potential land use with the properties of individual parcels of land, also called land units. A land unit is an area that is, according to predetermined properties, different from the surrounding land and can be assumed to have homogeneous land properties (e.g. climate, soils, cover). Land components (also called landform elements, terrain units or land surface segments) are often used as land units, mainly because their boundaries frequently coincide with transitions in environmental conditions. Although land components have traditionally been delineated by studying topographical maps, interpreting aerial photographs and making field measurements, such manual mapping techniques are very time-consuming and subjective. Land component maps can be generated more objectively and faster by using computer algorithms. This paper compares the maps produced by three algorithms, namely the automated land component mapper (ALCoM), the iterative self-organizing data analysis technique algorithm (ISODATA) and multi-resolution image segmentation (MRS), to determine which technique produces the most homogenous and morphologically-representative land components for an area in the Western Cape province of South Africa. The results revealed that the three methods produced significantly different land component maps. While ISODATA's units were relatively homogenous, their boundaries rarely followed morphological discontinuities. ALCoM performed better in delineating land components along terrain discontinuities, but produced relatively heterogeneous land components. Overall, MRS performed consistently well and was significantly more sensitive to morphological discontinuities than the other two methods tested. Land use managers should, however, use MRS with care as more research is needed to determine what effect its different input parameters have on land unit boundaries.

show abstract

Segmentation using a region-growing thresholding

Cited by 89 publications

References 4 publications

Brain Tumor Extraction from MRI Images using MATLAB

Brain Tumor Extraction from MRI Images using MATLAB

[Paper] Urban Road Extraction Based-on Morphological Operations and Radon Transform on DSM Data

A comparison of land unit delineation techniques for land evaluation in the Western Cape, South Africa

Contact Info

Product

Resources

About