Parallel Segmentation of Multi-Channel Images Using Multi-Dimentional Mathematical Morphology

2006 ◽  
pp. 270-291
Author(s):  
Antonio Plaza ◽  
Javier Plaza ◽  
David Valencia ◽  
Pablo Martiez
Keyword(s):  
Mathematical Morphology ◽  
Parallel Implementation ◽  
Region Growing ◽  
Large Data ◽  
Remotely Sensed ◽  
Morphological Operations ◽  
Remotely Sensed Data ◽  
Imaging Spectrometer ◽  
Seeded Region Growing ◽  
Multi Channel Imaging

Multi-channel images are characteristic of certain applications, such as medical imaging or remotely sensed data analysis. Mathematical morphology-based segmentation of multi-channel imagery has not been fully accomplished yet, mainly due to the lack of vector-based strategies to extend classic morphological operations to multidimensional imagery. For instance, the most important morphological approach for image segmentation is the watershed transformation, a hybrid of seeded region growing and edge detection. In this chapter, we describe a vector-preserving framework to extend morphological operations to multi-channel images, and further propose a fully automatic multi-channel watershed segmentation algorithm that naturally combines spatial and spectral/temporal information. Due to the large data volumes often associated with multi-channel imaging, this chapter also develops a parallel implementation strategy to speed up performance. The proposed parallel algorithm is evaluated using magnetic resonance images and remotely sensed hyperspectral scenes collected by the NASA Jet Propulsion Laboratory Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS).

Parallel Segmentation of Multi-Channel Images Using Multi-Dimensional Mathematical Morphology

2011 ◽  
pp. 321-340 ◽  
Author(s):  
Antonio Plaza ◽  
Javier Plaza ◽  
David Valencia ◽  
Pablo Martinez
Keyword(s):  
Mathematical Morphology ◽  
Parallel Implementation ◽  
Region Growing ◽  
Large Data ◽  
Remotely Sensed ◽  
Morphological Operations ◽  
Remotely Sensed Data ◽  
Imaging Spectrometer ◽  
Seeded Region Growing ◽  
Multi Channel Imaging

Multi-channel images are characteristic of certain applications, such as medical imaging or remotely sensed data analysis. Mathematical morphology-based segmentation of multi-channel imagery has not been fully accomplished yet, mainly due to the lack of vector-based strategies to extend classic morphological operations to multidimensional imagery. For instance, the most important morphological approach for image segmentation is the watershed transformation, a hybrid of seeded region growing and edge detection. In this chapter, we describe a vector-preserving framework to extend morphological operations to multi-channel images, and further propose a fully automatic multi-channel watershed segmentation algorithm that naturally combines spatial and spectral/temporal information. Due to the large data volumes often associated with multi-channel imaging, this chapter also develops a parallel implementation strategy to speed up performance. The proposed parallel algorithm is evaluated using magnetic resonance images and remotely sensed hyperspectral scenes collected by the NASA Jet Propulsion Laboratory Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS).

scholarly journals Seeded Region Growing pada Ruang Warna HSI untuk Segmentasi Citra Ikan Tuna

2017 ◽  
Vol 9 (1) ◽  
pp. 56
Author(s):  
Wanvy Arifha Saputra ◽  
Agus Zainal Arifin
Keyword(s):  
Image Segmentation ◽  
Mathematical Morphology ◽  
Color Space ◽  
Region Growing ◽  
Saturation Intensity ◽  
Seeded Region Growing ◽  
A Value ◽  
Hsi Color Space ◽  
Process Classification

The image of the tuna before entering process classification, it must have a good segmentation results. The result of good segmentation is object and background separate clearly. The image of tuna which has a distribution of light that is uneven and has a complex texture will produce an error segmentation. One method of image segmentation was seeded region growing and parameters that used only two, namely seed and threshold. This research proposed method seeded region growing in the HSI color space for image segmentation of tuna. The Color space of RGB (red green blue) on image of tuna transformed into a color space HSI (hue saturation intensity) then only the hue color space used as segmentation by using seeded region growing. Determination of seed and threshold parameters can do manually and the result of the segmentation do refinement with mathematical morphology. The experiment using 30 image of tuna to segmentation and evaluation methods using RAE (relative foreground area error), MAE (missclassification error) and the MHD (modified Hausdroff distance). The image of the tuna successfully performed segmentation evidenced by a value RAE, ME and MHD respectively are 5,40%, 1,53% dan 0,41%.

scholarly journals Automated tumor segmentation in MR brain image using fuzzy c-means clustering and seeded region methodology

2021 ◽  
Vol 10 (2) ◽  
pp. 284
Author(s):  
Mustafa Zuhaer Nayef AL-Dabagh
Keyword(s):  
Region Growing ◽  
Automated System ◽  
Tumor Segmentation ◽  
Morphological Operations ◽  
Jaccard Coefficient ◽  
Fuzzy C Means ◽  
Seeded Region Growing ◽  
Processing Step ◽  
Fuzzy C Means Clustering ◽  
Comparison Of The Results

<span id="docs-internal-guid-c8cba487-7fff-2314-f38a-f2936a74e0fd"><span>Automated segmentation of a tumor is still a considerably exciting research topic in the medical imaging processing field, and it plays a considerable role in forming a right diagnosis, to aid effective medical treatment. In this work, a fully automated system for segmentation of the brain tumor in MRI images is introduced. The suggested system consists of three parts: Initially, the image is pre-processed to enhance contrast, eliminate noise, and strip the skull from the image using filtering and morphological operations. Secondly, segmentation of the image happens using two techniques, fuzzy c-means clustering (FCM) and with the application of a seeded region growing algorithm (SGR). Thirdly, this method proposes a post-processing step to smooth segmentation region edges using morphological operations. The testing of the proposed system involved 233 patients, which included 287 MRI images. A comparison of the results ensued, with the manual verification of the traces performed by doctors, which ultimately proved an average Dice Coefficient of 90.13% and an average Jaccard Coefficient of 82.60% also, by comparison with traditional segmentation techniques such as FCM method. The segmentation results and quantitative data analysis demonstrates the effectiveness of the suggested system.</span></span>

scholarly journals Semi-automatic Segmentation of Liver Tumors from CT Scans Using Bayesian Rule-based 3D Region Growing

2008 ◽  
Author(s):  
Yingyi Qi ◽  
Wei Xiong ◽  
Wee Keng Leow ◽  
Qi Tian ◽  
Jiayin Zhou ◽  
...  
Keyword(s):  
Liver Tumors ◽  
Automatic Segmentation ◽  
Three Dimensional ◽  
Region Growing ◽  
Ct Scans ◽  
Tumor Segmentation ◽  
Morphological Operations ◽  
Model Matching ◽  
Bayesian Decision ◽  
Seeded Region Growing

Automatic segmentation of liver tumorous regions often fails due to high noise and large variance of tumors. In this work, a semi-automatic algorithm is proposed to segment liver tumors from computed tomography (CT) images. To cope with the variance of tumors, their intensity probability density functions (PDF) are modeled as a bag of Gaussians unlike the previous works where the tumor is modeled as a single Gaussian, and employ a three-dimensional seeded region growing (SRG) method. The bag of Gaussians are initialized at manually selected seeds and updated during growing process iteratively. There are two criteria to be fulfilled for growing: one is the Bayesian decision rule, and the other is a model matching measure. Once the growing is terminated, morphological operations are performed to refine the result. This method, showing promising performance, has been evaluated using ten CT scans of livers with twenty tumors provided by the organizer of the 3D Liver Tumor Segmentation Challenge 2008.

THE ROLE OF REMOTE SENSING DATA FOR COASTAL ZONE MONITIORING AND MANAGEMENT (CASE STUDY FOR THE EAST PART OF GULF OF FINLAND)

2017 ◽  
Author(s):  
Nikifor Ostanin ◽  
Nikifor Ostanin
Keyword(s):  
Remote Sensing ◽  
Coastal Zone ◽  
Environmental Changes ◽  
Rapid Development ◽  
Water Environment ◽  
Remote Sensing Data ◽  
Remotely Sensed ◽  
Gulf Of Finland ◽  
Coastal Protection ◽  
Remotely Sensed Data

Coastal zone of the Eastern Gulf of Finland is subjected to essential natural and anthropogenic impact. The processes of abrasion and accumulation are predominant. While some coastal protection structures are old and ruined the problem of monitoring and coastal management is actual. Remotely sensed data is important component of geospatial information for coastal environment research. Rapid development of modern satellite remote sensing techniques and data processing algorithms made this data essential for monitoring and management. Multispectral imagers of modern high resolution satellites make it possible to produce advanced image processing, such as relative water depths estimation, sea-bottom classification and detection of changes in shallow water environment. In the framework of the project of development of new coast protection plan for the Kurortny District of St.-Petersburg a series of archival and modern satellite images were collected and analyzed. As a result several schemes of underwater parts of coastal zone and schemes of relative bathymetry for the key areas were produced. The comparative analysis of multi-temporal images allow us to reveal trends of environmental changes in the study areas. This information, compared with field observations, shows that remotely sensed data is useful and efficient for geospatial planning and development of new coast protection scheme.

Sign in / Sign up

Export Citation Format

Share Document