A Wavelet Relational Fuzzy C-Means Algorithm for 2D Gel Image Segmentation
| Autor: | Mohamed T. Faheem, Shaheera Rashwan, Amany Sarhan, Bayumy A. B. Youssef |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2013 |
| Předmět: |
Article Subject
Computer science Wavelet Analysis ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Scale-space segmentation HL-60 Cells lcsh:Computer applications to medicine. Medical informatics Fuzzy logic General Biochemistry Genetics and Molecular Biology Wavelet Fuzzy Logic Image Processing Computer-Assisted Cluster Analysis Humans Segmentation Computer vision Electrophoresis Gel Two-Dimensional Leukemia General Immunology and Microbiology business.industry Segmentation-based object categorization Applied Mathematics Wavelet transform General Medicine Image segmentation Blood Proteins Neoplasm Proteins Fetal Alcohol Spectrum Disorders Modeling and Simulation Pattern recognition (psychology) lcsh:R858-859.7 Artificial intelligence business Algorithm Algorithms Research Article |
| Zdroj: | Computational and Mathematical Methods in Medicine, Vol 2013 (2013) Computational and Mathematical Methods in Medicine |
| ISSN: | 1748-6718 |
| Popis: | One of the most famous algorithms that appeared in the area of image segmentation is the FuzzyC-Means (FCM) algorithm. This algorithm has been used in many applications such as data analysis, pattern recognition, and image segmentation. It has the advantages of producing high quality segmentation compared to the other available algorithms. Many modifications have been made to the algorithm to improve its segmentation quality. The proposed segmentation algorithm in this paper is based on the FuzzyC-Means algorithm adding the relational fuzzy notion and the wavelet transform to it so as to enhance its performance especially in the area of 2D gel images. Both proposed modifications aim to minimize the oversegmentation error incurred by previous algorithms. The experimental results of comparing both the FuzzyC-Means (FCM) and the Wavelet FuzzyC-Means (WFCM) to the proposed algorithm on real 2D gel images acquired from human leukemias, HL-60 cell lines, and fetal alcohol syndrome (FAS) demonstrate the improvement achieved by the proposed algorithm in overcoming the segmentation error. In addition, we investigate the effect of denoising on the three algorithms. This investigation proves that denoising the 2D gel image before segmentation can improve (in most of the cases) the quality of the segmentation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text