Akciğer Bölgesinin Bölütlenmesinde Karmaşık Değerli Sınıflayıcıların Karşılaştırılması
| Autor: | Ceylan, Murat, Özbay, Yüksel, Uçan, Osman Nuri |
|---|---|
| Rok vydání: | 2011 |
| Předmět: | |
| Zdroj: | Volume: 8, Issue: 1 Cankaya University Journal of Science and Engineering |
| ISSN: | 2564-7954 |
| Popis: | Image segmentation is an important step in many computer vision algorithms.The objective of segmentation is to obtain an optimal region of convergence. Error inthis stage will impact all higher level activities. In this study, three types of complexvaluedclassifier were compared to the segmentation of lung region. These classifiers arecomplex-valued artificial neural network (CVANN), complex-valued wavelet artificial neuralnetwork (CVWANN) and complex valued artificial neural network with complex wavelettransform (CWT-CVANN). To test the performance of the proposed systems, Lung ImageDatabase Consortium (LIDC) dataset was used. Obtained results shown that lung regionsegmentation done using CVWANN and CVANN with worst accuracy rates as 38.59% and75.66%, respectively. On the other hand, CWT-CVANN structure segmented lung region with 100% accuracy rate. Moreover, this structure required only 4.5 second per image forsegmentation task. Thus, it is concluded that CWT-CVANN is a comprising method inlung region segmentation problem. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|