CCE-based index selection for neuro assisted MR-image segmentation
| Autor: | M. Sase, Y. Suganaimi, Yukio Kosugi, T. Momose, K. Kameyama, Naoko Uemoto, J. Nishikawa |
|---|---|
| Rok vydání: | 2002 |
| Předmět: |
Contextual image classification
Artificial neural network Segmentation-based object categorization business.industry Vector quantization Scale-space segmentation Pattern recognition Image segmentation Machine learning computer.software_genre Electronic mail Segmentation Artificial intelligence business computer Mathematics |
| Zdroj: | ICIP (2) |
| DOI: | 10.1109/icip.1996.560762 |
| Popis: | For image segmentation with the aid of neural networks of a reasonable size, it is important to select the most effective combination of secondary indices to be used for the classification. Here, the authors introduce a vector quantized conditional class entropy (VQCCE) criterion to evaluate which indices are effective for pattern classification, without testing on the actual classifiers. The proposed method was successfully applied for brain MR segmentation problems to classify the gray-matter/white-matter regions. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|