Multi feature fusion using deep belief network for automatic pap-smear cell image classification
| Autor: | Moh. Faturrahman, Ito Wasito, Fakhirah D. Ghaisani, Ratna Mufidah |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Cervical cancer
Contextual image classification business.industry Local binary patterns Computer science Feature extraction Smear cell Pattern recognition 02 engineering and technology medicine.disease Class (biology) Image (mathematics) 03 medical and health sciences Deep belief network 0302 clinical medicine 0202 electrical engineering electronic engineering information engineering medicine 020201 artificial intelligence & image processing Artificial intelligence business 030217 neurology & neurosurgery |
| Zdroj: | 2017 International Conference on Computer, Control, Informatics and its Applications (IC3INA). |
| DOI: | 10.1109/ic3ina.2017.8251733 |
| Popis: | Early detection of cervical cancer plays an important rule to prevent the cancer metastasis. One of the common approach to early detection of cervical cancer is pap-smear image analysis. Nevertheless the manual pap- smear image analysis have some drawbacks such as provides inconsistent result, takes long time and prone to error occur. Therefore automatic pap-smear cell image classification is required to help pathologist choose the appropriate treatment to patients. In this study, authors propose multi feature fussion among Local Binary Pattern (LBP), Gray Level Co-Occurence Matrix (GLCM) and Shape Features using Deep Belief Network (DBN) for pap- smear cell image classification. The aim of this study is to measure the accuracy of two class classification of pap- smear cell image by the proposed method. The result shows that proposed method achieves the best accuracy at 97.35 % and slightly outperforms existing methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|