| Autor: |
Tala, Entesar B., Thabet, Eman |
| Předmět: |
|
| Zdroj: |
Al-Qadisiyah Journal of Pure Science; 2022, Vol. 27 Issue 1, p1-15, 15p |
| Abstrakt: |
Detection and recognition of Diabetic Retinopathy (DR) at the early phase can prevent the risk of gradual damage in the retina and vision loss. Many works have been introduced for automatic DR recognition and diagnosis in recent years. To date, there are still some issues that are required to work on to improve the quality and the performance of automatic DR recognition systems. Therefore, this paper introduces a machine learning-based approach for DR diagnosis and recognition by proposing texture analysis features of the GLDM technique (Contrast, Angular Second Moment, Entropy, Mean, and Inverse Difference Moment) feature and feed-forward neural network classifier. The proposed method has achieved a recognition accuracy of 95% according to undertaken experiments and performance analysis. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
