Analysis of Detection of Drow and Entire Co-Occurrence Matrix GLCM Method on The Classification of Image
| Autor: | Saib Suwilo, Taufik Ismail Simanjuntak, Rahmat Widia Sembiring |
|---|---|
| Rok vydání: | 2019 |
| Předmět: | |
| Zdroj: | Journal of Physics: Conference Series. 1361:012028 |
| ISSN: | 1742-6596 1742-6588 |
| Popis: | Grey level co-occurrence matrix or GLCM is a method for obtaining features of a textural image. On the previous study of GLCM, using only 4-degree degrees 0, 45, 90 and 135 in calculating the result of features. Periodicity, directionalityand randomness are the three most important factors in characterizing textures. Therefore, textural directionality is a basic feature of the image and plays an important role in image descriptions, which can be used to describe image textures. So this research will analyse the effect of modification of directionality or direction of adegree of texture distribution on GLCM by using 8 degree direction, which is degree 0, 45, 90, 135, 180, 225, 270, and 315 to know theeffect that impact on theimage by using support vector machine as aclassifier. The results showed that the SVM classifier was not able to work well on GLCM feature extraction, but the performance of the modification resulted in a consistent increase in accuracy by performing 10 tests. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|