Experiments On Iris Classification And Retrieval With Fixed Number Of Surf Keypoints And Texture Features
The paper discusses the results obtained in some experiments made on iris images classification using texture features and SURF (Speeded Up Robust Features) keypoints. We used a method proposed by us, which we named DENOL, that generates a fixed number of SURF keypoints for each image in the dataset...
| मुख्य लेखकों: | , , |
|---|---|
| स्वरूप: | लेख |
| भाषा: | English |
| प्रकाशित: |
Publishing House of the Romanian Academy
2023-11-01
|
| श्रृंखला: | Memoirs of the Scientific Sections of the Romanian Academy |
| विषय: | |
| ऑनलाइन पहुंच: | http://mss.academiaromana-is.ro/mem_sc_st_2023/11_IPavaloi_final.pdf |
| सारांश: | The paper discusses the results obtained in some experiments made on iris images classification using texture features and SURF (Speeded Up Robust Features) keypoints. We used a method proposed by us, which we named DENOL, that generates a fixed number of SURF keypoints for each image in the dataset, by adapting for each image, in SURF keypoints generation process, the Hessian threshold parameter. To obtain texture features we have used four MATHLAB different programs. The experiments used two well-known datasets, UBIRIS and UPOL. The matching procedure for two images is based on the nearest neighbour ratio equation. The results obtained are comparable with those provided by Masek implementation of Daugman’s method. |
|---|---|
| आईएसएसएन: | 1224-1407 2343-7049 |