An Evaluation on the Robustness of Five Popular Keypoint Descriptors to Image Modifications Specific to Laser Scanning Microscopy
Laser scanning microscopy (LSM) techniques are of paramount importance at this time for key domains such as biology, medicine, or materials science. Computer vision methods are instrumental for boosting the potential of LSM, providing reliable results for important tasks, such as image segmentation,...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8410670/ |
| _version_ | 1830357415707541504 |
|---|---|
| author | Devrim Unay Stefan G. Stanciu |
| author_facet | Devrim Unay Stefan G. Stanciu |
| author_sort | Devrim Unay |
| collection | DOAJ |
| description | Laser scanning microscopy (LSM) techniques are of paramount importance at this time for key domains such as biology, medicine, or materials science. Computer vision methods are instrumental for boosting the potential of LSM, providing reliable results for important tasks, such as image segmentation, registration, classification, or retrieval in a fraction of the time that a human expert would require (at similar or even higher accuracy levels). Image keypoint extraction and description represent essential building blocks of modern computer vision approaches, and the development of such techniques has gained massive interest over the past couple of decades. In this paper, we compare side-by-side five popular keypoint description techniques, scale invariant feature transform (SIFT), speeded-up robust features (SURF), binary robust invariant scalable keypoints (BRISK), fast retina keypoint (FREAK) and BLOCK, with respect to their capacity to represent in a reproducible manner image regions contained in LSM data sets acquired under different acquisition conditions. We evaluate this capacity in terms of descriptor matching performance, using data sets acquired in a principled manner and a thorough Precision-Recall analysis. We identify which of the five evaluated techniques is most robust to specific LSM image modifications associated to the laser beam power, photomultiplier gain, or pixel dwell, and show that certain pre-processing steps have the potential to enhance keypoint matching. |
| first_indexed | 2024-12-20T02:22:06Z |
| format | Article |
| id | doaj.art-449a54c5994749c9990372d78db57ce6 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T02:22:06Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-449a54c5994749c9990372d78db57ce62022-12-21T19:56:47ZengIEEEIEEE Access2169-35362018-01-016401544016410.1109/ACCESS.2018.28552648410670An Evaluation on the Robustness of Five Popular Keypoint Descriptors to Image Modifications Specific to Laser Scanning MicroscopyDevrim Unay0https://orcid.org/0000-0003-3478-7318Stefan G. Stanciu1https://orcid.org/0000-0002-1676-3040Department of Biomedical Engineering, İzmir University of Economics, İzmir, TurkeyCenter for Microscopy-Microanalysis and Information Processing, University Politehnica of Bucharest, Bucharest, RomaniaLaser scanning microscopy (LSM) techniques are of paramount importance at this time for key domains such as biology, medicine, or materials science. Computer vision methods are instrumental for boosting the potential of LSM, providing reliable results for important tasks, such as image segmentation, registration, classification, or retrieval in a fraction of the time that a human expert would require (at similar or even higher accuracy levels). Image keypoint extraction and description represent essential building blocks of modern computer vision approaches, and the development of such techniques has gained massive interest over the past couple of decades. In this paper, we compare side-by-side five popular keypoint description techniques, scale invariant feature transform (SIFT), speeded-up robust features (SURF), binary robust invariant scalable keypoints (BRISK), fast retina keypoint (FREAK) and BLOCK, with respect to their capacity to represent in a reproducible manner image regions contained in LSM data sets acquired under different acquisition conditions. We evaluate this capacity in terms of descriptor matching performance, using data sets acquired in a principled manner and a thorough Precision-Recall analysis. We identify which of the five evaluated techniques is most robust to specific LSM image modifications associated to the laser beam power, photomultiplier gain, or pixel dwell, and show that certain pre-processing steps have the potential to enhance keypoint matching.https://ieeexplore.ieee.org/document/8410670/Keypoint descriptorslaser scanning microscopyscale invariant feature transform (SIFT)speeded-up robust features (SURF)binary robust invariant scalable keypoints (BRISK)fast retina keypoint (FREAK) |
| spellingShingle | Devrim Unay Stefan G. Stanciu An Evaluation on the Robustness of Five Popular Keypoint Descriptors to Image Modifications Specific to Laser Scanning Microscopy IEEE Access Keypoint descriptors laser scanning microscopy scale invariant feature transform (SIFT) speeded-up robust features (SURF) binary robust invariant scalable keypoints (BRISK) fast retina keypoint (FREAK) |
| title | An Evaluation on the Robustness of Five Popular Keypoint Descriptors to Image Modifications Specific to Laser Scanning Microscopy |
| title_full | An Evaluation on the Robustness of Five Popular Keypoint Descriptors to Image Modifications Specific to Laser Scanning Microscopy |
| title_fullStr | An Evaluation on the Robustness of Five Popular Keypoint Descriptors to Image Modifications Specific to Laser Scanning Microscopy |
| title_full_unstemmed | An Evaluation on the Robustness of Five Popular Keypoint Descriptors to Image Modifications Specific to Laser Scanning Microscopy |
| title_short | An Evaluation on the Robustness of Five Popular Keypoint Descriptors to Image Modifications Specific to Laser Scanning Microscopy |
| title_sort | evaluation on the robustness of five popular keypoint descriptors to image modifications specific to laser scanning microscopy |
| topic | Keypoint descriptors laser scanning microscopy scale invariant feature transform (SIFT) speeded-up robust features (SURF) binary robust invariant scalable keypoints (BRISK) fast retina keypoint (FREAK) |
| url | https://ieeexplore.ieee.org/document/8410670/ |
| work_keys_str_mv | AT devrimunay anevaluationontherobustnessoffivepopularkeypointdescriptorstoimagemodificationsspecifictolaserscanningmicroscopy AT stefangstanciu anevaluationontherobustnessoffivepopularkeypointdescriptorstoimagemodificationsspecifictolaserscanningmicroscopy AT devrimunay evaluationontherobustnessoffivepopularkeypointdescriptorstoimagemodificationsspecifictolaserscanningmicroscopy AT stefangstanciu evaluationontherobustnessoffivepopularkeypointdescriptorstoimagemodificationsspecifictolaserscanningmicroscopy |