On the Objectivity of the Objective Function—Problems with Unsupervised Segmentation Evaluation Based on Global Score and a Possible Remedy
Image segmentation is a crucial stage at the very beginning of many geographic object-based image analysis (GEOBIA) workflows. While segmentation quality is generally deemed of great importance, selecting adequate tuning parameters for a segmentation algorithm can be tedious and subjective. Procedur...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/9/8/769 |
| _version_ | 1798030862883749888 |
|---|---|
| author | Sebastian Böck Markus Immitzer Clement Atzberger |
| author_facet | Sebastian Böck Markus Immitzer Clement Atzberger |
| author_sort | Sebastian Böck |
| collection | DOAJ |
| description | Image segmentation is a crucial stage at the very beginning of many geographic object-based image analysis (GEOBIA) workflows. While segmentation quality is generally deemed of great importance, selecting adequate tuning parameters for a segmentation algorithm can be tedious and subjective. Procedures to automatically choose parameters of a segmentation algorithm are meant to make the process objective and reproducible. One of those approaches, and perhaps the most frequently used unsupervised parameter optimization method in the context of GEOBIA is called the objective function, also known as Global Score. Unfortunately, the method exhibits a hitherto widely neglected, yet severe source of instability, which makes quality rankings inconsistent. We demonstrate the issue in detail and propose a modification of the Global Score to mitigate the problem. This hopefully serves as a starting point to spark further development of the popular approach. |
| first_indexed | 2024-04-11T19:48:08Z |
| format | Article |
| id | doaj.art-70056b2607424f8cb394cc1fd8b471b0 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-11T19:48:08Z |
| publishDate | 2017-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-70056b2607424f8cb394cc1fd8b471b02022-12-22T04:06:23ZengMDPI AGRemote Sensing2072-42922017-07-019876910.3390/rs9080769rs9080769On the Objectivity of the Objective Function—Problems with Unsupervised Segmentation Evaluation Based on Global Score and a Possible RemedySebastian Böck0Markus Immitzer1Clement Atzberger2Institute of Surveying, Remote Sensing and Land Information (IVFL), University of Natural Resources and Life Sciences, Vienna (BOKU), Peter Jordan Strasse 82, 1190 Vienna, AustriaInstitute of Surveying, Remote Sensing and Land Information (IVFL), University of Natural Resources and Life Sciences, Vienna (BOKU), Peter Jordan Strasse 82, 1190 Vienna, AustriaInstitute of Surveying, Remote Sensing and Land Information (IVFL), University of Natural Resources and Life Sciences, Vienna (BOKU), Peter Jordan Strasse 82, 1190 Vienna, AustriaImage segmentation is a crucial stage at the very beginning of many geographic object-based image analysis (GEOBIA) workflows. While segmentation quality is generally deemed of great importance, selecting adequate tuning parameters for a segmentation algorithm can be tedious and subjective. Procedures to automatically choose parameters of a segmentation algorithm are meant to make the process objective and reproducible. One of those approaches, and perhaps the most frequently used unsupervised parameter optimization method in the context of GEOBIA is called the objective function, also known as Global Score. Unfortunately, the method exhibits a hitherto widely neglected, yet severe source of instability, which makes quality rankings inconsistent. We demonstrate the issue in detail and propose a modification of the Global Score to mitigate the problem. This hopefully serves as a starting point to spark further development of the popular approach.https://www.mdpi.com/2072-4292/9/8/769segmentation evaluationGEOBIAparameter optimizationGlobal Score |
| spellingShingle | Sebastian Böck Markus Immitzer Clement Atzberger On the Objectivity of the Objective Function—Problems with Unsupervised Segmentation Evaluation Based on Global Score and a Possible Remedy Remote Sensing segmentation evaluation GEOBIA parameter optimization Global Score |
| title | On the Objectivity of the Objective Function—Problems with Unsupervised Segmentation Evaluation Based on Global Score and a Possible Remedy |
| title_full | On the Objectivity of the Objective Function—Problems with Unsupervised Segmentation Evaluation Based on Global Score and a Possible Remedy |
| title_fullStr | On the Objectivity of the Objective Function—Problems with Unsupervised Segmentation Evaluation Based on Global Score and a Possible Remedy |
| title_full_unstemmed | On the Objectivity of the Objective Function—Problems with Unsupervised Segmentation Evaluation Based on Global Score and a Possible Remedy |
| title_short | On the Objectivity of the Objective Function—Problems with Unsupervised Segmentation Evaluation Based on Global Score and a Possible Remedy |
| title_sort | on the objectivity of the objective function problems with unsupervised segmentation evaluation based on global score and a possible remedy |
| topic | segmentation evaluation GEOBIA parameter optimization Global Score |
| url | https://www.mdpi.com/2072-4292/9/8/769 |
| work_keys_str_mv | AT sebastianbock ontheobjectivityoftheobjectivefunctionproblemswithunsupervisedsegmentationevaluationbasedonglobalscoreandapossibleremedy AT markusimmitzer ontheobjectivityoftheobjectivefunctionproblemswithunsupervisedsegmentationevaluationbasedonglobalscoreandapossibleremedy AT clementatzberger ontheobjectivityoftheobjectivefunctionproblemswithunsupervisedsegmentationevaluationbasedonglobalscoreandapossibleremedy |