PARSEG: a computationally efficient approach for statistical validation of botanical seeds’ images
Abstract Human recognition and automated image validation are the most widely used approaches to validate the output of binary segmentation methods but, as the number of pixels in an image easily exceeds several million, they become highly demanding from both practical and computational standpoint....
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-56228-6 |
| _version_ | 1797259309320503296 |
|---|---|
| author | Luca Frigau Claudio Conversano Jaromír Antoch |
| author_facet | Luca Frigau Claudio Conversano Jaromír Antoch |
| author_sort | Luca Frigau |
| collection | DOAJ |
| description | Abstract Human recognition and automated image validation are the most widely used approaches to validate the output of binary segmentation methods but, as the number of pixels in an image easily exceeds several million, they become highly demanding from both practical and computational standpoint. We propose a method, called PARSEG, which stands for PArtitioning, Random Selection, Estimation, and Generalization; being the basic steps within this procedure. Suggested method enables us to perform statistical validation of binary images by selecting the minimum number of pixels from the original image to be used for validation without deteriorating the effectiveness of the validation procedure. It utilizes binary classifiers to accomplish image validation and selects the optimal sample of pixels according to a specific objective function. As a result, the computational complexity of the validation experiment is substantially reduced. The procedure’s effectiveness is illustrated by considering images composed of approximately 13 million pixels from the field of seed recognition. PARSEG provides roughly the same precision of the validation process when extended to the entire image, but it utilizes only about 4% of the original number of pixels, thus reducing, by about 90%, the computing time required to validate a binary segmented image. |
| first_indexed | 2024-04-24T23:07:23Z |
| format | Article |
| id | doaj.art-c3b4275030a740c0892888a9066cebb1 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T23:07:23Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-c3b4275030a740c0892888a9066cebb12024-03-17T12:25:14ZengNature PortfolioScientific Reports2045-23222024-03-0114111710.1038/s41598-024-56228-6PARSEG: a computationally efficient approach for statistical validation of botanical seeds’ imagesLuca Frigau0Claudio Conversano1Jaromír Antoch2Department of Economics and Business Sciences, University of CagliariDepartment of Economics and Business Sciences, University of CagliariFaculty of Mathematics and Physics, Charles UniversityAbstract Human recognition and automated image validation are the most widely used approaches to validate the output of binary segmentation methods but, as the number of pixels in an image easily exceeds several million, they become highly demanding from both practical and computational standpoint. We propose a method, called PARSEG, which stands for PArtitioning, Random Selection, Estimation, and Generalization; being the basic steps within this procedure. Suggested method enables us to perform statistical validation of binary images by selecting the minimum number of pixels from the original image to be used for validation without deteriorating the effectiveness of the validation procedure. It utilizes binary classifiers to accomplish image validation and selects the optimal sample of pixels according to a specific objective function. As a result, the computational complexity of the validation experiment is substantially reduced. The procedure’s effectiveness is illustrated by considering images composed of approximately 13 million pixels from the field of seed recognition. PARSEG provides roughly the same precision of the validation process when extended to the entire image, but it utilizes only about 4% of the original number of pixels, thus reducing, by about 90%, the computing time required to validate a binary segmented image.https://doi.org/10.1038/s41598-024-56228-6Statistical image validationImage segmentationBackground subtractionBig dataClassificationCART |
| spellingShingle | Luca Frigau Claudio Conversano Jaromír Antoch PARSEG: a computationally efficient approach for statistical validation of botanical seeds’ images Scientific Reports Statistical image validation Image segmentation Background subtraction Big data Classification CART |
| title | PARSEG: a computationally efficient approach for statistical validation of botanical seeds’ images |
| title_full | PARSEG: a computationally efficient approach for statistical validation of botanical seeds’ images |
| title_fullStr | PARSEG: a computationally efficient approach for statistical validation of botanical seeds’ images |
| title_full_unstemmed | PARSEG: a computationally efficient approach for statistical validation of botanical seeds’ images |
| title_short | PARSEG: a computationally efficient approach for statistical validation of botanical seeds’ images |
| title_sort | parseg a computationally efficient approach for statistical validation of botanical seeds images |
| topic | Statistical image validation Image segmentation Background subtraction Big data Classification CART |
| url | https://doi.org/10.1038/s41598-024-56228-6 |
| work_keys_str_mv | AT lucafrigau parsegacomputationallyefficientapproachforstatisticalvalidationofbotanicalseedsimages AT claudioconversano parsegacomputationallyefficientapproachforstatisticalvalidationofbotanicalseedsimages AT jaromirantoch parsegacomputationallyefficientapproachforstatisticalvalidationofbotanicalseedsimages |