Mask R-CNN and GrabCut Algorithm for an Image-based Calorie Estimation System
Background: A calorie estimation system based on food images uses computer vision technology to recognize and count calories. There are two key processes required in the system: detection and segmentation. Many algorithms can undertake both processes, each algorithm with different levels of accuracy...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Universitas Airlangga
2022-04-01
|
Series: | Journal of Information Systems Engineering and Business Intelligence |
Online Access: | https://e-journal.unair.ac.id/JISEBI/article/view/30060 |
_version_ | 1811159659325685760 |
---|---|
author | Tiara Lestari Subaran Transmissia Semiawan Nurjannah Syakrani |
author_facet | Tiara Lestari Subaran Transmissia Semiawan Nurjannah Syakrani |
author_sort | Tiara Lestari Subaran |
collection | DOAJ |
description | Background: A calorie estimation system based on food images uses computer vision technology to recognize and count calories. There are two key processes required in the system: detection and segmentation. Many algorithms can undertake both processes, each algorithm with different levels of accuracy.
Objective: This study aims to improve the accuracy of calorie calculation and segmentation processes using a combination of Mask R-CNN and GrabCut algorithms.
Methods: The segmentation mask generated from Mask R-CNN and GrabCut were combined to create a new mask, then used to calculate the calorie. By considering the image augmentation technique, the accuracy of the calorie calculation and segmentation processes were observed to evaluate the method’s performance.
Results: The proposed method could achieve a satisfying result, with an average calculation error value of less than 10% and an F1 score above 90% in all scenarios.
Conclusion: Compared to earlier studies, the combination of Mask R-CNN and GrabCut could obtain a more satisfying result in calculating food calories with different shapes.
Keywords: Augmentation, Calorie Calculation, Detection |
first_indexed | 2024-04-10T05:44:54Z |
format | Article |
id | doaj.art-04dce67d1fe64f089bd0096c23734b79 |
institution | Directory Open Access Journal |
issn | 2598-6333 2443-2555 |
language | English |
last_indexed | 2024-04-10T05:44:54Z |
publishDate | 2022-04-01 |
publisher | Universitas Airlangga |
record_format | Article |
series | Journal of Information Systems Engineering and Business Intelligence |
spelling | doaj.art-04dce67d1fe64f089bd0096c23734b792023-03-06T02:56:32ZengUniversitas AirlanggaJournal of Information Systems Engineering and Business Intelligence2598-63332443-25552022-04-018111010.20473/jisebi.8.1.1-1024595Mask R-CNN and GrabCut Algorithm for an Image-based Calorie Estimation SystemTiara Lestari Subaran0Transmissia Semiawan1https://orcid.org/0000-0002-1724-922XNurjannah Syakrani2https://orcid.org/0000-0001-9747-6475Department of Computer Engineering and Informatics, Bandung State Polytechnic, IndonesiaDepartment of Computer Engineering and Informatics, Bandung State Polytechnic, IndonesiaDepartment of Computer Engineering and Informatics, Bandung State Polytechnic, IndonesiaBackground: A calorie estimation system based on food images uses computer vision technology to recognize and count calories. There are two key processes required in the system: detection and segmentation. Many algorithms can undertake both processes, each algorithm with different levels of accuracy. Objective: This study aims to improve the accuracy of calorie calculation and segmentation processes using a combination of Mask R-CNN and GrabCut algorithms. Methods: The segmentation mask generated from Mask R-CNN and GrabCut were combined to create a new mask, then used to calculate the calorie. By considering the image augmentation technique, the accuracy of the calorie calculation and segmentation processes were observed to evaluate the method’s performance. Results: The proposed method could achieve a satisfying result, with an average calculation error value of less than 10% and an F1 score above 90% in all scenarios. Conclusion: Compared to earlier studies, the combination of Mask R-CNN and GrabCut could obtain a more satisfying result in calculating food calories with different shapes. Keywords: Augmentation, Calorie Calculation, Detectionhttps://e-journal.unair.ac.id/JISEBI/article/view/30060 |
spellingShingle | Tiara Lestari Subaran Transmissia Semiawan Nurjannah Syakrani Mask R-CNN and GrabCut Algorithm for an Image-based Calorie Estimation System Journal of Information Systems Engineering and Business Intelligence |
title | Mask R-CNN and GrabCut Algorithm for an Image-based Calorie Estimation System |
title_full | Mask R-CNN and GrabCut Algorithm for an Image-based Calorie Estimation System |
title_fullStr | Mask R-CNN and GrabCut Algorithm for an Image-based Calorie Estimation System |
title_full_unstemmed | Mask R-CNN and GrabCut Algorithm for an Image-based Calorie Estimation System |
title_short | Mask R-CNN and GrabCut Algorithm for an Image-based Calorie Estimation System |
title_sort | mask r cnn and grabcut algorithm for an image based calorie estimation system |
url | https://e-journal.unair.ac.id/JISEBI/article/view/30060 |
work_keys_str_mv | AT tiaralestarisubaran maskrcnnandgrabcutalgorithmforanimagebasedcalorieestimationsystem AT transmissiasemiawan maskrcnnandgrabcutalgorithmforanimagebasedcalorieestimationsystem AT nurjannahsyakrani maskrcnnandgrabcutalgorithmforanimagebasedcalorieestimationsystem |