Enhancing image annotation technique of fruit classification using a deep learning approach
An accurate image retrieval technique is required due to the rapidly increasing number of images. It is important to implement image annotation techniques that are fast, simple, and, most importantly, automatically annotate. Image annotation has recently received much attention due to the massive ri...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI
2023
|
Subjects: | |
Online Access: | http://eprints.utm.my/107240/1/MohdFauziOthman2023_EnhancingImageAnnotationTechniqueofFruit.pdf |
_version_ | 1811132499890274304 |
---|---|
author | Mamat, Normaisharah Othman, Mohd. Fauzi Abdulghafor, Rawad Alwan, Ali A. Gulzar, Yonis |
author_facet | Mamat, Normaisharah Othman, Mohd. Fauzi Abdulghafor, Rawad Alwan, Ali A. Gulzar, Yonis |
author_sort | Mamat, Normaisharah |
collection | ePrints |
description | An accurate image retrieval technique is required due to the rapidly increasing number of images. It is important to implement image annotation techniques that are fast, simple, and, most importantly, automatically annotate. Image annotation has recently received much attention due to the massive rise in image data volume. Focusing on the agriculture field, this study implements automatic image annotation, namely, a repetitive annotation task technique, to classify the ripeness of oil palm fruit and recognize a variety of fruits. This approach assists farmers to enhance the classification of fruit methods and increase their production. This study proposes simple and effective models using a deep learning approach with You Only Look Once (YOLO) versions. The models were developed through transfer learning where the dataset was trained with 100 images of oil fruit palm and 400 images of a variety of fruit in RGB images. Model performance and accuracy of automatically annotating the images with 3500 fruits were examined. The results show that the annotation technique successfully annotated a large number of images accurately. The mAP result achieved for oil palm fruit was 98.7% and the variety of fruit was 99.5%. |
first_indexed | 2024-09-24T00:05:16Z |
format | Article |
id | utm.eprints-107240 |
institution | Universiti Teknologi Malaysia - ePrints |
language | English |
last_indexed | 2024-09-24T00:05:16Z |
publishDate | 2023 |
publisher | MDPI |
record_format | dspace |
spelling | utm.eprints-1072402024-09-01T06:21:24Z http://eprints.utm.my/107240/ Enhancing image annotation technique of fruit classification using a deep learning approach Mamat, Normaisharah Othman, Mohd. Fauzi Abdulghafor, Rawad Alwan, Ali A. Gulzar, Yonis T58.6-58.62 Management information systems TA Engineering (General). Civil engineering (General) An accurate image retrieval technique is required due to the rapidly increasing number of images. It is important to implement image annotation techniques that are fast, simple, and, most importantly, automatically annotate. Image annotation has recently received much attention due to the massive rise in image data volume. Focusing on the agriculture field, this study implements automatic image annotation, namely, a repetitive annotation task technique, to classify the ripeness of oil palm fruit and recognize a variety of fruits. This approach assists farmers to enhance the classification of fruit methods and increase their production. This study proposes simple and effective models using a deep learning approach with You Only Look Once (YOLO) versions. The models were developed through transfer learning where the dataset was trained with 100 images of oil fruit palm and 400 images of a variety of fruit in RGB images. Model performance and accuracy of automatically annotating the images with 3500 fruits were examined. The results show that the annotation technique successfully annotated a large number of images accurately. The mAP result achieved for oil palm fruit was 98.7% and the variety of fruit was 99.5%. MDPI 2023-01 Article PeerReviewed application/pdf en http://eprints.utm.my/107240/1/MohdFauziOthman2023_EnhancingImageAnnotationTechniqueofFruit.pdf Mamat, Normaisharah and Othman, Mohd. Fauzi and Abdulghafor, Rawad and Alwan, Ali A. and Gulzar, Yonis (2023) Enhancing image annotation technique of fruit classification using a deep learning approach. Sustainability (Switzerland), 15 (2). pp. 1-19. ISSN 2071-1050 http://dx.doi.org/10.3390/su15020901 DOI:10.3390/su15020901 |
spellingShingle | T58.6-58.62 Management information systems TA Engineering (General). Civil engineering (General) Mamat, Normaisharah Othman, Mohd. Fauzi Abdulghafor, Rawad Alwan, Ali A. Gulzar, Yonis Enhancing image annotation technique of fruit classification using a deep learning approach |
title | Enhancing image annotation technique of fruit classification using a deep learning approach |
title_full | Enhancing image annotation technique of fruit classification using a deep learning approach |
title_fullStr | Enhancing image annotation technique of fruit classification using a deep learning approach |
title_full_unstemmed | Enhancing image annotation technique of fruit classification using a deep learning approach |
title_short | Enhancing image annotation technique of fruit classification using a deep learning approach |
title_sort | enhancing image annotation technique of fruit classification using a deep learning approach |
topic | T58.6-58.62 Management information systems TA Engineering (General). Civil engineering (General) |
url | http://eprints.utm.my/107240/1/MohdFauziOthman2023_EnhancingImageAnnotationTechniqueofFruit.pdf |
work_keys_str_mv | AT mamatnormaisharah enhancingimageannotationtechniqueoffruitclassificationusingadeeplearningapproach AT othmanmohdfauzi enhancingimageannotationtechniqueoffruitclassificationusingadeeplearningapproach AT abdulghaforrawad enhancingimageannotationtechniqueoffruitclassificationusingadeeplearningapproach AT alwanalia enhancingimageannotationtechniqueoffruitclassificationusingadeeplearningapproach AT gulzaryonis enhancingimageannotationtechniqueoffruitclassificationusingadeeplearningapproach |