Image classification for edge-cloud setting: a comparison study for OCR application
The increasing number of smart devices has led to a rise in the complexity and volume of the image generated. Deep learning is an increasingly common approach for image classification, a fundamental task in many applications. Due to its high computational requirements, implementation in edge devices...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universiti Putra Malaysia Press
2022
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/92592/ http://psasir.upm.edu.my/id/eprint/92592/1/17%20JST-2896-2021.pdf |
| _version_ | 1848861672403369984 |
|---|---|
| author | Kean, Kenneth Hoong Tan Wong, Yee Wan Nugroho, Hermawan |
| author_facet | Kean, Kenneth Hoong Tan Wong, Yee Wan Nugroho, Hermawan |
| author_sort | Kean, Kenneth Hoong Tan |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | The increasing number of smart devices has led to a rise in the complexity and volume of the image generated. Deep learning is an increasingly common approach for image classification, a fundamental task in many applications. Due to its high computational requirements, implementation in edge devices becomes challenging. Cloud computing serves as an enabler, allowing devices with limited resources to perform deep learning. For cloud computing, however, latency is an issue and is undesirable. Edge computing addresses the issue by redistributing data and tasks closer to the edge. Still, a suitable offloading strategy is required to ensure optimal performance with methods such as LeNet-5, OAHR, and Autoencoder (ANC) as feature extractors paired with different classifiers (such as artificial neural network (ANN) and support vector machine (SVM)). In this study, models are evaluated using a dataset representing Optical Character Recognition (OCR) task. The OCR application has recently been used in many task-offloading studies. The evaluation is based on the time performance and scoring criteria. In terms of time performance, a fully connected ANN using features from the ANC is faster by a factor of over 60 times compared to the fastest performing SVM. Moreover, scoring performance shows that the SVM is less prone to overfit in the case of a noisy or imbalanced dataset in comparison with ANN. So, adopting SVM in which the data distribution is unspecified will be wiser as there is a lower tendency to overfit. The training and inference time, however, are generally higher than ANN. |
| first_indexed | 2025-11-15T13:04:51Z |
| format | Article |
| id | upm-92592 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T13:04:51Z |
| publishDate | 2022 |
| publisher | Universiti Putra Malaysia Press |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-925922022-05-27T22:30:38Z http://psasir.upm.edu.my/id/eprint/92592/ Image classification for edge-cloud setting: a comparison study for OCR application Kean, Kenneth Hoong Tan Wong, Yee Wan Nugroho, Hermawan The increasing number of smart devices has led to a rise in the complexity and volume of the image generated. Deep learning is an increasingly common approach for image classification, a fundamental task in many applications. Due to its high computational requirements, implementation in edge devices becomes challenging. Cloud computing serves as an enabler, allowing devices with limited resources to perform deep learning. For cloud computing, however, latency is an issue and is undesirable. Edge computing addresses the issue by redistributing data and tasks closer to the edge. Still, a suitable offloading strategy is required to ensure optimal performance with methods such as LeNet-5, OAHR, and Autoencoder (ANC) as feature extractors paired with different classifiers (such as artificial neural network (ANN) and support vector machine (SVM)). In this study, models are evaluated using a dataset representing Optical Character Recognition (OCR) task. The OCR application has recently been used in many task-offloading studies. The evaluation is based on the time performance and scoring criteria. In terms of time performance, a fully connected ANN using features from the ANC is faster by a factor of over 60 times compared to the fastest performing SVM. Moreover, scoring performance shows that the SVM is less prone to overfit in the case of a noisy or imbalanced dataset in comparison with ANN. So, adopting SVM in which the data distribution is unspecified will be wiser as there is a lower tendency to overfit. The training and inference time, however, are generally higher than ANN. Universiti Putra Malaysia Press 2022 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/92592/1/17%20JST-2896-2021.pdf Kean, Kenneth Hoong Tan and Wong, Yee Wan and Nugroho, Hermawan (2022) Image classification for edge-cloud setting: a comparison study for OCR application. Pertanika Journal of Science and Technology, 30 (2). pp. 1157-1170. ISSN 0128-7680; ESSN: 2231-8526 http://www.pertanika.upm.edu.my/pjst/browse/regular-issue?article=JST-2896-2021 10.47836/pjst.30.2.17 |
| spellingShingle | Kean, Kenneth Hoong Tan Wong, Yee Wan Nugroho, Hermawan Image classification for edge-cloud setting: a comparison study for OCR application |
| title | Image classification for edge-cloud setting: a comparison study for OCR application |
| title_full | Image classification for edge-cloud setting: a comparison study for OCR application |
| title_fullStr | Image classification for edge-cloud setting: a comparison study for OCR application |
| title_full_unstemmed | Image classification for edge-cloud setting: a comparison study for OCR application |
| title_short | Image classification for edge-cloud setting: a comparison study for OCR application |
| title_sort | image classification for edge-cloud setting: a comparison study for ocr application |
| url | http://psasir.upm.edu.my/id/eprint/92592/ http://psasir.upm.edu.my/id/eprint/92592/ http://psasir.upm.edu.my/id/eprint/92592/ http://psasir.upm.edu.my/id/eprint/92592/1/17%20JST-2896-2021.pdf |