Enhancement of Image Classification Using Transfer Learning and GAN-Based Synthetic Data Augmentation
- Title
- Enhancement of Image Classification Using Transfer Learning and GAN-Based Synthetic Data Augmentation
- Creator
- Chatterjee S.; Hazra D.; Byun Y.-C.; Kim Y.-W.
- Description
- Plastic bottle recycling has a crucial role in environmental degradation and protection. Position and background should be the same to classify plastic bottles on a conveyor belt. The manual detection of plastic bottles is time consuming and leads to human error. Hence, the automatic classification of plastic bottles using deep learning techniques can assist with the more accurate results and reduce cost. To achieve a considerably good result using the DL model, we need a large volume of data to train. We propose a GAN-based model to generate synthetic images similar to the original. To improve the image synthesis quality with less training time and decrease the chances of mode collapse, we propose a modified lightweight-GAN model, which consists of a generator and a discriminator with an auto-encoding feature to capture essential parts of the input image and to encourage the generator to produce a wide range of real data. Then a newly designed weighted average ensemble model based on two pre-trained models, inceptionV3 and xception, to classify transparent plastic bottles obtains an improved classification accuracy of 99.06%. 2022 by the authors. Licensee MDPI, Basel, Switzerland.
- Source
- Mathematics, Vol-10, No. 9
- Date
- 2022-01-01
- Publisher
- MDPI
- Subject
- deep learning; generative adversarial networks; image classification; plastic bottle; transfer learning
- Coverage
- Chatterjee S., Department of Computer Engineering, Jeju National University, Jeju, 63243, South Korea; Hazra D., Department of Computer Engineering, Jeju National University, Jeju, 63243, South Korea; Byun Y.-C., Department of Computer Engineering, Jeju National University, Jeju, 63243, South Korea; Kim Y.-W., Centre for Digital Innovation, CHRIST University (Deemed to be University), Karnataka, Bengaluru, 560029, India
- Rights
- All Open Access; Gold Open Access
- Relation
- ISSN: 22277390
- Format
- Online
- Language
- English
- Type
- Article
Collection
Citation
Chatterjee S.; Hazra D.; Byun Y.-C.; Kim Y.-W., “Enhancement of Image Classification Using Transfer Learning and GAN-Based Synthetic Data Augmentation,” CHRIST (Deemed To Be University) Institutional Repository, accessed February 26, 2025, https://archives.christuniversity.in/items/show/15115.