A4 Article in conference proceedings
Identifying Images with Ladders Using Deep CNN Transfer Learning (2020)
Pandey, G., Baranwal, A., & Semenov, A. (2020). Identifying Images with Ladders Using Deep CNN Transfer Learning. In I. Czarnowski, R. J. Howlett, & L. C. Jain (Eds.), Intelligent Decision Technologies 2019 : Proceedings of the 11th KES International Conference on Intelligent Decision Technologies (KES-IDT 2019), Volume 1 (pp. 143-153). Springer. Smart Innovation, Systems and Technologies, 142. https://doi.org/10.1007/978-981-13-8311-3_13
JYU authors or editors
Publication details
All authors or editors: Pandey, Gaurav; Baranwal, Arvind; Semenov, Alexander
Parent publication: Intelligent Decision Technologies 2019 : Proceedings of the 11th KES International Conference on Intelligent Decision Technologies (KES-IDT 2019), Volume 1
Parent publication editors: Czarnowski, Ireneusz; Howlett, Robert J.; Jain, Lakhmi C.
Conference:
- International conference on intelligent decision technologies
Place and date of conference: Malta, 17.-19.6.2019
ISBN: 978-981-13-8310-6
eISBN: 978-981-13-8311-3
Journal or series: Smart Innovation, Systems and Technologies
ISSN: 2190-3018
eISSN: 2190-3026
Publication year: 2020
Number in series: 142
Pages range: 143-153
Number of pages in the book: 354
Publisher: Springer
Place of Publication: Singapore
Publication country: Singapore
Publication language: English
DOI: https://doi.org/10.1007/978-981-13-8311-3_13
Publication open access: Not open
Publication channel open access:
Abstract
Deep Convolutional Neural Networks (CNNs) as well as transfer learning using their pre-trained models often find applications in image classification tasks. In this paper, we explore the utilization of pre-trained CNNs for identifying images containing ladders. We target a particular use case, where an insurance firm, in order to decide the price for workers’ compensation insurance for its client companies, would like to assess the risk involved in their workplace environments. For this, the workplace images provided by the client companies can be utilized and the presence of ladders in such images can be considered as a workplace hazard and therefore an indicator of risk. To this end, we explore the utilization of pre-trained CNN models: VGG-16 and VGG-19, to extract features from images in a training set, that in turn are used to train a binary classifier (classifying an image as ladder and no ladder). The trained binary classifier can then be used for future predictions. Moreover, we explore the effect of including standard image augmentation techniques to enrich the training set. We also explore improving classification predictions by combining predictions generated by two individual binary classifiers that utilize features obtained from pre-trained VGG-16 and VGG-19 models. Our experimental results compare accuracies of classifiers that utilize features obtained using pre-trained VGG-16 and VGG-19 models. Furthermore, we analyze improvements in accuracies achieved on using image augmentation techniques as well as on combining predictions from VGG-16 and VGG-19 transfer learning based binary classifiers.
Keywords: automated pattern recognition; machine learning
Free keywords: CNN; image classification; deep learning
Contributing organizations
Ministry reporting: Yes
Reporting Year: 2020
JUFO rating: 1