5 February 2019 Convolutional neural networks for automatic meter reading
Author Affiliations +
Abstract
We tackle automatic meter reading (AMR) by leveraging the high capability of convolutional neural networks (CNNs). We design a two-stage approach that employs the Fast-YOLO object detector for counter detection and evaluates three different CNN-based approaches for counter recognition. In the AMR literature, most datasets are not available to the research community since the images belong to a service company. In this sense, we introduce a public dataset, called Federal University of Paraná-AMR dataset, with 2000 fully and manually annotated images. This dataset is, to the best of our knowledge, three times larger than the largest public dataset found in the literature and contains a well-defined evaluation protocol to assist the development and evaluation of AMR methods. Furthermore, we propose the use of a data augmentation technique to generate a balanced training set with many more examples to train the CNN models for counter recognition. In the proposed dataset, impressive results were obtained and a detailed speed/accuracy trade-off evaluation of each model was performed. In a public dataset, state-of-the-art results were achieved using <200 images for training.
© 2019 SPIE and IS&T 1017-9909/2019/$25.00 © 2019 SPIE and IS&T
Rayson Laroca, Victor Barroso, Matheus A. Diniz, Gabriel R. Gonçalves, William R. Schwartz, and David Menotti "Convolutional neural networks for automatic meter reading," Journal of Electronic Imaging 28(1), 013023 (5 February 2019). https://doi.org/10.1117/1.JEI.28.1.013023
Received: 4 September 2018; Accepted: 11 December 2018; Published: 5 February 2019
JOURNAL ARTICLE
14 PAGES


SHARE
Advertisement
Advertisement
Back to Top