A pattern recognition procedure for the identification of digital numbers in electrical meters using Neural Networks

  title={A pattern recognition procedure for the identification of digital numbers in electrical meters using Neural Networks},
  author={Daladier Jabba and M. Rodriguez and Geovanni Berdugo and Maria Calle and Miguel Jimeno and Eduardo E. Zurek},
  journal={2012 IEEE Symposium on Industrial Electronics and Applications},
  • D. JabbaM. Rodriguez E. Zurek
  • Published 1 September 2012
  • Engineering
  • 2012 IEEE Symposium on Industrial Electronics and Applications
This paper presents an approach for number pattern recognition process applied to a practical example: identification of digital numbers in electrical meters using Neural Networks. Results of the implementation were confronted with real measurements for validation purposes. 

Figures and Tables from this paper

Digital recognition of electric meter with deep learning

Experimental results show that digital of different types of electric meters can be recognized efficiently by the proposed method and the effect of different appearances of digital screen different shooting angles and environmental interference can be eliminated, thus improving the adaptability of the method.

Use SSD to Detect the Digital Region in Electricity Meter

From the experimental results, it is demonstrated that the presented deep learning methods detect the digital region better than the pre-trained SSD model.



Recognition of the numbers of numerical civilian instrumentations based on bp neural network

This article uses iterative global threshold to binarize the images and then adopts projection method to locate the target regions and divide the numbers and indicates that the recognition rate is above 98%.

Pattern Recognition and Image Processing

A very brief survey of recent developments in basic pattern recognition and image processing techniques is presented.

Recognition of On-Line Hand-Drawn Graphical Symbols Based on BP Neural Network

A neural network model of on-line hand- drawn graphical symbols identifying is established and a hand-drawn graphical symbols on-lines authentication system is developed with a good result of on line hand- Drawn graphical symbol recognition.

Neural networks for classification: a survey

  • G. Zhang
  • Computer Science
    IEEE Trans. Syst. Man Cybern. Part C
  • 2000
The issues of posterior probability estimation, the link between neural and conventional classifiers, learning and generalization tradeoff in classification, the feature variable selection, as well as the effect of misclassification costs are examined.

Use of MATLAB Neural Networks Toolbox in a character recognition problem

  • M. Trebar
  • Computer Science
    Comput. Appl. Eng. Educ.
  • 2005
The solution of the character recognition problem is described from the beginning: collecting the data, data encoding, defining the input‐output mapping architecture to the training, and testing the neural networks with the NN Toolbox.

A Survey of Methods and Strategies for Feature Extraction in Handwritten Script Identification

  • Snehal DalalL. Malik
  • Computer Science
    2008 First International Conference on Emerging Trends in Engineering and Technology
  • 2008
This paper provides a review of advances in feature extraction techniques and an appreciation for the range of techniques that have been developed is provided rather than to simply list sources.

License Plate Recognition Algorithm Based on Radial Basis Function Neural Networks

  • Weihua Wang
  • Computer Science
    2009 International Symposium on Intelligent Ubiquitous Computing and Education
  • 2009
The results show that compared with BP neural network, the RBF neural network can decrease the error recognition rate, the complexity of the system architecture, the training time, and the recognition time efficiently.

Feature extraction methods for character recognition-A survey

Recognition of printed Chinese characters by using Neural Network

This article presents a technique for the recognition of printed Chinese characters using back propagation algorithm and discusses Chinese character recognition using preprocessing, projection and zoning feature extraction.

Offline handwritten character recognition using neural network

This paper adopts segmentation based handwritten word recognition where neural networks are used to identify individual characters and post processing technique that uses lexicon is employed to improve the overall recognition accuracy.