Open AccessInvestigation on Intelligent Recognition System of Instrument Based on Multi-step Convolution Neural Network
Author(s) -
Feng Shan,
S.K. Hui,
Xiaoyun Tang,
Weiwei Shi,
Xiaowei Wang,
Xiaofeng Li,
Xurong Zhang,
Haiwei Zhang
Publication year - 2020
Publication title -
international journal of computer and communication engineering
Language(s) - English
Resource type - Journals
ISSN - 2010-3743
DOI - 10.17706/ijcce.2020.9.4.185-192
Subject(s) - calipers , vernier scale , computer science , artificial intelligence , convolutional neural network , computer vision , artificial neural network , convolution (computer science) , standard test image , robustness (evolution) , pattern recognition (psychology) , image (mathematics) , image processing , mathematics , biochemistry , chemistry , geometry , cartography , gene , geography
Digital instruments are widely used in industrial control, traffic, equipment displays and other fields because of the intuitive characteristic of their test data. Aiming at the character recognition scene of digital display Vernier caliper, this paper creatively proposes an intelligent instrument recognition system based on multi-step convolution neural network (CNN). Firstly, the image smples are collected from the Vernier caliper test site, and their resolution and size are normalized. Then the CNN model was established to train the image smples and extract the features. The digital display region in the image smples were extracted according to the image features, and the numbers in the Vernier caliper were cut out. Finally, using the MINIST datas set of Vernier caliper is established, and the CNN model is used to recognize it. The test results show that the overall recognition rate of the proposed CNN model is more than 95%, and has good robustness and generalization ability.