Abstract | ||
---|---|---|
In many industrial applications, digits on instrument display need to be automatically identified. In this paper, we propose a new feature extraction method based on non-luminous digital tubes for recognition of digits on instrument display. The advantage of this method is that it is required fewer digital tubes to represent a digit on multimeters. And based on feature coding detection, a corresponding recognition algorithm is proposed to recognize digits on multimeters. The algorithm can identify digits well only using a few steps to detect features so that the algorithm is very efficient. The experimental results show that the recognition rate can reach 99.36% and recognition time is not more than 0.2 milliseconds using a PC with 2.0GHz CPU. They demonstrate that the proposed method is effective and fast in digital recognition, which can meet the requirements for the automatic identification of digits on multimeters. It is significant for application in real time systems. |
Year | Venue | Keywords |
---|---|---|
2017 | 2017 10TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI) | multimeter, image processing, feature extraction, digital recognition |
Field | DocType | Citations |
Computer vision,Pattern recognition,Computer science,Feature coding,Numerical digit,Feature extraction,Image segmentation,Digital image,Artificial intelligence,Recognition algorithm,Multimeter | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Caiyun Wu | 1 | 16 | 8.46 |
QingXiang Wu | 2 | 44 | 12.42 |
Caiyou Yuan | 3 | 0 | 0.68 |
Peng-Fei Li | 4 | 56 | 20.94 |
Yanan Zhang | 5 | 9 | 6.92 |
Yao Xiao | 6 | 13 | 7.62 |