Win10+VS2017+OpenCV3.4.6
In this work, we complete the task of carriage number detection in a set of images.
The binary images can be obtained by performing grayscale processing and thresholding on the input images.
Then we detect the edges using Canny operator and make two groups of closing operation and opening operation with them.
Finally, only the character area with more texture edge information can be retained after such operation, and the character detection process is completed.
The cut characters are obtained by the x-y projection method.
After template matching, the recognized characters are printed on the original image to complete the character recognition process at last.
More details are in HERE
If you get any problems or find any bugs, don't hesitate to comment on GitHub or make a pull request !
The project is mainly created by Yihe Wu (BenJamin Blue) in NJUST, June 2019.
Thanks Zehua Zhao, Hao Zhang, Yaobin Mao and bloggers in CSDN for giving helpful supports.
Please cite these papers in your publications if it helps your research:
@inproceedings{wu2019carriage_number_detection_using_OpneCV,
author = {BenJamin Blue},
title = {carriage_number_detection_using_OpneCV},
year = {2019}
}
The project is freely available for free non-commercial use, and may be redistributed under these conditions.
For commercial queries, please drop an e-mail at [email protected]. We will send the detail agreement to you.