Read the indicator value using Deep Learning

Version 1.0.1 (5,46 Mo) par Takuji Fukumoto
Read the indicator (meter) value using CNN regression with pre-trained AlexNet
0.0
(0)
144 téléchargements
Mise à jour 25 déc. 2020
Afficher la licence sur GitHub

In factories and other workplaces, there are many scenes where people read the meter value visually. If you work for it for long time, you get stressed and human error can occur. You may try rules-based image processing. but it is not easy to create a robust algorithm that can handle any environment.

In this sample code, the meter value obtained by the camera is predicted using deep learning regression.
I customized the pre-trained CNN network (AlexNet) for regression and applied the model into the task to read meter values.

You can get the pretrained AlexNet here.
https://jp.mathworks.com/matlabcentral/fileexchange/59133-deep-learning-toolbox-model-for-alexnet-network

[Keyward]
Image processing・Computer Vision・Deep Learning・CNN・Deep Learning・Machine Learning・Regression・Transfer learning

Citation pour cette source

Takuji Fukumoto (2024). Read the indicator value using Deep Learning (https://github.com/mathworks/Read-the-indicator-value-using-Deep-Learning/releases/tag/1.0.1), GitHub. Récupéré le .

Compatibilité avec les versions de MATLAB
Créé avec R2019a
Compatible avec R2019a
Plateformes compatibles
Windows macOS Linux
Catégories
En savoir plus sur Image Data Workflows dans Help Center et MATLAB Answers
Remerciements

Inspiré par : Deep Learning Toolbox Model for AlexNet Network

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Version Publié le Notes de version
1.0.1

See release notes for this release on GitHub: https://github.com/mathworks/Read-the-indicator-value-using-Deep-Learning/releases/tag/1.0.1
1.0.0

Pour consulter ou signaler des problèmes liés à ce module complémentaire GitHub, accédez au dépôt GitHub.
Pour consulter ou signaler des problèmes liés à ce module complémentaire GitHub, accédez au dépôt GitHub.