Skip to content

Piyachetnoy/FSC-Rare-Ind

Repository files navigation

Few-Shot Counting for Custom Industrial Objects

Automation of industrial objects counting, using Few-Shot Counting and Feature Detection approach.

Description

Counting industrial objects is challenging due to their similar appearances and complex shapes. This paper adapts Few-Shot Counting (FSC) to minimize labeled data requirements while improving accuracy. We use Fam- Net with rule-based feature detection to enhance robustness in industrial settings. Additionally, we introduce the INDT dataset, focusing on diverse industrial objects. Our approach integrates density map estimation with feature detection to improve interpretability and reduce over-counting errors. Experimental results show improved accu- racy on industrial objects and strong generalization to other datasets, highlighting FSC’s potential for industrial automation, with future work aimed at optimizing model structure and feature extraction for further performance improvements.

Getting Started

Clone repository to your local device.
Our datasets can be found at Download Datasets

Dependencies

  • Python 3.10.11
  • pip 25.0.1

Installing

Executing program

  • How to run the program
  • Step-by-step bullets
pip install -r requirements.txt

Authors

Piyachet Pongsantichai LinkedIn

Version History

  • 0.1
    • Initial Release

License

This project is licensed under the MIT License - see the .md file for details

Acknowledgments

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published