Search

This study aims to develop a low-cost, multi-purpose module based on edge computing for bacterial colony counting and classification. Due to the time-consuming and error-prone nature of traditional methods, this new system has been developed with microcontroller integration and artificial intelligence support. The system utilizes the Arduino Nano 33 BLE microcontroller and a 0.3MP OV7675 camera module, employing Gaussian Blur and Adaptive Thresholding techniques for image processing to better define bacterial colonies. The labeling and feature extraction of colonies involve analyzing characteristics such as area, perimeter, and density. Convolutional Neural Networks and Support Vector Machines have been used for bacterial colony counting and classification. The combination of these two algorithms has facilitated colony analysis. The developed system enables tracking of colony numbers and growth rates over time, emphasizing the importance of a microcontroller-integrated and AI-supported system in achieving fast and traceable results in bacterial colony counting and classification. [ABSTRACT FROM AUTHOR]