Multi-Task Bacterial Colony Detection and Classification Using YOLOv8 with Edge Optimization for Resource-Constrained Deployment
Abstract
Manual counting and classification of bacterial colonies are critical yet labor-intensive tasks in microbiology, prone to human error particularly on densely populated plates. This work proposes a multi-task deep learning framework trained on the Annotated Germs for Automated Recognition (AGAR) dataset (18,000 images; 9,202 training / 3,067 testing) to automate Colony Forming Unit (CFU) enumeration and species classification. A custom multi-task CNN employing global regression served as the baseline, but demonstrated limited performance in clustered colony environments due to the absence of spatial localization. To address this, a YOLOv8 object detection architecture was adopted with high-resolution 1024x1024 inputs, enabling instance-level colony detection and label assignment. The model achieved a classification accuracy of 98.13% and a counting accuracy of 98.27% (within a 10-colony margin), demonstrating strong predictive capability. To bridge the gap between model performance and practical deployability, the trained model was optimized through unstructured and structured pruning, ONNX conversion, and reduced-precision inference (FP32, FP16, INT8). On a Raspberry Pi 4B, ONNX FP32 and FP16 variants offered the best balance between inference speed (~6.4s) and accuracy (MAE ~2.20). Unstructured pruning preserved predictive accuracy (MAE ~2.01) without runtime gains, while structured pruning resulted in significant accuracy degradation (MAE ~6.3), revealing the sensitivity of instance-level colony detection to architectural compression. These findings provide practical guidance for selecting optimization strategies in resource-constrained laboratory deployments.
Related
- Microbiota-constrained bacterial density limits phage infection in the gut and allows persistence of susceptible cells
- When Raman Spectral Fidelity and Bacterial Classification Accuracy Diverge
- Sharpness-Aware Minimization (SAM) Improves Classification Accuracy of Bacterial Raman Spectral Data Enabling Portable Diagnostics
- Receptive-field-constrained stimulus optimization for human early and intermediate visual cortex
- Mutanome-guided immunopeptidomics of blood plasma for neoepitope detection in solid tumors is constrained by cfDNA variant calling sensitivity and MS detection limits
BibTeX
@misc{desai2026multitask,
title = {{Multi-Task Bacterial Colony Detection and Classification Using YOLOv8 with Edge Optimization for Resource-Constrained Deployment}},
author = {Belaguppa Manjunath Ashwin Desai and Rohan Rajesh and Shreyas Murthy and Pronama Biswas and Revathi Vaithiyanathan},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.09818},
eprint = {2609.09818},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.09818},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Multi-Task Bacterial Colony Detection and Classification Using YOLOv8 with Edge Optimization for Resource-Constrained Deployment
AU - Belaguppa Manjunath Ashwin Desai
AU - Rohan Rajesh
AU - Shreyas Murthy
AU - Pronama Biswas
AU - Revathi Vaithiyanathan
PY - 2026
DA - 2026/09/09
PB - arXiv
DO - 10.48550/arxiv.2609.09818
UR - https://arxiv.org/abs/2609.09818
AB - Manual counting and classification of bacterial colonies are critical yet labor-intensive tasks in microbiology, prone to human error particularly on densely populated plates. This work proposes a multi-task deep learning framework trained on the Annotated Germs for Automated Recognition (AGAR) dataset (18,000 images; 9,202 training / 3,067 testing) to automate Colony Forming Unit (CFU) enumeration and species classification. A custom multi-task CNN employing global regression served as the baseline, but demonstrated limited performance in clustered colony environments due to the absence of spatial localization. To address this, a YOLOv8 object detection architecture was adopted with high-resolution 1024x1024 inputs, enabling instance-level colony detection and label assignment. The model achieved a classification accuracy of 98.13% and a counting accuracy of 98.27% (within a 10-colony margin), demonstrating strong predictive capability. To bridge the gap between model performance and practical deployability, the trained model was optimized through unstructured and structured pruning, ONNX conversion, and reduced-precision inference (FP32, FP16, INT8). On a Raspberry Pi 4B, ONNX FP32 and FP16 variants offered the best balance between inference speed (~6.4s) and accuracy (MAE ~2.20). Unstructured pruning preserved predictive accuracy (MAE ~2.01) without runtime gains, while structured pruning resulted in significant accuracy degradation (MAE ~6.3), revealing the sensitivity of instance-level colony detection to architectural compression. These findings provide practical guidance for selecting optimization strategies in resource-constrained laboratory deployments.
ER -