Search papers, labs, and topics across Lattice.
This paper introduces ACFamNet and ACFamNet Pro, extensions of the FamNet object counting technique, to address the challenges of counting small and clustered bacterial colonies in images. ACFamNet incorporates region of interest pooling with alignment and optimized feature engineering to handle small object sizes and clustering, while ACFamNet Pro further enhances the model with multi-head attention and residual connections for improved generalization. Experimental results demonstrate that ACFamNet Pro significantly outperforms existing methods, achieving a 9.64% MNAE, highlighting its effectiveness in automated bacterial colony counting.
Multi-head attention and residual connections can significantly boost the accuracy of object counting in clustered environments, enabling more reliable bacterial colony analysis.
Automated bacterial colony counting from images is an important technique to obtain data required for the development of vaccines and antibiotics. However, bacterial colonies present unique machine vision challenges that affect counting, including (1) small physical size, (2) object clustering, (3) high data annotation cost, and (4) limited cross-species generalisation. While FamNet is an established object counting technique effective for clustered objects and costly data annotation, its effectiveness for small colony sizes and cross-species generalisation remains unknown. To address the first three challenges, we propose ACFamNet, an extension of FamNet that handles small and clustered objects using a novel region of interest pooling with alignment and optimised feature engineering. To address all four challenges above, we introduce ACFamNet Pro, which augments ACFamNet with multi-head attention and residual connections, enabling dynamic weighting of objects and improved gradient flow. Experiments show that ACFamNet Pro achieves a mean normalised absolute error (MNAE) of 9.64% under 5-fold cross-validation, outperforming ACFamNet and FamNet by 2.23% and 12.71%, respectively.