Instance camera focus prediction for crystal agglomeration classification

2026-01-13

AI Summary

This study addresses the challenge that two-dimensional microscopic images, constrained by limited depth of field, often misclassify crystals at different focal depths as agglomerates, thereby compromising analytical accuracy. To resolve this issue, the authors propose an instance-level focus state prediction network that integrates optical imaging characteristics with human visual perception mechanisms to accurately assess the focus state of each individual crystal. This focus-aware information is then incorporated into an instance segmentation–based agglomeration classification pipeline, effectively distinguishing genuine agglomerates from visually overlapping but physically separate crystals. Experimental results on datasets of ammonium perchlorate and sucrose crystals demonstrate that the proposed method significantly outperforms baseline models in both agglomeration classification and segmentation accuracy.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Agglomeration refers to the process of crystal clustering due to interparticle forces. Crystal agglomeration analysis from microscopic images is challenging due to the inherent limitations of two-dimensional imaging. Overlapping crystals may appear connected even when located at different depth layers. Because optical microscopes have a shallow depth of field, crystals that are in-focus and out-of-focus in the same image typically reside on different depth layers and do not constitute true agglomeration. To address this, we first quantified camera focus with an instance camera focus prediction network to predict 2 class focus level that aligns better with visual observations than traditional image processing focus measures. Then an instance segmentation model is combined with the predicted focus level for agglomeration classification. Our proposed method has a higher agglomeration classification and segmentation accuracy than the baseline models on ammonium perchlorate crystal and sugar crystal dataset.

Problem

• crystal agglomeration
• microscopic imaging
• depth of field
• focus prediction
• instance segmentation

Innovation

• instance focus prediction
• crystal agglomeration classification
• instance segmentation
• depth-aware imaging
• microscopic image analysis