# Efficient Microscopic Image Instance Segmentation for Food Crystal Quality Control

arXiv: https://arxiv.org/abs/2409.18291 · HTML: https://mlsanity.com/paper/2409.18291/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 26 Sep 2024.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019)
- [Cell Detection with Star-convex Polygons](https://mlsanity.com/paper/1806.03535/) (2018)
- [OccuSeg: Occupancy-aware 3D Instance Segmentation](https://mlsanity.com/paper/2003.06537/) (2020)
- [CIA-Net: Robust Nuclei Instance Segmentation with Contour-aware Information Aggregation](https://mlsanity.com/paper/1903.05358/) (2019)
- [Transformer based multiple instance learning for weakly supervised histopathology image segmentation](https://mlsanity.com/paper/2205.08878/) (2022)
- [Monocular Instance Motion Segmentation for Autonomous Driving: KITTI InstanceMotSeg Dataset and Multi-task Baseline](https://mlsanity.com/paper/2008.07008/) (2020)

## Built on by (most cited first, 2 of 2)

- [Confidence-aware agglomeration classification and segmentation of 2D microscopic food crystal images](https://mlsanity.com/paper/2507.23206/) (2025)
- [Instance camera focus prediction for crystal agglomeration classification](https://mlsanity.com/paper/2601.09004/) (2026)

## Abstract (arXiv)

This paper is directed towards the food crystal quality control area for manufacturing, focusing on efficiently predicting food crystal counts and size distributions. Previously, manufacturers used the manual counting method on microscopic images of food liquid products, which requires substantial human effort and suffers from inconsistency issues. Food crystal segmentation is a challenging problem due to the diverse shapes of crystals and their surrounding hard mimics. To address this challenge, we propose an efficient instance segmentation method based on object detection. Experimental results show that the predicted crystal counting accuracy of our method is comparable with existing segmentation methods, while being five times faster. Based on our experiments, we also define objective criteria for separating hard mimics and food crystals, which could benefit manual annotation tasks on similar dataset.