Incremental learning to segment micrographs

We propose a simple segmentation framework based on classification and supervised incremental learning. A statistical model of pixel classes is learnt by incrementally adding new sample image patches to automatically-learned probability functions.
Image Analysis and Microscopy in Food Science: Computer Vision and Visual Inspection

When computer vision experts evaluate algorithms, they often focus on segmentation quality and optimisation of resources. On the other hand, they often neglect simplicity and interactivity.
Association of total mixed ration particle fractions retained on the Penn State Particle Separator with milk, fat, and protein yield lactation curves at the cow level

The objective of this study was to assess the association of particle size in TMR estimated using the Penn State Particle Separator with production of milk, fat, and protein on a representative sample of Ragusa dairy farms, while controlling for nutrient content.
Microstructural properties of milk fat globules

A method is presented to quantitatively measure structural changes induced by milk processing and storage, such as fat aggregation and milk fat globule membrane disruption, by analysing confocal micrographs.
Quantitative analysis of nanostructures’ shape and distribution in micrographs using image analysis

The objective of this study was to develop an automatic method to reproduce human-like discriminative capabilities in the context of microstructure evaluation.
Segmentation of structural features in cheese micrographs using pixel statistics

In this paper, a machine learning method was employed based on a statistical model of image pixels, learned from sample images by human training. The observation underlying to this class of segmentation
methods is that image pixels can be considered as a statistical population.
Incremental Learning to Segment Micrographs

The main problem of classication approaches is the long, tedious, human-intensive training phase. In our experience, an accurate image labelling can take several hours to an expert operator.
An Interactive Level Set Approach to Semi-automatic Detection of Features in Food Micrographs

In this paper, we propose a fast approximate level set algorithm for the detection of microstructural features in food micrographs. Our approximation method is in the spirit of. Hence, we chose a user-assisted approach. Approximating the exact evolution equation allows for interactive computations.