MarblingPredictor
Problem
Dry-cured ham is a traditional Mediterranean meat product consumed throughout the world. This product is very variable in terms of composition and quality. Consumer’s acceptability of this product is influenced by different factors, in particular, visual intramuscular fat and its distribution across the slice, also known as marbling. On-line marbling assessment is of great interest for the industry for classification purposes. However, until now this assessment has been traditionally carried out by panels of experts, which is tedious and very time-consuming to be implement in industry.
Proposed Solution: MarblingPredictor
We propose the software MarblingPredictor with a friendly graphical interface, which provide the following tools:
Predicts the marbling score of the three most representative ham muscles from square regions of interest automatically extracted from a ham slice.
Estimate the rate of subcutaneous and intermuscular fat content in the ham slice.
Predict the marbling score of regions manually drawn on the slices.
MarblingPredictos is very fast to analyse online ham slices on a general-purpose personal computer. MarblingPredictor software can competently support both basic research in food labs or can be embeded into industry systems.
Demostration video
Collaborators
Publications
Eva Cernadas, Manuel Fernández-Delgado, Elena Fulladosa and Israel Muñoz. Automatic marbling prediction of sliced dry-cured ham using image segmentation, texture analysis and regression, Expert Systemas with Applications, 206 (2022). 2022, 206, 117765 (DOI) (PDF).
Eva Cernadas, Manuel Fernández-Delgado, Manisha Sirsat, Elena Fulladosa and Israel Muñoz. MarblingPredictor: a software to analyse the quality of dry-cured ham slices, Meat Science, 2024, 109713 (DOI)
Downloads
Please, cite the paper above if you use the software MarblingPredictor in your research.
- Usage and installation instructions (PDF)
- Windows installer - setupMarblingPredictor.exe
- Ubuntu 20.04 installer - marblingpredictor_1.0_all.deb
Image and annotations dataset
The set of images and their annotations can be downloaded from the HamMarbling repository.
Información
-
- Investigadores
- Eva Cernadas García
- Manuel Fernández Delgado
- Elena Fulladosa
- Israel Muñoz