Skip to main content

Food Image Analysis

Authored on
Kategorie

Trivializing, man is what he eats and drinks. Diet has a direct impact on our well-being, physical fitness, health and quality of life. This fact is an obvious motivation to carry out the work on the analysis of food quality. In our case, we offer means of such the analysis using computer vision and image processing methods.

Image

Some time ago we have demonstrated the utility of magnetic resonance imaging in food quality assessment. When the cost of this imaging modality decreases, we will be ready to apply our solutions for assessing the quality of food. By analyzing the texture of the image in cheeses, we evaluate the distribution of internal holes. As strange as it sounds, the type and arrangement of the holes in the cheese makes a difference. A similar analysis of color characteristics and texture of cold meats enables evaluation of grinding and composition, including fat content. After all, we want to eat tasty but not greasy. The results of our work also show that on the basis of tomographic images we can recognize varieties and we can qualitatively characterize vegetables and fruits, including potatoes, carrots, apples and probably many others.

Projekt Ziarno

We also have interesting information for those over the age of 18 and 21, for those who can and do appreciate the taste of beer. We can recognise varieties of malting barley from photographs. We have also shown that analysis of the shape, texture and colour of the surface of barley grains makes it possible to assess their quality, recognise typical damage, infections, and sort them.  

Projekt Ziarno

In image analysis, we not only apply available solutions such as deep neural networks. We mainly use our own developments, algorithms and software for research on food shape, colour and texture. We make some of our software available to others. An example is the open-source qmazda project, which includes tools for image segmentation, data extraction and classification. Using our programmes, it is possible to analyse plant varieties, assess food quality and build solutions to support producers, processors and consumers. We encourage all interested parties to contact us and collaborate.

Achievements
Seed - prototype
Seed - algorithms

 

0
Contact persons

 

  • Prof. Piotr M. Szczypiński, e-mail: piotr.szczypinski@p.lodz.pl
    Institute of Electronics, Lodz University of Technology
    tel.: +48 42631 2642

 

0
Relevant publications

 

0