Somatic cell count in buffalo milk using fuzzy clustering and image processing techniques
| Autor: | Viviani Gomes, Cristiano Hora de Oliveira Fontes, Camila Costa Baccili, Karen Nascimento da Silva, Adonias Magdiel Silva Ferreira, Gabriel Jesus Alves de Melo, Aline Silva Ramos |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Fuzzy clustering
Buffaloes Computer science 020209 energy MASTITE ANIMAL Cell Count Image processing Mastitis 02 engineering and technology Fuzzy logic Image Processing Computer-Assisted Photography 0202 electrical engineering electronic engineering information engineering Animals Preprocessor Segmentation Microscopy business.industry Pattern recognition General Medicine Thresholding Identification (information) Milk Female 020201 artificial intelligence & image processing Animal Science and Zoology Artificial intelligence business Somatic cell count Food Science |
| Zdroj: | Repositório Institucional da USP (Biblioteca Digital da Produção Intelectual) Universidade de São Paulo (USP) instacron:USP |
| ISSN: | 1469-7629 0022-0299 |
| DOI: | 10.1017/s0022029921000042 |
| Popis: | This research communication presents an automatic method for the counting of somatic cells in buffalo milk, which includes the application of a fuzzy clustering method and image processing techniques (somatic cell count with fuzzy clustering and image processing|, SCCFCI). Somatic cell count (SCC) in milk is the main biomarker for assessing milk quality and it is traditionally performed by exhaustive methods consisting of the visual observation of cells in milk smears through a microscope, which generates uncertainties associated with human interpretation. Unlike other similar works, the proposed method applies the Fuzzy C-Means (FCM) method as a preprocessing step in order to separate the images (objects) of the cells into clusters according to the color intensity. This contributes signficantly to the performance of the subsequent processing steps (thresholding, segmentation and recognition/identification). Two methods of thresholding were evaluated and the Watershed Transform was used for the identification and separation of nearby cells. A detailed statistical analysis of the results showed that the SCCFCI method is able to provide results which are consistent with those obtained by conventional counting. This method therefore represents a viable alternative for quality control in buffalo milk production. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|