Resumen

ALVES DE MELO, Gabriel Jesus et al. Method for somatic cell count in bovine milk images captured from optical microscope. Zootecnia Trop. [online]. 2014, vol.32, n.1, pp.77-82. ISSN 0798-7269.

This work presents a hybrid segmentation method for counting somatic cells in bovine milk images, intended to detect an infection known as mastitis, which is the major cause of loss in dairy farming. By applying image processing techniques that use cell morphology it was possible to develop an algorithm capable of detecting and segmenting those cells. The segmentation is accomplished employing a new thresholding procedure to eliminate background and other residues. The remaining connected cells are separated in the fi nal segmentation step, by the use of the watershed transform. The experimental results were obtained using a large set of images from different sources. A performance comparison between the manual counting and the proposed method indicates that the later one is a promising solution to automate systems for detection of bovine mastitis via optical microscopy.

Palabras clave : image processing; microscopy video; watershed transform; somatic cells.

        · resumen en Español | Portugués     · texto en Portugués     · Portugués ( pdf )