Automatic segmentation and classification of human intestinal parasites from microscopy images

Human intestinal parasites constitute a problem in most tropical countries, causing death or physical and mental disorders. Their diagnosis usually relies on the visual analysis of microscopy images, with error rates that may range from moderate to high. The problem has been addressed via computational image analysis, but only for a few species and images free of fecal impurities. In routine, fecal impurities are a real challenge for automatic image analysis. We have circumvented this problem by a method that can segment and classify, from bright field microscopy images with fecal impurities, the 15 most common species of protozoan cysts, helminth eggs, and larvae in Brazil. Our approach exploits ellipse matching and image foresting transform for image segmentation, multiple object descriptors and their optimum combination by genetic programming for object representation, and the optimum-path forest classifier for object recognition. The results indicate that our method is a promising approach toward the fully automation of the enteroparasitosis diagnosis. © 2012 IEEE.

Estudo de métodos para classificação e localização precisa de padrões usando um sistema de luz estruturada

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Reconhecimento de cores de objetos e de alimentos de cromaticidades opostas por pintos de corte

The aim of this research was to evaluate, by preference tests, the ability of perception of broiler chicks in the recognition of objects and foods of different colors. The survey was conducted in Brazil and consisted in the conditioning of 60 sexed one-day-old chicks using 30 male chicks and 30 female chicks for three days with blue balls and red food colors chosen for having opposed chromaticities. After the conditioning phase, a preference test was performed, in which the animals were placed individually in the center of an arena test with four options: red food, blue food, red balls and blue balls. Each bird was measured for 10 minutes. Latency to the first peck and the number of pecks, the number of sequential pecks at each object type or food, the total time the bird in each occupied compartment and the first occupied slot were recorded. According to the results, female chicks are less inhibited when in contact with a new situation when compared with males. However, males were able to establish a standard environment in the conditioning phase and opted for the compartment which was closer to that situation, associating the blue color to the ball and red color to the food. Overall, among the types of object colors and between types of food colors, the birds took less time for the decision on the choice of blue food and blue ball, showing a greater attraction, at first, to this color. Between the two ball colors, shorter latency period, greater number of interactions as well as more time spent on site were related to the blue sphere, verifying greater preference for this object. When evaluating the types of food colors, it was observed that the highest averages related to the number of pecks, and sequential pecks occurred with red food. Therefore, it is concluded that the birds recognized the red and blue food object, with the blue color having greater attractiveness for broiler chicks when compared to red.

The effects of acute and chronic administration of phosphatidylserine on cell proliferation and survival in the dentate gyms of adult and middle-aged rats

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Reconhecimento de contorno de edifício em imagens de alta resolução usando os momentos complexos de Zernike

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)