Sistema WEB de controle de anemia em ovinos

Abstract

Haemonchus contortus is a nematode that infects various animal species, particularly small ruminants such as sheep. It is one of the main causative agents of anemia in these animals, a condition that leads to weight loss, wool reduction, and decreased milk production, thereby causing financial losses to farmers and a reduction in overall productivity. Currently, several strategies exist to mitigate this problem, mainly through the use of anthelmintics that effectively control this parasite. However, their administration must be carefully managed and correctly applied to prevent the development of resistance. Unfortunately, in many cases this is not observed. A considerable number of farmers apply these products indiscriminately, either by increasing or reducing the prescribed dose, which contributes to the selection of resistant parasite populations. Accurate identification of anemia within the herd is often a critical factor for effective control, as animals are frequently diagnosed only after exhibiting severe clinical signs such as significant weight loss, wool depletion, and general debilitation. One effective tool for early identification of anemia is the FAMACHA© card, which assists farmers in determining the health status of animals by comparing the color of the ocular mucosa with a standardized color scale. Nevertheless, access to this tool presents challenges related to cost, proper use, and correct interpretation. Considering these issues, and given that sheep farming represents an important source of income for the population of Northeastern Brazil, the present study proposes a methodology that integrates a web-based system for selective anemia control in with a mobile application. These two components operate in a unified manner: the application enables the capture of ocular mucosa images and provides immediate feedback on whether the animal is anemic, while the web system offers more comprehensive and robust management capabilities. The platform allows for the analysis, monitoring, and understanding of the dynamics of anemia propagation caused by the parasite in the region, in addition to generating reports and incorporating Machine Learning and Computer Vision models to detect the ocular mucosa and classify it as healthy or anemic.