Detection of Chicken Diseases from Fecal Images with the Pre-Trained Places365-GoogLeNet Model
İlkay Çınar
Abstract
A variety of chicken diseases pose significant challenges to chicken farmers worldwide, posing a threat to the safety of food and potentially resulting in economic losses. In this study, we propose the utilization of the pre-trained deep learning model, Places365-GoogLeNet, for the detection of chicken diseases from chicken fecal images, including Healthy, Coccidiosis, Salmonella, and New Castle Disease. By leveraging the powerful image analysis capabilities of deep learning, our approach achieves a remarkable classification accuracy of 98.91%. This accuracy surpasses the results reported in related studies in the literature. Moreover, our findings highlight the potential of artificial intelligence and machine learning techniques, particularly in the agricultural sector, for automated disease detection. The presented results not only contribute to early disease diagnosis and prompt intervention in poultry farming but also pave the way for future research to develop more advanced methods and utilize larger and diverse datasets to enhance the model's generalization ability.