This research proposes an automatic approach for classifying pigeon pox lesions using the DenseNet model, a deep learning architecture renowned for its dense connectivity patterns and efficient feature reuse. Pigeon pox, caused by the avipox virus, poses significant threats to avian populations and the poultry industry worldwide. Traditional diagnostic methods are laborious and time-consuming, prompting the exploration of machine learning techniques for automated disease diagnosis. The proposed approach leverages DenseNet for feature extraction from pigeon pox images, aiming to develop a robust and accurate classification system capable of distinguishing between healthy and infected birds based on visual features extracted from skin lesions. The study systematically evaluates the performance of the DenseNet model, demonstrating exceptional discriminatory power with an AUC of 0.99, accuracy of 0.98, and F1-score of 0.98. Comparative analysis with other deep learning models further validates DenseNet's superiority in pigeon pox classification. Overall, the proposed approach offers a promising solution for the early detection and control of pigeon pox, thereby improving bird health and welfare while mitigating economic losses in the poultry industry.

Accurate identification and classification of intestinal parasitic eggs are essential for effectively diagnosing and treating parasitic infections. Traditional manual microscopic diagnosis methods are time-consuming and prone to errors. Recent advancements in technology have shown potential in automating this process, yet more advanced and accurate methods are needed to overcome existing challenges. The proposed research aims to develop a robust and efficient approach for intestinal parasitic egg segmentation and classification using the Mask R-CNN algorithm. The research begins with an extensive review of existing literature on intestinal parasitic infections, their impact, and the limitations of current diagnostic methods. It further explores the principles of image processing, medical imaging techniques, and the fundamentals of the Mask R-CNN algorithm. The proposed work involves accessing a dataset comprising 10 thousand images of 10 different types of parasitic eggs from IEEE and preprocessing them to enhance their quality. The Mask R-CNN algorithm is then trained on this dataset, enabling it to accurately segment and classify intestinal parasitic eggs. Performance evaluation uses quantitative measures such as Precision, recall, and F1-score (shown in Table [1](#tbl-cap-0001)). The results demonstrate the effectiveness of the Mask R-CNN algorithm in segmenting and classifying intestinal parasitic eggs, achieving an overall accuracy of 95%. These findings contribute to intestinal parasitic egg analysis by providing an advanced and automated approach for SegmentationSegmentation and classification. Future research endeavors could expand the dataset, optimise computational efficiency, and integrate the developed algorithm into practical diagnostic tools.