Bulldogs Nose Detection using Deep Learning

• Joyce Katiuccia Medeiros Ramos Carvalho UCDB
• Pedro Henrique Neves da Silva UFMS https://orcid.org/0000-0002-6983-3049
• Sandra Adriana Uhry UCDB
• Gustavo da Silva Andrade UFMS https://orcid.org/0009-0004-0248-7083
• Gisele Braziliano de Andrade UCDB
• Hemerson Pistori UCDB https://orcid.org/0000-0001-8181-760X
• Newton Loebens UNIPAMPA https://orcid.org/0000-0001-6309-9309

Resumo

An animal nose identification system could allow efficient monitoring of pets, and it can be used in applications such as identifying animal breeds or possible diseases and/or injuries. For that, a bulldog image dataset was build from French bulldogs. To carry out the validation through cross-validation, 10 folds (K-folds) were created. Afterward, five convolutional neural networks (CNN) were trained with our dataset to identify the nose: Faster R-CNN (Region-based CNN), SABL (Side-Aware Boundary Localization), RetinaNet (ResNet50+FPN), VFNet (VarifocalNet), and ATSS (Adaptive Training Sample Selection). Faster R-CNN, SABL, RetinaNet, VFNet and ATSS were used for training in the first phase, while ATSS, Faster R-CNN, ATSS and SABL in the second. The results showed that the ATSS network obtained the highest values of mAP and Accuracy in the first phase. Moreover, SABL network achieved the highest values of mAP50, mAP75, Recall, F-Score and Accuracy at the end of the second phase.

Palavras-chave: Computer Vision, Neural Networks, Brachycephalic Obstructive Airway Syndrome, Stenotic Nares, Bulldogs Nose