This study presents an innovative approach to the problem of stall number detection in dairy
farms, leveraging the power of deep learning and object detection models. An existing …

The automated identification of stall numbers [19] from cow teat images holds significant
promise in optimizing livestock management systems. In this study, various pre-trained …

This report outlines the development of a custom Convolutional Neural Network (CNN)
using PyTorch for image classification, leveraging a dataset comprising 1149 training …

Canine cardiomegaly detection requires precise Vertebral Heart Size (VHS) measurements
from thoracic radiographs. This study presents an automated solution using a fine-tuned …

This study presents a comprehensive comparative analysis of the YOLOv8 object detection
architecture and its two novel variations: YOLOv8-ConvNeXtV2 and YOLOv8-DyHead. The …

This report presents a comparison between two deep convolutional neural network models,
VGG16 and a homemade model based on VGG50, for cow teat image classification tasks …

This project focuses on detecting the number of stalls in a dataset of images using the
YOLOv5 object detection algorithm. The dataset comprises 1042 images for training and …

This research introduces a novel deep learning approach for keypoint detection in
radiographs to objectively measure heart size. By employing a state-of-the-art convolutional …

The segmentation of bird sound spectrograms is a critical task for bioacoustic analysis,
enabling more efficient ecological monitoring and sound event detection. This study …

This study presents a deep learning framework for detecting keypoints and estimating
vertebral heart size (VHS) from canine heart images. The proposed method utilizes a …