Dataset

This dataset was created by Roudranil Das

Contents

The duck image dataset is a curated collection of digital images featuring various species of ducks in diverse environments and poses. This dataset encompasses a wide range of images captured from different angles, lighting conditions, and backgrounds, providing a comprehensive representation of ducks in natural habitats. The images may include single or multiple ducks, swimming, flying, resting, or engaging in other behaviors commonly observed in ducks. Each image is labeled with relevant metadata, such as the species of duck depicted, location, and potentially additional annotations for specific attributes or actions. This dataset serves as a valuable resource for research and development in computer vision, wildlife biology, ecological studies, and related fields, facilitating tasks such as species recognition, behavior analysis, and habitat monitoring.

Dataset

This dataset was created by Nothing_None_123

Released under MIT

Contents

Duck Hunt Object Detection Dataset

This dataset contains 1,004 labeled images from the classic NES game "Duck Hunt" (1984), specifically prepared for YOLO (You Only Look Once) object detection training. The dataset includes sprites of the iconic hunting dog and ducks in various states, augmented to provide a balanced and comprehensive training set for computer vision models.

Perfect for: - Object detection model training - Computer vision research - Retro gaming AI projects - YOLO algorithm benchmarking - Educational purposes

🎯 Dataset Statistics

Class Distribution

📁 Dataset Structure

yolo_dataset_augmented/
├── images/
│  ├── train/      # 711 training images
│  └── val/       # 260 validation images
├── labels/
│  ├── train/      # 711 YOLO annotation files
│  └── val/       # 260 YOLO annotation files
├── classes.txt     # Class names mapping
├── dataset.yaml     # YOLO configuration file
└── augmented_dataset_stats.json # Detailed statistics

🔧 Data Augmentation Details

The original 47 images were enhanced using advanced data augmentation techniques to create a balanced dataset:

Augmentation Techniques Applied:

• Geometric Transformations: Rotation (±15°), horizontal/vertical flipping, scaling (0.8-1.2x), translation
• Color Adjustments: Brightness (0.7-1.3x), contrast (0.8-1.2x), saturation (0.8-1.2x)
• Quality Variations: Gaussian noise, slight blur for robustness
• Advanced Techniques: Mosaic augmentation (YOLO-style 4-image combination)

Augmentation Parameters:

{
  'rotation_range': (-15, 15),    # Small rotations for game sprites
  'brightness_range': (0.7, 1.3),  # Brightness variations
  'contrast_range': (0.8, 1.2),   # Contrast adjustments
  'saturation_range': (0.8, 1.2),  # Color saturation
  'noise_intensity': 0.02,      # Gaussian noise
  'horizontal_flip_prob': 0.5,    # 50% chance horizontal flip
  'scaling_range': (0.8, 1.2),    # Scale variations
}

🚀 Usage Examples

Loading with YOLOv8 (Ultralytics)

from ultralytics import YOLO

# Load and train
model = YOLO('yolov8n.pt') # Load pretrained model
results = model.train(data='dataset.yaml', epochs=100, imgsz=640)

# Validate
metrics = model.val()

# Predict
results = model('path/to/test/image.png')

Loading with PyTorch

import torch
from torch.utils.data import Dataset, DataLoader
from PIL import Image
import os

class DuckHuntDataset(Dataset):
  def _init_(self, images_dir, labels_dir, transform=None):
    self.images_dir = images_dir
    self.labels_dir = labels_dir
    self.transform = transform
    self.images = os.listdir(images_dir)
  
  def _len_(self):
    return len(self.images)
  
  def _getitem_(self, idx):
    img_path = os.path.join(self.images_dir, self.images[idx])
    label_path = os.path.join(self.labels_dir, 
                 self.images[idx].replace('.png', '.txt'))
    
    image = Image.open(img_path)
    # Load YOLO annotations
    with open(label_path, 'r') as f:
      labels = f.readlines()
    
    if self.transform:
      image = self.transform(image)
      
    return image, labels

# Usage
dataset = DuckHuntDataset('images/train', 'labels/train')
dataloader = DataLoader(dataset, batch_size=32, shuffle=True)

YOLO Annotation Format

Each .txt file contains one line per object: class_id center_x center_y width height

Example annotation: 0 0.492 0.403 0.212 0.315 Where values are normalized (0-1) relative to image dimensions.

📊 Technical Specifications

• Image Dimensions: Variable (original sprite sizes preserved)
• Color Channels: RGB (3 channels)
• Annotation Precision: Float32 (normalized coordinates)
• File Naming: Descriptive names indicating class and augmentation type
• Quality: High-resolution pixel art sprites

🎮 Dataset Context

This dataset is based on sprites from the iconic 1984 NES game "Duck Hunt," one of the most recognizable video games in history. The game featured:

• The Dog: Your hunting companion who retrieves ducks and ...

Dataset

This dataset was created by Patricia-2025131053

Released under CC0: Public Domain

Contents

The dataset contains sample images from the Open Images Dataset v7. This dataset only contains images for the category 'ducks' and is arranged to fine-tune the YOLOv8 image segmentation models.

Directories:

The dataset contains two main directors, i.e., images and labels. These directories further contain 'train' and 'val' directories. As the names suggest, these directories contain images and labels for the training and validation of image segmentation models.

Dataset Description:

Training Images: 400 Validation Images: 50

Class/es: Duck

config.yaml

The dataset also contains a config.yaml file. This file contains paths for relevant directories that YOLOv8 needs to load datasets

Dataset

This dataset was created by badar sultan

Released under CC0: Public Domain

Contents

Dataset

This dataset was created by MinhDND

Released under Apache 2.0

Contents

Dataset

This dataset was created by Rizki Ramdhan Hilal

Released under Database: Open Database, Contents: © Original Authors

Contents

Dataset

This dataset was created by Huy Tran Duck

Contents

Dataset

This dataset was created by CPMP

Released under CC0: Public Domain

Contents

This purpose of this dataset is to provide data:

• photos already rotated
• video : animation of all photos rotating

... so it will be easy to anyone to play with Rabbit–duck illusion

https://upload.wikimedia.org/wikipedia/commons/thumb/1/1d/Kaninchen_und_Ente.svg/250px-Kaninchen_und_Ente.svg.png" alt="">

Dataset

This dataset was created by Siva krishna Thota

Contents

Dataset

This dataset was created by Huy Tran Duck

Released under Apache 2.0

Contents

Dataset

This dataset was created by Vaishali Agarwal

Contents

Dataset

This dataset was created by Johar M. Ashfaque

Contents

Context

This data set includes metadata and vectors representing images in the Drinking Waste Classification data set. The metadata and image vectors are retained as a separate data set in order to save on calculation time during a workshop demo. The metadata and image vectors are generated by the Drinking Waste Data Exploration and CV Design notebook.

The image vectors are extracted by chopping the last few layers off a pretrained neural network (resnet18).

Acknowledgements

The processed data in this data set is based on the data in the Drinking Waste Classification data set.

Workshop Exercises

Suggested exercises for workshop participants are included in the Drinking Waste Data Exploration and CV Design notebook..

Dataset

This dataset was created by Huy Tran Duck

Contents

Dataset

This dataset was created by Tho_Kieu_US

Released under CC BY-NC-SA 4.0

Contents

Dataset

This dataset was created by zh xyu

Contents