Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SPOTS-10: Animal Pattern Benchmark Dataset for Machine Learning Algorithms

John Atanbori

TL;DR

The SPOTS-10 dataset is an extensive collection of grayscale images showcasing diverse patterns found in ten animal species, divided into ten categories, with 5,000 images per category, to provide a resource for evaluating machine learning algorithms in situ.

Abstract

Recognising animals based on distinctive body patterns, such as stripes, spots, or other markings, in night images is a complex task in computer vision. Existing methods for detecting animals in images often rely on colour information, which is not always available in night images, posing a challenge for pattern recognition in such conditions. Nevertheless, recognition at night-time is essential for most wildlife, biodiversity, and conservation applications. The SPOTS-10 dataset was created to address this challenge and to provide a resource for evaluating machine learning algorithms in situ. This dataset is an extensive collection of grayscale images showcasing diverse patterns found in ten animal species. Specifically, SPOTS-10 contains 50,000 32 x 32 grayscale images, divided into ten categories, with 5,000 images per category. The training set comprises 40,000 images, while the test set contains 10,000 images. The SPOTS-10 dataset is freely available on the project GitHub page: https://github.com/Amotica/SPOTS-10.git by cloning the repository.

SPOTS-10: Animal Pattern Benchmark Dataset for Machine Learning Algorithms

TL;DR

The SPOTS-10 dataset is an extensive collection of grayscale images showcasing diverse patterns found in ten animal species, divided into ten categories, with 5,000 images per category, to provide a resource for evaluating machine learning algorithms in situ.

Abstract

Recognising animals based on distinctive body patterns, such as stripes, spots, or other markings, in night images is a complex task in computer vision. Existing methods for detecting animals in images often rely on colour information, which is not always available in night images, posing a challenge for pattern recognition in such conditions. Nevertheless, recognition at night-time is essential for most wildlife, biodiversity, and conservation applications. The SPOTS-10 dataset was created to address this challenge and to provide a resource for evaluating machine learning algorithms in situ. This dataset is an extensive collection of grayscale images showcasing diverse patterns found in ten animal species. Specifically, SPOTS-10 contains 50,000 32 x 32 grayscale images, divided into ten categories, with 5,000 images per category. The training set comprises 40,000 images, while the test set contains 10,000 images. The SPOTS-10 dataset is freely available on the project GitHub page: https://github.com/Amotica/SPOTS-10.git by cloning the repository.

Paper Structure

This paper contains 4 sections, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. The SPOTS-10 Dataset
  3. Baseline Experiments
  4. Conclusion

Figures (5)

  • Figure 1: Sample images of a leopard and a hyena are partially occluded by plants. This is a common situation in animal species datasets, as these animals often hide to ambush their prey. Therefore, the only visible features for identification are partial distinct markings that can be spotted through the bushes.
  • Figure 2: Randomly create non-fully overlapping 90x90 patches from the Tiger category, with a maximum of six patches per image.
  • Figure 3: Visualization of the conversion pipeline: RGB image converted to grayscale, followed by the application of inverse gamma correction of 0.9.
  • Figure 4: Shows varying samples from the complete dataset for each of the ten classes, including the class ID (label ID) and class names.
  • Figure 5: Shows the student model architecture used to emulate the behaviour of the base teacher models.