CVJun 15, 2017

Arabian Horse Identification Benchmark Dataset

arXiv:1706.04870v11 citations
Originality Synthesis-oriented
AI Analysis

This provides a standardized resource for researchers developing and testing identification algorithms for Arabian horses, but it is incremental as it focuses on a specific domain without introducing new methods.

The authors tackled the lack of a standard dataset for Arabian horse identification by creating a benchmark dataset of 300 color muzzle print images from 50 horses, designed to simulate real-world conditions with variations in quality and degradation factors.

The lack of a standard muzzle print database is a challenge for conducting researches in Arabian horse identification systems. Therefore, collecting a muzzle print images database is a crucial decision. The dataset presented in this paper is an option for the studies that need a dataset for testing and comparing the algorithms under development for Arabian horse identification. Our collected dataset consists of 300 color images that were collected from 50 Arabian horse muzzle species. This dataset has been collected from 50 Arabian horses with 6 muzzle print images each. A special care has been given to the quality of the collected images. The collected images cover different quality levels and degradation factors such as image rotation and image partiality for simulating real time identification operations. This dataset can be used to test the identification of Arabian horse system including the extracted features and the selected classifier.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes