Comparative Analysis of Different Methods for Classifying Polychromatic Sketches

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Baba, Fahd, Mack, Devon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912320640253952
author Baba, Fahd
Mack, Devon
author_facet Baba, Fahd
Mack, Devon
contents Image classification is a significant challenge in computer vision, particularly in domains humans are not accustomed to. As machine learning and artificial intelligence become more prominent, it is crucial these algorithms develop a sense of sight that is on par with or exceeds human ability. For this reason, we have collected, cleaned, and parsed a large dataset of hand-drawn doodles and compared multiple machine learning solutions to classify these images into 170 distinct categories. The best model we found achieved a Top-1 accuracy of 47.5%, significantly surpassing human performance on the dataset, which stands at 41%.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08186
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Comparative Analysis of Different Methods for Classifying Polychromatic Sketches
Baba, Fahd
Mack, Devon
Computer Vision and Pattern Recognition
Image classification is a significant challenge in computer vision, particularly in domains humans are not accustomed to. As machine learning and artificial intelligence become more prominent, it is crucial these algorithms develop a sense of sight that is on par with or exceeds human ability. For this reason, we have collected, cleaned, and parsed a large dataset of hand-drawn doodles and compared multiple machine learning solutions to classify these images into 170 distinct categories. The best model we found achieved a Top-1 accuracy of 47.5%, significantly surpassing human performance on the dataset, which stands at 41%.
title Comparative Analysis of Different Methods for Classifying Polychromatic Sketches
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.08186