Abstract

Image classifiers work effectively when applied on structured images, yet they often fail when applied on images with very high visual complexity. This paper describes experiments applying state-of-the-art object classifiers toward a unique set of ‘images in the wild’ with high visual complexity collected on the island of Bali. The text describes differences between actual images in the wild and images from Imagenet, and then discusses a novel approach combining informational cues particular to video with an ensemble of imperfect classifiers in order to improve classification results on video sourced images of plants in the wild.

BibTex

@INPROCEEDINGS{Bohlen2021,
  author={Böhlen, Marc and Jain, Raunaq and Sujarwo, Wawan and Chandola, Varun},
  booktitle={2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)}, 
  title={From images in the wild to video-informed image classification}, 
  year={2021},
  pages={656-661},
  keywords={Visualization;Conferences;Machine learning;Complexity theory;Image classification;Artificial intelligence in environmental studies;photography;video;video structure;classification;images in the wild;neural network-based image classification},
  doi={10.1109/ICMLA52953.2021.00109}}