Dataset: Multiplexed Illumination for Classifying Visually Similar Objects
Access status:
Open Access
Type
DatasetAbstract
This dataset accompanies the paper Multiplexed Illumination for Classifying Visually Similar Objects. Project details are here: https://roboticimaging.org/Projects/LSClassifier/ The dataset contains 16000 10-bit images of five types of real and synthetic fruit. It is split across ...
See moreThis dataset accompanies the paper Multiplexed Illumination for Classifying Visually Similar Objects. Project details are here: https://roboticimaging.org/Projects/LSClassifier/ The dataset contains 16000 10-bit images of five types of real and synthetic fruit. It is split across three categories: Relightable models: high-quality single-illuminant images. These drive the pattern selection and classifier training, and can be used to devise and evaluate new multiplexing schemes. SNR-Optimal: Captured with inference-time conditions, with more evident noise, and with illumination patterns selected to be optimal in terms of signal-to-noise (SNR) ratio. Greedy: Also captured with inference-time conditions, these patterns were jointly trained along with the classifier using our proposed greedy pattern selection scheme. Preprint of paper available at: https://arxiv.org/abs/2009.11084
See less
See moreThis dataset accompanies the paper Multiplexed Illumination for Classifying Visually Similar Objects. Project details are here: https://roboticimaging.org/Projects/LSClassifier/ The dataset contains 16000 10-bit images of five types of real and synthetic fruit. It is split across three categories: Relightable models: high-quality single-illuminant images. These drive the pattern selection and classifier training, and can be used to devise and evaluate new multiplexing schemes. SNR-Optimal: Captured with inference-time conditions, with more evident noise, and with illumination patterns selected to be optimal in terms of signal-to-noise (SNR) ratio. Greedy: Also captured with inference-time conditions, these patterns were jointly trained along with the classifier using our proposed greedy pattern selection scheme. Preprint of paper available at: https://arxiv.org/abs/2009.11084
See less
Date
2020-01-01Publisher
The University of SydneyLicence
Copyright All Rights ReservedFaculty/School
Faculty of Engineering, School of Aerospace Mechanical and Mechatronic EngineeringDepartment, Discipline or Centre
Sydney Institute for Robotics and Intelligent SystemsShare