Multiplexed Illumination for Classifying Visually Similar Objects
This work addresses the challenge of distinguishing indistinguishable objects for applications like forgery detection and quality control, though it is incremental as it builds on existing illumination-based methods.
The paper tackles the problem of classifying visually similar objects, such as forged/authentic bills or healthy/unhealthy plants, by proposing multiplexed illumination to extend classifier capabilities, demonstrating a marked improvement over fixed-illuminant approaches on fruit samples.
Distinguishing visually similar objects like forged/authentic bills and healthy/unhealthy plants is beyond the capabilities of even the most sophisticated classifiers. We propose the use of multiplexed illumination to extend the range of objects that can be successfully classified. We construct a compact RGB-IR light stage that images samples under different combinations of illuminant position and colour. We then develop a methodology for selecting illumination patterns and training a classifier using the resulting imagery. We use the light stage to model and synthetically relight training samples, and propose a greedy pattern selection scheme that exploits this ability to train in simulation. We then apply the trained patterns to carry out fast classification of new objects. We demonstrate the approach on visually similar artificial and real fruit samples, showing a marked improvement compared with fixed-illuminant approaches as well as a more conventional code selection scheme. This work allows fast classification of previously indistinguishable objects, with potential applications in forgery detection, quality control in agriculture and manufacturing, and skin lesion classification.