Colloquium Computer Science - Prof. P. Radeva University of Barcelona

Title: Uncertainty modeling within an End-to-end framework for Food Image Analysis

Abstract:

Recently, computer vision approaches specially assisted by deep learning techniques have shown unexpected advancements that practically solve problems that never have been imagined to be automatized like face recognition or automated driving. However, food image recognition due to its high complexity and ambiguitu, still remains far from being solved. In this project, we focus on how to combine two challenging research lines: deep learning and  uncertainty modeling (epistemic and aleatoric uncertainty). After discussing our methodology to advance in this direction, we comment potential applications, as well as social and economic impact of the research on food image analysis.