I-Corps: Software application for predicting consumer food acceptability based on appearances under different illumination conditions

这个i-Corps项目的更广泛的影响/商业潜力是开发一个软件应用程序，以预测消费者在不同照明条件下的接受度。所提出的技术专注于与食品外观相关的消费者可接受性预测，评估外部照明可能如何影响基于深度学习的图像理解模型。消费者可能会从拟议的技术中受益，因为他们可以更准确地了解他们购买的产品，并降低风险。此外，这项拟议的技术可能被用来推荐正确的光照水平，这可能有助于减少食物浪费。有了适当的照明建议，零售商可能会发现购买增加和显著节省成本，因为可能会减少产品退货。这个i-Corps项目基于开发的照明估计深度学习模型，可以用来预测食品的可接受性。光照估计是许多计算机视觉应用的基本前提。非自然光照可能会影响人们对商品基本特征的感知，例如零售店中的食品在不同的光照条件下。当食品被放置在不同的光照条件下时，消费者对产品的反应会有所不同，这可能会进一步影响购买决策。目标是开发一种照明人类可接受性预测模型，可用于一般工业制造和检查应用。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this I-Corps project is the development of a software application to predict consumer acceptability under different illumination conditions. The proposed technology is focused on consumer acceptability prediction related to food appearance, evaluating how external illumination may affect a deep learning-based image understanding model. Consumers may benefit from the proposed technology by having a more accurate understanding of the products they purchase and a reduced risk. In addition, the proposed technology may be used to recommend the correct illumination levels, which may help reduce food waste. With proper illumination recommendations, retailers may find an increase in purchases and a significant cost-savings as there may be a reduction in product returns.This I-Corps project is based on the development of an illumination estimation deep learning model that may be used to predict food acceptability. Illumination estimation is a fundamental prerequisite for many computer vision applications. Unnatural illumination may influence human perceptions of essential characteristics of goods, e.g., food products in retail stores under different lighting conditions. When food products are placed under different lighting conditions, consumers feel differently in response to the products, which may further affect purchase decisions. The goal is to develop an illumination human acceptability prediction model, which may be transferred to general industrial manufacturing and inspection applications.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.