Multi-Modal Zero-Shot Prediction of Color Trajectories in Food Drying

2025-12-05

AI Summary

Accurate prediction of dynamic color evolution during food drying remains challenging, and existing low-dimensional color feature models suffer from poor generalizability across varying drying conditions. Method: This paper proposes a multimodal deep learning framework that jointly encodes high-dimensional temporal image features and process parameters, enabling the first zero-shot prediction of color trajectories across unseen drying conditions. The approach integrates temporal color dynamics with process variables and incorporates a zero-shot transfer strategy to overcome limitations imposed by conventional low-dimensional representations and condition-specific dependencies. Contribution/Results: Evaluated on biscuit and apple drying tasks, the method achieves RMSEs of 2.12 and 1.29, respectively—reducing prediction error by over 90% relative to baseline models. It significantly improves prediction accuracy, robustness, and cross-condition generalization capability.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Food drying is widely used to reduce moisture content, ensure safety, and extend shelf life. Color evolution of food samples is an important indicator of product quality in food drying. Although existing studies have examined color changes under different drying conditions, current approaches primarily rely on low-dimensional color features and cannot fully capture the complex, dynamic color trajectories of food samples. Moreover, existing modeling approaches lack the ability to generalize to unseen process conditions. To address these limitations, we develop a novel multi-modal color-trajectory prediction method that integrates high-dimensional temporal color information with drying process parameters to enable accurate and data-efficient color trajectory prediction. Under unseen drying conditions, the model attains RMSEs of 2.12 for cookie drying and 1.29 for apple drying, reducing errors by over 90% compared with baseline models. These experimental results demonstrate the model's superior accuracy, robustness, and broad applicability.

Problem

• Predicts color changes in food during drying
• Uses multi-modal data for unseen drying conditions
• Improves accuracy over low-dimensional feature methods

Innovation

• Integrates high-dimensional temporal color data with drying parameters
• Enables accurate color trajectory prediction under unseen conditions
• Achieves over 90% error reduction compared to baseline models