Muti-Stage Hierarchical Food Classification

TL;DR

This paper introduces a hierarchical food classification framework that aligns food image analysis with nutritional databases by leveraging a new dataset and a multi-stage clustering approach to improve discriminative feature extraction.

Contribution

The work presents a novel multi-stage hierarchical classification method and a new dataset that incorporates nutritional information for more accurate food item recognition.

Findings

Achieved promising results on VFN-nutrient dataset

Improved classification accuracy over existing methods

Demonstrated effectiveness of hierarchical clustering approach

Abstract

Food image classification serves as a fundamental and critical step in image-based dietary assessment, facilitating nutrient intake analysis from captured food images. However, existing works in food classification predominantly focuses on predicting 'food types', which do not contain direct nutritional composition information. This limitation arises from the inherent discrepancies in nutrition databases, which are tasked with associating each 'food item' with its respective information. Therefore, in this work we aim to classify food items to align with nutrition database. To this end, we first introduce VFN-nutrient dataset by annotating each food image in VFN with a food item that includes nutritional composition information. Such annotation of food items, being more discriminative than food types, creates a hierarchical structure within the dataset. However, since the food item annotations are solely based on nutritional composition information, they do not always show visual relations with each other, which poses significant challenges when applying deep learning-based techniques for classification. To address this issue, we then propose a multi-stage hierarchical framework for food item classification by iteratively clustering and merging food items during the training process, which allows the deep model to extract image features that are discriminative across labels. Our method is evaluated on VFN-nutrient dataset and achieve promising results compared with existing work in terms of both food type and food item classification.