Improving Food Detection For Images From a Wearable Egocentric Camera

TL;DR

This paper presents a method to improve food detection accuracy in images captured by a wearable eye-glass device by filtering out blurry images that hinder analysis performance.

Contribution

It introduces a pre-processing approach that rejects blurry images from the AIM device to enhance food detection accuracy in dietary assessment.

Findings

Filtering blurry images improves food detection performance.

The approach enhances the reliability of image-based dietary assessments.

Pre-processing reduces errors caused by poor image quality.

Abstract

Diet is an important aspect of our health. Good dietary habits can contribute to the prevention of many diseases and improve the overall quality of life. To better understand the relationship between diet and health, image-based dietary assessment systems have been developed to collect dietary information. We introduce the Automatic Ingestion Monitor (AIM), a device that can be attached to one's eye glasses. It provides an automated hands-free approach to capture eating scene images. While AIM has several advantages, images captured by the AIM are sometimes blurry. Blurry images can significantly degrade the performance of food image analysis such as food detection. In this paper, we propose an approach to pre-process images collected by the AIM imaging sensor by rejecting extremely blurry images to improve the performance of food detection.