You have requested a machine translation of selected content from our databases. This functionality is provided solely for your convenience and is in no way intended to replace human translation. Neither SPIE nor the owners and publishers of the content make, and they explicitly disclaim, any express or implied representations or warranties of any kind, including, without limitation, representations and warranties as to the functionality of the translation feature or the accuracy or completeness of the translations.
Translations are not retained in our system. Your use of this feature and the translations is subject to all use restrictions contained in the Terms and Conditions of Use of the SPIE website.
Chapter 12: DietCam: Multiview Regular-Shaped Food Recognition with a Camera Phone
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print format on
SPIE.org.
Abstract
Obesity has been a severe public health challenge to the general population and social welfare in many developed countries. In the past three decades, the obesity rate in has increased significantly, resulting in serious consequences such as diabetes, stroke, heart disease, and even cancer. Food intake assessment is significant for obesity management. However, few people are aware of their food intake, and most are not willing to assess food intake. The reason is the burdensome assessment methods and a lack of real-time feedback with these methods. Traditional food recording or food diary methods require manual records of the food type and the portion of the food taken, and the accuracy is influenced by human estimations of the food portions. Computer-aided and automatic food intake assessment methods provide a convenient channel for food intake monitoring, although robust and reliable methods are not available for real-time field applications.
Food recognition is a special case of category recognition for visual
object recognition in computer vision. The appearance of any particular meal is affected by many factors such as ingredients, cooking methods, cutting patterns, ingredient positions, occlusions, lighting conditions, etc. These factors are complex such that even meals of the same category may have different appearances. In contradiction, different types of food could have similar appearances that are difficult to distinguish by humans. These intraclass differences and interclass similarities make food recognition a challenging category recognition problem.
Online access to SPIE eBooks is limited to subscribing institutions.