Computer Vision Methods for the Real Time Assessment of Dietary Intake

用于实时评估膳食摄入量的计算机视觉方法

• 批准号: 7405586
• 负责人: Alejandro Terrazas
• 金额: $ 19.17万
• 依托单位: MEDIABALANCE, INC.
• 依托单位国家: 美国
• 财政年份: 2007
• 资助国家: 美国
• 起止时间: 2007-09-24 至 2008-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/7405586
• 关键词: Address; Adherence; Algorithms; Area; Behavior; Behavioral; Biological Neural Networks; Biometry; Body Weight decreased; Calculi; Cellular Phone; Cessation of life; Class; Coin; Computer Vision Systems; Computer software; Data; Databases; Decision Trees; Diabetic Diet; Diet Records; Dietary intake; Disease; Eating; Eating Behavior; Face; Feedback; Fingerprint; Food; Food and Beverages; Goals; Habits; Health; Image; Individual; Information Theory; Intake; Iris; Life; Life Style; Lighting; Machine Learning; Maintenance; Marketing; Mathematics; Measurement; Measures; Methods; Monitor; Numbers; Nutritional; Nutritionist; Obesity; Obesity associated disease; Pattern Recognition; Phase; Placement; Principal Investigator; Public Health; Research; Research Personnel; Security; Shapes; Simulate; Small Business Funding Mechanisms; Small Business Innovation Research Grant; System; Techniques; Technology; Testing; Text; Three-Dimensional Image; Time; Training; Treatment Protocols; United States; Wing; base; design; digital imaging; disability; improved; innovation; instrument; interest; obesity treatment; research study; size; usability

DESCRIPTION (provided by applicant): Obesity is a leading cause of preventable death and disability in the U.S. Self- monitoring of all foods and beverages consumed is central to weight loss and maintenance efforts; however, this places a heavy burden on the user. These same burdens also impede nutritional research. The proposed research is for the testing of a semi-automated, objective, near real-time computer vision and pattern recognition approach to the measurement of dietary intake. In the proposed product, cell phone pictures of meals and snacks will be analyzed by software in an attempt to automatically recognize as many items as possible. A small number of intelligent yes/no questions will help provide additional information when necessary in order to meet the accuracy demands of the target application. Following identification of the items, the software will estimate the portion sizes of all identified items. The experiments comprising this Phase I SBIR are (a) extract the most informative sets of features using a large number of food and beverage items taken from an existing database of real world meal images, (b) compare the accuracy of candidate pattern recognition approaches to identify items based on the extracted features, (c) identify the most feasible algorithms for estimating portion size, and (d) test usability and user acceptance with a simulated version of the product. Phase II will (a) apply the approach to a greater variety of food and beverage items, (b) improve automated analysis, and (c) compare the approach to existing assessment instruments. This research will extend defense- and security-related technologies to the assessment and treatment of obesity.

描述（由申请人提供）：在美国，肥胖是可预防的死亡和残疾的主要原因。自我监控所消耗的所有食物和饮料对于减肥和维持体重至关重要；然而，这给用户带来了沉重的负担。这些同样的负担也阻碍了营养研究。拟议的研究旨在测试半自动、客观、近实时的计算机视觉和模式识别方法来测量膳食摄入量。在拟议的产品中，软件将分析手机上的餐食和零食图片，以尝试自动识别尽可能多的物品。少量智能是/否问题将有助于在必要时提供附加信息，以满足目标应用的准确性要求。识别物品后，软件将估计所有已识别物品的份量大小。第一阶段 SBIR 的实验包括：(a) 使用从现实世界膳食图像的现有数据库中获取的大量食品和饮料项目提取信息最丰富的特征集，(b) 比较候选模式识别方法的准确性根据提取的特征识别项目，(c) 识别估计份量大小的最可行算法，以及 (d) 使用产品的模拟版本测试可用性和用户接受度。第二阶段将（a）将该方法应用于更多种类的食品和饮料项目，（b）改进自动化分析，以及（c）将该方法与现有评估工具进行比较。这项研究将把国防和安全相关技术扩展到肥胖的评估和治疗。