SBIR Phase IB: A multispectral system for real-time prediction of beef tenderness

SBIR IB 期：实时预测牛肉嫩度的多光谱系统

• 批准号: 1003673
• 负责人: Chris Calkins
• 金额: $ 5万
• 依托单位: Goldfinch Solutions, LLC
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-01-01 至 2010-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1003673&HistoricalAwards=false
• 关键词: SBIR; Phase; IB; multispectral; system

This Small Business Innovation Research Phase I project seeks to determine the feasibility of a multispectral imaging technology, to provide real time beef tenderness prediction. The hypothesis is that it is possible to predict the tenderness of beef using only a moderate number of bands for the image. This is based on the observation that hyperspectral images contain large amounts of redundant information. The technological challenge is to verify the hypothesis by identifying the key bands that are central to tenderness prediction and to develop a model to accurately predict tenderness. Identification of key bands will be performed using data mining and image analysis algorithms. Successful verification of the hypothesis will directly lead to the development of a multispectral system for tenderness prediction at commercial speeds. Currently there are limited methods for real time classification of beef by tenderness, the most important trait influencing consumer satisfaction. Meat packers have expressed a desire to sort by tenderness, because consumers are willing to pay a premium for steaks that are guaranteed tender (an added value of $170 to $421 per carcass certified as tender). Some of the major packers have expressed interest in a service to classify beef for tenderness. At 2.5% of value added per head for 20% of the cattle, annual revenue of $23.7 million to $58.7 million could be generated from service sales to the top four U.S. meat packers. International potential would magnify this effect. This project, if successful, is expected to enhance economic opportunities for cattle producers and processors by improving assessment of beef product quality to meet consumer expectations. This award is funded under the American Recovery and Reinvestment Act of 2009 (Public Law 111-5).

这个小企业创新研究第一阶段项目旨在确定多光谱成像技术的可行性，以提供真实的时间牛肉嫩度预测。该假设是，它是可能的预测牛肉的嫩度只使用一个中等数量的波段的图像。这是基于观察到高光谱图像包含大量冗余信息。技术上的挑战是通过识别对嫩度预测至关重要的关键带来验证这一假设，并开发一个模型来准确预测嫩度。将使用数据挖掘和图像分析算法识别关键条带。假设的成功验证将直接导致在商业速度的嫩度预测的多光谱系统的发展。目前有有限的方法真实的时间分类的牛肉嫩度，最重要的性状影响消费者满意度。肉类包装商表示希望根据嫩度进行分类，因为消费者愿意为保证嫩度的牛排支付额外费用（每具经认证嫩度的胴体增加170至421美元的价值）。一些主要的包装商表示有兴趣提供一项服务，对牛肉进行嫩度分类。按照20%的牛的人均增加值的2.5%计算，向美国四大肉类包装商提供的服务销售每年可产生2370万至5870万美元的收入。国际潜力将放大这一影响。该项目如果成功，预计将通过改善牛肉产品质量评估，满足消费者的期望，增加牛生产者和加工者的经济机会。该奖项是根据2009年美国复苏和再投资法案（公法111-5）资助的。