- Tao, Yang
- University of Maryland - College Park
- Start date
- End date
- The overall objective is to develop an on-line non-invasive technology that uses infrared imaging, laser range imaging, and time-series analysis to estimate the internal temperature of meat after cooking and to identify the coldest/hottest spots inside each meat piece on the cooking line. The proposed system will be confined to dynamic internal temperature estimation under laboratory test scales and speed.
The supporting objectives are:
- To develop an infrared imaging system and time-series based model for rapid estimation of meat internal temperature after cooking.
- To develop a laser range imaging system to extract 3-D shapes of boneless meat pieces.
- To combine the infrared imaging and 3-D information to identify the coldest/hottest spots inside the meat.
- More information
- NON-TECHNICAL SUMMARY: Consumption of ready-to-eat boneless chicken meat by American consumers is increasing annually. They are demanding consistently high-quality, low-cost chicken meat, along with the USDA assurance of food safety. The poultry processing industry faces a constant challenge to achieve the right temperature point in meat pieces on high-volume cooking lines that preserves yield and quality and also complies with USDA regulations. This project will develop an on-line, non-invasive technology that uses infrared and laser imaging to estimate the internal temperature of meat after cooking and to identify the coldest/hottest spots inside each meat piece on the cooking line. This 100% inspection would replace the current inspection practice which samples random pieces of meat and is slow, invasive, and susceptible to cross-contamination. The results from this study will create a new technology for on-line, non-contact monitoring for poultry meat cooking processes and will aid quality-control personnel to enhance the quality and safety of ready-to-eat boneless chicken products for the American consumer.
APPROACH: An infrared focal planar array camera will be setup to capture surface temperature distribution images of each meat portion immediately after cooking, and to detect areas with the lowest temperature value. The camera's field of view will capture multiple images. A non-invasive laser-based high-resolution range imaging system will provide 3-D information for volume and thickness measurement, indicating the most probable coldest/hottest spots inside the meat. Calibration based on a time series model will determine the temperature of most probable coldest/hottest spots in the meat, according to type of product and specific cooking conditions. A machine vision system will acquire, interpret and combine the IR thermograms and range images in real-time. The calibration data will originate from experiments that establish the statistical relationship between internal and external temperatures, as related to the thickness, mass, emissivity, cooking conditions, and type of meat. If the temperatures of the products differ largely, or the products are being overcooked, a signal for oven temperature adjustment will be generated. Similarly, if meat is identified having a spot colder than the minimum required temperature, a signal will be generated to remove the meat from the line for extra heating.
PROGRESS: 2000/09 TO 2004/03
Foodborne diseases caused by undercooked poultry fillets are significant problems that have changed the direction of research toward the assessment of internal temperatures in poultry meat during cooking. Based on the previous research results, a laser range imaging system was added for the geometrical information. A novel infrared and laser range imaging system has been developed to estimate the internal temperatures of chicken breasts during cooking. It consists of three subsystems: an infrared imaging system, a laser range imaging system, and a neural network modeling system. The infrared imaging is used to determine the surface temperature of chicken breasts during cooking. The laser range imaging is used to reconstruct the 3D images of chicken breasts. Then, the neural network model is developed to predict internal temperatures in chicken breasts based on surface temperatures and geometric information. The experimental results show that geometric variables play an important role in internal temperature estimation. By using three time-lagged sequential infrared images and the geometric information, the system can predict the temperature with the accuracy of 1.54oC for mean absolute error, 2% for mean absolute percent error, and 3.08oC2 for mean square error. The combined infrared and laser range imaging show the potential for real-time, non-contact, and non-invasive estimation of internal temperatures of chicken breasts. It has no cross-contamination and can be used as a new inspection tool for enhanced food quality and safety. Therefore, the results from this study has successfully met the objectives of the research project for a new technology for on-line, non-contact monitoring for poultry meat cooking processes, thereby aiding the quality-control personnel to enhance the quality and safety of ready-to-eat boneless chicken products for consumers.
IMPACT: 2000/09 TO 2004/03
The poultry processing industry faces a constant challenge to achieve the right temperature point in meat pieces on high-volume cooking lines that preserves yield and quality and also complies with USDA regulations for food safety. This project creates a non-invasive technology that uses infrared and laser imaging to estimate the internal temperature of meat after cooking and to identify the coldest/hottest spots inside each meat pieces on the cooling line. The technique will enable inspection of every meat pieces on lines and would replace the current manual inspection practice, which samples random pieces of meat and is slow, invasive, and susceptible to cross-contamination. It will add quality-control personnel to enhance the safety and quality of ready-to-eat boneless chicken products for consumers.
- Funding Source
- Nat'l. Inst. of Food and Agriculture
- Project source
- View this project
- Project number
- Accession number
- Prevention and Control
- Food Preparation and Handling
- Natural Toxins
- Viruses and Prions
- Bacterial Pathogens
- Chemical Contaminants
- Meat, Poultry, Game