Her Majesty the Queen in Right of Canada, As Represented by the Minister

Agri-food Canada

Alan Kwai-Wah Tong

Allan L Schaefer

Stephen D Jones

Richard C Graham

Shannon L Scott

Tong Liu

Claude D Gariepy

David John Robinson

A process for determining a tissue composition characteristic of a live animal or carcass involves the steps of: (a) obtaining either or both of at least one infrared thermographic image of the animal while it is alive, taken from at least one view, or at least one image of the carcass of the animal after slaughter, taken from at least one view, each thermographic image being capable of being represented as an array of pixels providing temperature data representative of temperature information at the corresponding part of the image; (b) calculating the value of at least one statistical measure of the temperature data for each thermographic image; (c) providing a predictive model wherein the tissue composition characteristic is included as an output variable, and the statistical measures of temperature data for each thermographic image are included as input variables; and (d) solving the predictive model to provide the value of the tissue composition characteristic. The process of the invention is useful in a wide variety of homoeotherinic animals. Tissue composition characteristics of interest include, without limitation, lean body mass, grade, carcass yield and rib eye area. An apparatus for performing the processes of the invention includes: (a) image acquisition means for obtaining the infrared thermographic images; (b) computing and storage means for storing each image as an array of pixels, calculating the value of statistical measures of the temperature data for each thermographic image, and providing and solving the predictive model; and (c) output means for providing an output of the value of the tissue composition characteristic.

Process for determining a tissue composition characteristic of an animal

In a process and apparatus for determining grading parameters of a carcass, the outline of an image of the carcass is traced and reference points representing anatomical features of the carcass are identified. Second reference points being located at pre-determined positions relative to the first reference points are then identified. The carcass image is divided into a plurality of sections, the boundaries of each section being determined as a function of the position of the first and second reference points, and the area of each section is determined. A grading parameter predictive equation is determined wherein the grading parameter is included as a dependent variable, and at least one area of a carcass image section is included as an independent variable. Solving the predictive equation provides a value for the grading parameter of the carcass. Other measurements which can be obtained from the carcass image and used as independent variables in predictive equations include distances from dorsal and ventral regions of the carcass image outline to a carcass mid-line, carcass widths, angular measurements between reference points, and measurements of curvature of the carcass image outline. Improved rib eye tracing techniques permit accurate measurement of rib eye parameters. The measured rib eye parameters may be used to determine a quality grade for the carcass or as independent variables in a carcass grading parameter predictive equation, alone, or in conjunction with measurements taken from the carcass image.

Method and apparatus for using image analysis to determine meat and

The invention provides methods of detecting poor meat quality in live animals using infrared thermography. Animals from a group of live domestic animals such as cattle or swine are scanned to produce thermographic images. The images are then statistically analyzed to determine a measure of central tendency such as the mean temperature for each animal's image and for all of the images in the group. A measure of dispersion from the measure of central tendency, such as standard deviation is determined. Then, animals are rejected as having a high probability of producing poor meat quality if the measure of central tendency for that animal's temperature differs from the measure of central tendency for the group by more than 0.9 standard deviations. Alternatively a set percent of animals are rejected, preferably up to 20%, these being animals whose measures of central tendency differ the most from the measure of central tendency for the group. When mean temperature is used as a measure of central tendency, the method is preferably practised by rejecting animals whose mean temperature differs from the group mean temperature by more than 1.28 times the standard deviation for the group. The method is particularly useful in detecting high probability of poor meat quality in groups of animals in an antemortem environment which have mean temperatures significantly above or below the normal surface temperatures for unstressed animals.

Method for detecting poor meat quality in groups of live animals

The invention provides methods of detecting poor meat quality in live animals using infrared thermography. In cattle, animals whose thermographs are predominantly outside the test temperature range, 28.degree.-32.degree..+-.2.degree. C., are rejected as having a high probability of producing poor meat quality. In swine, the test temperature range is 24.degree.-26.degree..+-.2.degree. C.

Growing community of inventors

Lacombe, Canada

Alan Kwai-Wah Tong