Juan Gutierrez Ibarra

Combined IR imaging-neural network method for the estimation of internal temperature in cooked chicken meat

A noninvasive method for the estimation of internal temperature in chicken meat immediately following cooking is proposed. The external temperature from iR images was correlated with measured internal temperature through a multilayer neural network. To provide inputs for the network, time series experiments were conducted to obtain simultaneous observations of internal and external temperatures immediately after cooking during the cooling process. An iR camera working at the spectral band of 3.4 to 5.0 µm registered external temperature distributions without the interference of close-to-oven environment, while conventional thermocouples registered internal temperatures. For an internal temperature at a given time, simultaneous and lagged external temperature observations were used as the input of the neural network. Based on practical and statistical considerations, a criterion is established to reduce the nodes in the neural network input. The combined method was able to estimate internal temperature for times between 0 and 540 s within a standard error of ± 1.01°C, and within an error of ± 1.07°C for short times after cooking (3 min), with two thermograms at times t and t+ 30 s. The method has great potential for monitoring of doneness of chicken meat in conveyor belt type cooking and can be used as a platform for similar studies in other food products.

INTERNAL TEMPERATURE OF COOKED CHICKEN MEAT THROUGH INFRARED IMAGING AND TIME SERIES ANALYSIS

A non-invasive method for the estimation of internal temperature of chicken meat immediately after cooking was developed. In this study, a statistical model to express the internal temperature of chicken breast muscle samples in terms of the external temperature and time is presented. For non-invasive and accurate external temperature measurement, an infrared camera based on focal plane array technology and with spectral band of 3.4 to 5 µm was employed. From temperature versus time data, the external temperature (measured from infrared imaging) with internal temperature (measured with embedded thermocouples) and time was correlated through time series analysis. Temperature time series observations were obtained from chicken breast muscle samples with similar thickness and shape, cooked in an industrial multipurpose oven at different cooking conditions. A time series autoregressive model to estimate internal temperature from external temperature data and time is proposed here. An estimation of internal temperature within an accuracy of ±1.22°C for cooling times between 0 and 450 s, and within an accuracy of ±0.55°C for zero seconds (immediately after cooking) resulted from this analysis. This method has great potential for the real-time determination of internal temperature of cooked chicken meat in industrial lines, which can aid quality control personnel and regulators to verify that the minimum endpoint temperature is achieved to ensure food safety.

Trading visibility and opening ratio in Talbot arrays

Abstract We describe Talbot array illuminators, based on binary phase gratings, with improved opening ratios and with visibility values slightly lower than unity. Experimental verification is implemented using a coherent optical processor for the synthesis of one-dimensional phase profiles.

Estimation of internal temperature in chicken meat by means of mid-infrared imaging and neural networks

A non-invasive method to estimate internal temperature in boneless, skinless chicken meat after cooing is presented. In this work, the internal temperature of chicken breast samples, measured at approximately half the thickness, was correlated with the external temperature of the surface above and the cooling time. For the non-invasive and accurate external temperature measurement a focal planar array IR camera with spectral range of 3.4-5 micrometers was used. At this spectral band, the interference of water vapor originated from the sample is practically eliminated. Neural networks were used to establish a correlation between internal temperature with external temperature and cooling time. To model the internal and external temperature time series a one-hidden layer feed forward layer, with three hidden nodes was used. The network was trained with 60 time series of 20 time points each one, ranging form 0 to 570 seconds. Training was conducted for 400 epochs, with learning rate 0.3. The predictions obtained were compared with a test data set to judge the performance of the network. The method has great potential for the real-time estimation of internal temperature of cooked chicken meat in industrial lines.

LEARNING VECTOR QUANTIZATION FOR COLOR CLASSIFICATION OF DISEASED AIR SACS IN CHICKEN CARCASSES

The variation in color features observed during the evolution of air–sacculitis in chicken carcasses is exploited to classify the disease using digital imaging and neural networks. For the experiments, air–sacculitis was induced by secondary infected of E. coli via direct inoculation of challenge bacteria. Mild and severely infected samples were obtained and imaged. For the supervised classification, a knowledge base set of normalized RGB values, corresponding to negative, mild, and severely infected air sac images, was obtained. Statistical data exploration indicated no significant difference between the color features of mild and severely infected sacs, but a significant difference was found between infected and negative tissues. A neural network using the learning vector quantization algorithm classified the data in infected and negative categories. Resubstitution and hold–out errors were calculated, giving an overall accuracy in the classification of 96.7%. Each poultry carcass sold in the U.S. must be visually inspected for its wholesomeness by a USDA inspector, with air–sacculitis being the major cause of condemnation in poultry processing plants. The method presented here has the potential for integration in a computer–assisted inspection of wholesomeness in poultry processing lines.

Talbot array illuminators with liquid crystal displays

First we show that a binary amplitude grating, altered by a suitable discrete phase modulation is transformed, by Fresnel diffraction, into another binary grating with reduced opening ratio. We employ this process as the basis for discussing segmented versions of Talbot array illuminators that can be displayed with liquid crystal displays.

Split Talbot array illuminators

We describe periodic binary patterns, with a basic cell formed by two or more bright intervals, that can be generated at fractional Talbot planes of multilevel phase gratings. These structures are proposed as alternate forms of Talbot array illuminators. A simple example is experimentally verified.

Array illuminators with phase gratings in cascade

We describe multilevel phase modulations for transforming any binary amplitude grating into another one with reduced opening ratio, without energy loss. From this, we propose arrangements of properly spaced phase gratings as array illuminators based on the Talbot effect.

Recovery of three-dimensional shapes by using a defocus structured light system

We present a new concept for 3D shape recovery using Defocused Structure Light (DSL) images. DSL technique externally extracts the depth information for the scene by using projections of cylindrical wavefronts on the object. These projections show different degrees of defocus as a function of the depth.

Self-imaging of discrete gratings at fractions of the Talbot distance: an eigenvalue problem

Using a matrix formulation of Fresnel diffraction, we describe discrete gratings that exhibit self-images at fractions of the Talbot distance. Such structures are obtained as solutions of an eigenvalue equation.