11. Markov chains for drunk identification

In this approach, the features used for intoxicated person discrimination are the eigenvalues of the transition matrices which correspond to Markov chains [39] used to model the pixels on the area of the forehead of each person. In the experimental procedure followed, a region on the forehead of both the drunk and the sober person was obtained, having 25 50 pixels size as shown in Figure 19, for a specific participant in the experiment. For this region, separately for the sober and the drunk person, the pixels of the forehead were brought into histograms of 8, 16, and 32 equal populated bins, respectively. The reduction of the histogram size from 256 graylevel representation to either 8, 16, or 32 bins were necessary to avoid sparse twodimensional transition matrices of first or second order, due to small number of pixels (25 50) in the inspected area of the forehead. For each person, a total of three transition matrices are created for the image of the sober and three for the image of the drunk. Accordingly, for the face in Figure 1 a more-or-less equal populated histogram with 16 bins is shown in Figure 20a. The transition matrix regarding the pixels of the histogram bins in Figure 20a is depicted as a black and white image in Figure 20b. This transition matrix of a Markov chain is a special tool for studying second-order statistics on the forehead, that is, co-occurrence properties of the pixels.

Based on these results, a network of neurons of relatively small size may contain all the necessary information for separating the sober from the drunk. This conclusion results from all data obtained from the people participated in the experiment. This network can be integrated into an automatic intoxication detection system, which by using the face image of an intoxicated person end evaluating, the pixel transition matrix from the forehead will employ the vectors of the eigenvalues of the transition matrix for recognition. A 2D representation of the eigenvalues space (from 16D) for a specific person is shown in Figure 21. The separability

Intoxication Identification Using Thermal Imaging http://dx.doi.org/10.5772/intechopen.72128 169

Figure 20. (a) A 16 bin histogram of the pixels on the forehead of a sober person, with 16 bins, (b) the transition matrix of

Figure 21. 2D representation of the eigenvalues space (from 16D) for a specific person. The two coordinates correspond to

the largest eigenvalues. The separability of the sober and drunk person is obvious even in the 2D space.

the pixels on the forehead of the sober person in Figure 1. Quantization in a 16 bin histogram has been used.

of the sober and drunk person is obvious even in the 2-D space.

Using the 41 50 16-D eigenvalue vectors for sober and that many for the drunk as data, a three layer neural network with different neurons at each layer, were trained. It was found that 16 neurons at the input layer are sufficient for the network to converge satisfactorily. In this process, a network was trained with the data from 40 people and its behavior was tested on the 41st (leave-one-out method). This process was repeated by excluding and testing each one of the 41 people. Each time a new network of neurons was trained, it was found that its magnitude is the same as the previous procedure having 16 input neurons. It was found in all cases that the person to be checked was correctly classified. The convergence success gave each time training error less than 2%. This fact shows that only one person out of 41 is not correctly identified, if he is drunk or not. This result is obtained for the case where 16 states have been used and therefore 16 eigenvalues of the transition matrix of each image.

Figure 19. Region on the forehead where the Markov properties of the pixels are studied.

Based on these results, a network of neurons of relatively small size may contain all the necessary information for separating the sober from the drunk. This conclusion results from all data obtained from the people participated in the experiment. This network can be integrated into an automatic intoxication detection system, which by using the face image of an intoxicated person end evaluating, the pixel transition matrix from the forehead will employ the vectors of the eigenvalues of the transition matrix for recognition. A 2D representation of the eigenvalues space (from 16D) for a specific person is shown in Figure 21. The separability of the sober and drunk person is obvious even in the 2-D space.

11. Markov chains for drunk identification

168 Human-Robot Interaction - Theory and Application

properties of the pixels.

In this approach, the features used for intoxicated person discrimination are the eigenvalues of the transition matrices which correspond to Markov chains [39] used to model the pixels on the area of the forehead of each person. In the experimental procedure followed, a region on the forehead of both the drunk and the sober person was obtained, having 25 50 pixels size as shown in Figure 19, for a specific participant in the experiment. For this region, separately for the sober and the drunk person, the pixels of the forehead were brought into histograms of 8, 16, and 32 equal populated bins, respectively. The reduction of the histogram size from 256 graylevel representation to either 8, 16, or 32 bins were necessary to avoid sparse twodimensional transition matrices of first or second order, due to small number of pixels (25 50) in the inspected area of the forehead. For each person, a total of three transition matrices are created for the image of the sober and three for the image of the drunk. Accordingly, for the face in Figure 1 a more-or-less equal populated histogram with 16 bins is shown in Figure 20a. The transition matrix regarding the pixels of the histogram bins in Figure 20a is depicted as a black and white image in Figure 20b. This transition matrix of a Markov chain is a special tool for studying second-order statistics on the forehead, that is, co-occurrence

Using the 41 50 16-D eigenvalue vectors for sober and that many for the drunk as data, a three layer neural network with different neurons at each layer, were trained. It was found that 16 neurons at the input layer are sufficient for the network to converge satisfactorily. In this process, a network was trained with the data from 40 people and its behavior was tested on the 41st (leave-one-out method). This process was repeated by excluding and testing each one of the 41 people. Each time a new network of neurons was trained, it was found that its magnitude is the same as the previous procedure having 16 input neurons. It was found in all cases that the person to be checked was correctly classified. The convergence success gave each time training error less than 2%. This fact shows that only one person out of 41 is not correctly identified, if he is drunk or not. This result is obtained for the case where 16 states have been

used and therefore 16 eigenvalues of the transition matrix of each image.

Figure 19. Region on the forehead where the Markov properties of the pixels are studied.

Figure 20. (a) A 16 bin histogram of the pixels on the forehead of a sober person, with 16 bins, (b) the transition matrix of the pixels on the forehead of the sober person in Figure 1. Quantization in a 16 bin histogram has been used.

Figure 21. 2D representation of the eigenvalues space (from 16D) for a specific person. The two coordinates correspond to the largest eigenvalues. The separability of the sober and drunk person is obvious even in the 2D space.
