**5.4.1 Training sets**

56 Advances in Object Recognition Systems

with no inclusion in the system's composite image of any false-class images. For both cases, we aimed in observing if there was any change in the class separation ability of the M-HONN system. We constrained the true-class objects to unity correlation peak-height and we used the same as before Targets for the false- and true- class images of the NNET block. The target of the false-class object is T 40 false , and the Target of the true-class object is T 40 true in the training set of the NNET block for the M-HONN system. It had no built-in

Fig. 8. (Adapted by Kypraios et al., 2008) shows (a) the reference angle, Θ0, and the two inclass training images at the angles Θ1 and Θ2. The test image is on the bisector at angle Θ3; (b) the correlation peak-heights for each input image over a range of Θ3 = [5° 40°] for the

From the conducted experiments we drew Table 1. The forth column of Table 1 records the values taken for the in-class training image and the fifth column contains all the values taken for the out-of-class training image. It is shown from the third column of Table 1 that M-HONN system gave sufficient discrimination ability between the two objects, the Jaguar S-type car and the RX-7 Police patrol car. It produced 12% class separation (with the falseclass images included in the synthesis of the composite image with zero correlation peakheight constraint). By not including any false-class images in the system's composite image, but by setting to unity correlation peak-height constraint the true-class images and keeping constant the target of the false-class object to T 40 false and the target of the true-class object to T 40 true , the M-HONN system increased the class separation to 27%. Thus, the

information on the test images.

M-HONN system.

We have conducted several tests (Kypraios et al., 2009) for evaluating the performance of the M-HONN system in recognising multiple objects of the same class or of different classes. Several training sets were created for testing the system's performance with still images and with video sequences. The first training set consisted of still images of the Jaguar S-type car for a distortion range over 0 to 360 out-of-plane rotated at 10 increments. The second training set consisted of still images of the RX-7 Police patrol car for a distortion range approximately over 0 to 360 out-of-plane rotated at 10 increments. The third training set consisted of video frames of a Ferrari Testarossa car within a background clutter scene. The fourth training set consisted of still images of different car park scenes. A fifth training set consisted of video frames we have taken showing a sequence of a Jaguar S-type car and a Ferrari Testarossa car within a background clutter scene. All the training and test sets of the still images and of the video sequence frames were used in grey-scale bitmap format, and they were sized to 256x256. All the test and train input still images and video frames were concatenated row-by-row into a vector form prior being processed by the NNET block of the M-HONN system.

Performance Analysis of

the Modified-Hybrid Optical Neural Network Object Recognition System Within Cluttered Scenes 59

Fig. 9. It shows the first visual problem for testing the M-HONN object recognition system's ability of problem solving. M-HONN system tries to recognise certain angles of view of the input object while rejecting others. The training set consisted of still images of the Jaguar Stype car out-of-plane rotated over a range 0° to 170° to belong in the true-class, and still images of the Jaguar S-type car out-of-plane rotated over a range 180° to 360° to belong in the false-class. We have indicated with the solid line the recognised true-class objects and

Police patrol car over approximately the same range. The training set consisted of still images of the Jaguar S-type car out-of-plane rotated over a range 0° to 360° to belong in the true-class, and still images of the RX-7 Mazda Efini Police patrol car out-of-plane rotated over approximately a range 0° to 360° to belong in the false-class. The true-class images were constrained to unit correlation peak-height in the synthesis of the M-HONN system's composite image, and the false-class images were constrained to zero correlation peak-height in the synthesis of the M-HONN system's composite image. We have set the true-class target classification levels (here we assume there is only one *class=1*, so there is no need to set any target connections for a second output neuron) to be class 1 T 240 true , and for false-class the target classification levels were set to be class 1 T 240 false . Here, we have set higher target classification level values for increasing the inter-class discrimination abilities of the M-HONN system. It worth mentioning that we could have set *class=2* and, then, set a target classification level for class 2 T with no need to include false-class objects, but adjust the constraint matrix of true the system's composite image to class 1 and class 2 different fixed correlation peak-height values. The test set consisted of non-training input still images of Jaguar S-type car objects inserted in plain background at different out-of-plane rotation angles over a range 0° to 360°, and input still images of RX-7 Mazda Efini Police patrol cars inserted in plain background at different out-of-plane rotation angles over a range 0° to 360°. As shown on Fig. 11, M-HONN system was able to successfully recognise the Jaguar S-type car poses over the range 0° to 360° to belong in the true-class, and the RX-7 Mazda Efini car poses over approximately the same range 0° to 360° to belong in the false-class. Again, we have indicated with the solid line the

recognised true-class objects and with the dashed line the recognised false-class objects.

with the dashed line the recognised false-class objects.

### **5.4.2 Biologically-inspired knowledge representation and learning**

As S. Haykin in his work on artificial neural network architectures (S. Haykin, 1999) observes, pattern recognition systems need to be re-designed in novel architectures, if they are to be solving more complex problems. He argues that such novel architectures should be designed with separate blocks of a recognition unit and a knowledge learning unit, and that the implementation of such designs can be only possible with the combination of artificial neural networks architectures with other tools as a hybrid. Some of the elements (S. Haykin, 1999) that such biologically-inspired hybrid systems need to exploit are, the non-linearity of the input information, learning and adaptation to the input information, and provide an attentional mechanism for the hybrid system to be able to select certain information to be included in its learning against other input. Therefore, knowledge representation and learning becomes a central issue in the design and implementation of such hybrid biologically-inspired pattern recognition systems (Lee & Portier, 2007).

Aler et al. in their work discuss the knowledge representation and its role in knowledge learning (Aler et al., 2000). Aler et al. argue the effects that altering the knowledge representation can have on the problem knowledge learned and problem solving. They consider any problem solving system to consist of a domain theory which specifies the task to be solved, the initial problem states and the aimed problem goals, and a control knowledge which guides the decision-making process. They were able to demonstrate the effects of knowledge representation to the efficiency of the problem solving process.

Recent work we have conducted (Kypraios, 2010) has demonstrated the problem solving ability of the HONN-type systems, such as the M-HONN system for multiple objects recognition. We have shown the system is able to solve, in particular, different visual tasks. Fig. 9 shows the first problem we have tested M-HONN system for recognising different angles of view of the input object. The training set consisted of still images of the Jaguar S-type car out-of-plane rotated over a range 0° to 170° to belong in the true-class, and still images of the Jaguar S-type car out-of-plane rotated over a range 180° to 360° to belong in the false-class. The true-class images were constrained to unit correlation peak-height in the synthesis of the M-HONN system's composite image, and the false-class images were constrained to zero correlation peak-height in the synthesis of the M-HONN system's composite image (see Fig. 10). We have set the true-class target classification levels (here we assume there is only one *class=1*, so there is no need to set any target connections for a second output neuron) to be class 1 T 40 true , and for false-class the target classification levels were set to be class 1 T 40 false . The test set consisted of multiple Jaguar S-type car objects inserted in plain background at different non-training out-of-plane rotation angles over a range 0° to 360°. As shown on Fig. 9, M-HONN system was able to correctly recognise the Jaguar S-type car poses over the range 0° to 170° to belong in the true-class, and the Jaguar S-type car poses over the range 180° to 360° to belong in the false-class. We have indicated with the solid line the recognised true-class objects and with the dashed line the recognised false-class objects.

Fig. 11 shows the second test we conducted to demonstrate the system's ability of problem solving where we want the system to recognise only the true-class objects of the Jaguar Stype car over a range 0° to 360°, and reject the false-class objects of the RX-7 Mazda Efini 58 Advances in Object Recognition Systems

As S. Haykin in his work on artificial neural network architectures (S. Haykin, 1999) observes, pattern recognition systems need to be re-designed in novel architectures, if they are to be solving more complex problems. He argues that such novel architectures should be designed with separate blocks of a recognition unit and a knowledge learning unit, and that the implementation of such designs can be only possible with the combination of artificial neural networks architectures with other tools as a hybrid. Some of the elements (S. Haykin, 1999) that such biologically-inspired hybrid systems need to exploit are, the non-linearity of the input information, learning and adaptation to the input information, and provide an attentional mechanism for the hybrid system to be able to select certain information to be included in its learning against other input. Therefore, knowledge representation and learning becomes a central issue in the design and implementation of such hybrid biologically-inspired pattern recognition systems (Lee &

Aler et al. in their work discuss the knowledge representation and its role in knowledge learning (Aler et al., 2000). Aler et al. argue the effects that altering the knowledge representation can have on the problem knowledge learned and problem solving. They consider any problem solving system to consist of a domain theory which specifies the task to be solved, the initial problem states and the aimed problem goals, and a control knowledge which guides the decision-making process. They were able to demonstrate the

Recent work we have conducted (Kypraios, 2010) has demonstrated the problem solving ability of the HONN-type systems, such as the M-HONN system for multiple objects recognition. We have shown the system is able to solve, in particular, different visual tasks. Fig. 9 shows the first problem we have tested M-HONN system for recognising different angles of view of the input object. The training set consisted of still images of the Jaguar S-type car out-of-plane rotated over a range 0° to 170° to belong in the true-class, and still images of the Jaguar S-type car out-of-plane rotated over a range 180° to 360° to belong in the false-class. The true-class images were constrained to unit correlation peak-height in the synthesis of the M-HONN system's composite image, and the false-class images were constrained to zero correlation peak-height in the synthesis of the M-HONN system's composite image (see Fig. 10). We have set the true-class target classification levels (here we assume there is only one

*class=1*, so there is no need to set any target connections for a second output neuron) to be class 1 T 40 true , and for false-class the target classification levels were set to be class 1 T 40 false . The test set consisted of multiple Jaguar S-type car objects inserted in plain background at different non-training out-of-plane rotation angles over a range 0° to 360°. As shown on Fig. 9, M-HONN system was able to correctly recognise the Jaguar S-type car poses over the range 0° to 170° to belong in the true-class, and the Jaguar S-type car poses over the range 180° to 360° to belong in the false-class. We have indicated with the solid line the recognised true-class

Fig. 11 shows the second test we conducted to demonstrate the system's ability of problem solving where we want the system to recognise only the true-class objects of the Jaguar Stype car over a range 0° to 360°, and reject the false-class objects of the RX-7 Mazda Efini

objects and with the dashed line the recognised false-class objects.

effects of knowledge representation to the efficiency of the problem solving process.

**5.4.2 Biologically-inspired knowledge representation and learning** 

Portier, 2007).

Fig. 9. It shows the first visual problem for testing the M-HONN object recognition system's ability of problem solving. M-HONN system tries to recognise certain angles of view of the input object while rejecting others. The training set consisted of still images of the Jaguar Stype car out-of-plane rotated over a range 0° to 170° to belong in the true-class, and still images of the Jaguar S-type car out-of-plane rotated over a range 180° to 360° to belong in the false-class. We have indicated with the solid line the recognised true-class objects and with the dashed line the recognised false-class objects.

Police patrol car over approximately the same range. The training set consisted of still images of the Jaguar S-type car out-of-plane rotated over a range 0° to 360° to belong in the true-class, and still images of the RX-7 Mazda Efini Police patrol car out-of-plane rotated over approximately a range 0° to 360° to belong in the false-class. The true-class images were constrained to unit correlation peak-height in the synthesis of the M-HONN system's composite image, and the false-class images were constrained to zero correlation peak-height in the synthesis of the M-HONN system's composite image. We have set the true-class target classification levels (here we assume there is only one *class=1*, so there is no need to set any target connections for a second output neuron) to be class 1 T 240 true , and for false-class the target classification levels were set to be class 1 T 240 false . Here, we have set higher target classification level values for increasing the inter-class discrimination abilities of the M-HONN system. It worth mentioning that we could have set *class=2* and, then, set a target classification level for class 2 T with no need to include false-class objects, but adjust the constraint matrix of true the system's composite image to class 1 and class 2 different fixed correlation peak-height values. The test set consisted of non-training input still images of Jaguar S-type car objects inserted in plain background at different out-of-plane rotation angles over a range 0° to 360°, and input still images of RX-7 Mazda Efini Police patrol cars inserted in plain background at different out-of-plane rotation angles over a range 0° to 360°. As shown on Fig. 11, M-HONN system was able to successfully recognise the Jaguar S-type car poses over the range 0° to 360° to belong in the true-class, and the RX-7 Mazda Efini car poses over approximately the same range 0° to 360° to belong in the false-class. Again, we have indicated with the solid line the recognised true-class objects and with the dashed line the recognised false-class objects.

Performance Analysis of

chosen to build the input mask

performance within clutter

the Modified-Hybrid Optical Neural Network Object Recognition System Within Cluttered Scenes 61

the synthesis of the composite image of the M-HONN system. Thus, in one of the tests we created a training set consisting of Jaguar S-type car objects out-of-plane rotated over a range 20° to 70° at 10° increments to belong in true-class 1, RX-7 Mazda Efini Police patrol car objects out-of-plane rotated over approximately a range 20° to 70°at 10° increments to belong in true-class 2, and a random car park scene to belong in false-class. The true-class 1 images were constrained to unit correlation peak-height, the true-class 2 images were constrained to half-a-unit correlation peak-height, and the false-class images were constrained to zero correlation peak-height in the synthesis of the M-HONN system's composite image. We have set the true-class 1 and true-class 2 target classification levels to be class 1 T 180 true and class 2 T 90 true , and for false-class 1 and false-class 2 the target classification levels were set to be class 1 T 10 false and class 2 T 10 false . The test set (see Fig. 12) consisted of input still images of a Jaguar S-type car object and a RX-7 Mazda Efini Police patrol car object both inserted in a car park background scene (not the one we included in the training set), positioned off-the-centre and out-of-plane rotated over a range 20° to 70°. During the process of inserting the objects in to the car park scene some Gaussian noise is added, too. The M-HONN system was able to correctly discriminate between class 1 and class 2. However, in this test the emphasis was to study the effect that knowledge representation in the form of the composite image synthesis has on the problem solving. In

c in

c from the training set image of true-class 2 object of the

<sup>c</sup> , which we

Additional tests we conducted have demonstrated the effect that has the input mask

effect, as shown in Fig. 13, when we have chosen to build the input mask

car and completely suppressing any features of the background car park scene.

applied it on both the training set and the test set, from the training set image of true-class 1 object of the Jaguar S-type car, then the system synthesised its composite image by nonlinearly revealing more features for the true-class 1 object of the Jaguar S-type car, allowing less features for the true-class 2 object of the RX-7 Mazda Efini Police patrol car and completely suppressing any features of the background car park scene. When we have

RX-7 Mazda Efini Police patrol car, then the system synthesise its composite image (see Fig. 14) by non-linearly revealing more features for the true-class 2 object of the RX-7 Mazda Efini Police patrol car, allowing less features for the true-class 1 object of the Jaguar S-type

Fig. 12. It shows one of the test set input images used for assessing the M-HONN system's

Fig. 10. It shows the composite image the M-HONN system synthesised for a training set consisting of still images of the Jaguar S-type car out-of-plane rotated over a range 0° to 360°.

60 Advances in Object Recognition Systems

Fig. 10. It shows the composite image the M-HONN system synthesised for a training set consisting of still images of the Jaguar S-type car out-of-plane rotated over a range 0° to 360°.

Fig. 11. It shows the second visual problem for testing the M-HONN object recognition system's ability of problem solving. M-HONN system tries to recognise only the true-class

consisted of still images of the Jaguar S-type car out-of-plane rotated over a range 0° to 360° to belong in the true-class, and still images of the RX-7 Mazda Efini Police patrol car out-ofplane rotated over approximately a range 0° to 360° to belong in the false-class. We have indicated with the solid line the recognised true-class objects and with the dashed line the

objects of the Jaguar S-type car and reject all the false-class objects. The training set

recognised false-class objects.

Additional tests we conducted have demonstrated the effect that has the input mask c in the synthesis of the composite image of the M-HONN system. Thus, in one of the tests we created a training set consisting of Jaguar S-type car objects out-of-plane rotated over a range 20° to 70° at 10° increments to belong in true-class 1, RX-7 Mazda Efini Police patrol car objects out-of-plane rotated over approximately a range 20° to 70°at 10° increments to belong in true-class 2, and a random car park scene to belong in false-class. The true-class 1 images were constrained to unit correlation peak-height, the true-class 2 images were constrained to half-a-unit correlation peak-height, and the false-class images were constrained to zero correlation peak-height in the synthesis of the M-HONN system's composite image. We have set the true-class 1 and true-class 2 target classification levels to be class 1 T 180 true and class 2 T 90 true , and for false-class 1 and false-class 2 the target classification levels were set to be class 1 T 10 false and class 2 T 10 false . The test set (see Fig. 12) consisted of input still images of a Jaguar S-type car object and a RX-7 Mazda Efini Police patrol car object both inserted in a car park background scene (not the one we included in the training set), positioned off-the-centre and out-of-plane rotated over a range 20° to 70°. During the process of inserting the objects in to the car park scene some Gaussian noise is added, too. The M-HONN system was able to correctly discriminate between class 1 and class 2. However, in this test the emphasis was to study the effect that knowledge representation in the form of the composite image synthesis has on the problem solving. In effect, as shown in Fig. 13, when we have chosen to build the input mask <sup>c</sup> , which we applied it on both the training set and the test set, from the training set image of true-class 1 object of the Jaguar S-type car, then the system synthesised its composite image by nonlinearly revealing more features for the true-class 1 object of the Jaguar S-type car, allowing less features for the true-class 2 object of the RX-7 Mazda Efini Police patrol car and completely suppressing any features of the background car park scene. When we have chosen to build the input mask c from the training set image of true-class 2 object of the RX-7 Mazda Efini Police patrol car, then the system synthesise its composite image (see Fig. 14) by non-linearly revealing more features for the true-class 2 object of the RX-7 Mazda Efini Police patrol car, allowing less features for the true-class 1 object of the Jaguar S-type car and completely suppressing any features of the background car park scene.

Fig. 12. It shows one of the test set input images used for assessing the M-HONN system's performance within clutter

Performance Analysis of

respectively.

background car park scene.

the Modified-Hybrid Optical Neural Network Object Recognition System Within Cluttered Scenes 63

class classification levels. We constrained true-class 1 of the Jaguar S-type object images to unit correlation peak-height constraint, and true-class 2 of the Ferrari Testarossa car to halfa-unit correlation peak-height constraint in the synthesis of the M-HONN system's composite image. Fig. 15 (a) and Fig. 15 (b) show the output correlation planes response of the M-HONN system for class 1, which are normalised to the overall maximum correlation plane peak-height value for all the input images. Fig. 15 (c) and Fig. 15 (d) show the output correlation plane response of the M-HONN system for class 2, which are normalised to the overall maximum correlation plane peak-height value for all the input images. From the recorded results we have shown that the M-HONN system has accommodated the recognition of class 1 and class 2 objects by output neuron 1 and output neuron 2,

Fig. 14. It shows the synthesised composite image of the M-HONN system. The training set set consisted of Jaguar S-type car objects out-of-plane rotated over a range 20° to 70° at 10° increments to belong in true-class 1, RX-7 Mazda Efini Police patrol car objects out-of-plane rotated over approximately a range 20° to 70°at 10° increments to belong in true-class 2, and a random car park scene to belong in false-class. Now we have built the input mask from the training set image of true-class 2 object of the RX-7 Mazda Efini Police patrol car, then the system synthesised its composite image by non-linearly revealing more features for the true-class 2 object of the RX-7 Mazda Efini Police patrol car, allowing less features for the true-class 1 object of the Jaguar S-type car and completely suppressing any features of the

In the second series of conducted tests, we aimed to assess the ability of the M-HONN system to recognise multiple objects of different classes within a cluttered video sequence. Fig. 16 shows indicatively four of the video frames from the recorded video sequence. The frame rate of the video sequence was 25 frames per second (fps). The training consisted of images of the Jaguar S-type car out-of-plane rotated over 20° to 80° degrees at 20° increments. We added two images of the Jaguar S-type car out-of-plane rotated at 130° and 140° to fall inside the false-class object for increasing the peak sharpness and class discrimination abilities of the M-HONN system. For our conducted tests we found the best values for the true-class 1 and true-class 2 classification values to be class 1 T 240 true and class 2 T 240 true , respectively, and the best values for the false-class 1 and false-class 2

From the above observations and conducted experiments, the M-HONN system, as all the HONN-type systems, combine in their design a knowledge representation unit being the optical correlator block with a knowledge learning unit being the NNET block. Moreover, HONN-type systems, such as M-HONN, have been proven in previous work we have done (Kypraios et al., 2002) to non-linearly combine the weighted, extracted by the NNET block, input training set. In effect, in HONN-type systems the attentional mechanism is provided by the extracted weights of the NNET block to be able to select certain features to be included in its composite image against other ones. Additionally, the M-HONN system, as shown above, can learn and adapt to the input information depending on the created training set itself. Here, the created training set comprises the domain theory of the task to be solved, the initial problem states and the problem goals are given by the true-class and false-class classification levels, and the synthesised composite image provides the control knowledge which guides the decision-making process.

Fig. 13. It shows the synthesised composite image of the M-HONN system. The training set set consisted of Jaguar S-type car objects out-of-plane rotated over a range 20° to 70° at 10° increments to belong in true-class 1, RX-7 Mazda Efini Police patrol car objects out-of-plane rotated over approximately a range 20° to 70°at 10° increments to belong in true-class 2, and a random car park scene to belong in false-class. When we have built the input mask from the training set image of true-class 1 object of the Jaguar S-type car, then the system synthesised its composite image by non-linearly revealing more features for the true-class 1 object of the Jaguar S-type car, allowing less features for the true-class 2 object of the RX-7 Mazda Efini Police patrol car and completely suppressing any features of the background car park scene.

#### **5.4.3 Multiple objects recognition**

Here, we summarise several tests we previously conducted for explicitly testing the M-HONN system's ability to recognise multiple objects of different classes (Kypraios et al., 2008). In the first series of conducted tests, the training set consisted of three Jaguar S-type car images out-of-plane rotated at 40° 60° and 80° to belong in class 1, and three Ferrari Testarossa extracted video frames from a recorded video sequence to belong in class 2. For our application purposes it was found to be adequate to set class1 T 40 true and class2 T 40 true for the true-class target classification levels and class1 T 40 false and class2 T 40 false for the false62 Advances in Object Recognition Systems

From the above observations and conducted experiments, the M-HONN system, as all the HONN-type systems, combine in their design a knowledge representation unit being the optical correlator block with a knowledge learning unit being the NNET block. Moreover, HONN-type systems, such as M-HONN, have been proven in previous work we have done (Kypraios et al., 2002) to non-linearly combine the weighted, extracted by the NNET block, input training set. In effect, in HONN-type systems the attentional mechanism is provided by the extracted weights of the NNET block to be able to select certain features to be included in its composite image against other ones. Additionally, the M-HONN system, as shown above, can learn and adapt to the input information depending on the created training set itself. Here, the created training set comprises the domain theory of the task to be solved, the initial problem states and the problem goals are given by the true-class and false-class classification levels, and the synthesised composite image provides the control

Fig. 13. It shows the synthesised composite image of the M-HONN system. The training set set consisted of Jaguar S-type car objects out-of-plane rotated over a range 20° to 70° at 10° increments to belong in true-class 1, RX-7 Mazda Efini Police patrol car objects out-of-plane rotated over approximately a range 20° to 70°at 10° increments to belong in true-class 2, and a random car park scene to belong in false-class. When we have built the input mask from the training set image of true-class 1 object of the Jaguar S-type car, then the system

synthesised its composite image by non-linearly revealing more features for the true-class 1 object of the Jaguar S-type car, allowing less features for the true-class 2 object of the RX-7 Mazda Efini Police patrol car and completely suppressing any features of the background

Here, we summarise several tests we previously conducted for explicitly testing the M-HONN system's ability to recognise multiple objects of different classes (Kypraios et al., 2008). In the first series of conducted tests, the training set consisted of three Jaguar S-type car images out-of-plane rotated at 40° 60° and 80° to belong in class 1, and three Ferrari Testarossa extracted video frames from a recorded video sequence to belong in class 2. For our application purposes it was found to be adequate to set class1 T 40 true and class2 T 40 true for the true-class target classification levels and class1 T 40 false and class2 T 40 false for the false-

knowledge which guides the decision-making process.

car park scene.

**5.4.3 Multiple objects recognition** 

class classification levels. We constrained true-class 1 of the Jaguar S-type object images to unit correlation peak-height constraint, and true-class 2 of the Ferrari Testarossa car to halfa-unit correlation peak-height constraint in the synthesis of the M-HONN system's composite image. Fig. 15 (a) and Fig. 15 (b) show the output correlation planes response of the M-HONN system for class 1, which are normalised to the overall maximum correlation plane peak-height value for all the input images. Fig. 15 (c) and Fig. 15 (d) show the output correlation plane response of the M-HONN system for class 2, which are normalised to the overall maximum correlation plane peak-height value for all the input images. From the recorded results we have shown that the M-HONN system has accommodated the recognition of class 1 and class 2 objects by output neuron 1 and output neuron 2, respectively.

Fig. 14. It shows the synthesised composite image of the M-HONN system. The training set set consisted of Jaguar S-type car objects out-of-plane rotated over a range 20° to 70° at 10° increments to belong in true-class 1, RX-7 Mazda Efini Police patrol car objects out-of-plane rotated over approximately a range 20° to 70°at 10° increments to belong in true-class 2, and a random car park scene to belong in false-class. Now we have built the input mask from the training set image of true-class 2 object of the RX-7 Mazda Efini Police patrol car, then the system synthesised its composite image by non-linearly revealing more features for the true-class 2 object of the RX-7 Mazda Efini Police patrol car, allowing less features for the true-class 1 object of the Jaguar S-type car and completely suppressing any features of the background car park scene.

In the second series of conducted tests, we aimed to assess the ability of the M-HONN system to recognise multiple objects of different classes within a cluttered video sequence. Fig. 16 shows indicatively four of the video frames from the recorded video sequence. The frame rate of the video sequence was 25 frames per second (fps). The training consisted of images of the Jaguar S-type car out-of-plane rotated over 20° to 80° degrees at 20° increments. We added two images of the Jaguar S-type car out-of-plane rotated at 130° and 140° to fall inside the false-class object for increasing the peak sharpness and class discrimination abilities of the M-HONN system. For our conducted tests we found the best values for the true-class 1 and true-class 2 classification values to be class 1 T 240 true and class 2 T 240 true , respectively, and the best values for the false-class 1 and false-class 2

Performance Analysis of

plane.

**6. Conclusion and future work** 

robust to intra-class distortions of the input objects.

the Modified-Hybrid Optical Neural Network Object Recognition System Within Cluttered Scenes 65

Fig. 16. It shows indicatively four of the video frames from the recorded video sequence. The locked window unit is on top of the maximum correlation peak-height values. With the dashed line we have shown the secondary correlation peaks of the output plane and with the solid line we have shown the maximum correlation peak-height value of the output

We have described the design and implementation of the M-HONN system. In particular, we focused in the design and implementation of the M-HONN system for multiple objects recognition of the same and of different classes. The inherited shift invariance properties by the optical correlator block of the system can accommodate for the recognition of multiple objects of the same class. The cross-correlation of each masked test set image with the transformed reference kernel returns an output correlation plane peak value for each cross-correlation step. Thus, the maximum peak height values of the output correlation plane correspond to the recognised true-class objects. By augmenting the output layer of the NNET block of the M-HONN system we can accommodate for the recognition of multiple objects of different classes. In effect, we increase the number of the output layer neurons proportionally with the number of the different object classes. We assign one output neuron to each different class. It was proven experimentally that by choosing different values of the classification levels for the true-class ClT and false-class ClF objects we can control the M-HONN system's behaviour and it can be varied from more like a high-pass biased filter, which generally gives sharp correlation peaks and good clutter suppression but is more sensitive to intra-class distortions, to more like a MVSDF filter behaviour, which generally gives broader correlation peaks but is more

We have assessed the performance of the M-HONN system by conducting several series of tests. We assessed the system's ability to detect non-training in-class images that are oriented at the intermediate angle of view between the training images. From the recorded

classification values to be class 1 T 240 false and class 2 T 240 false . We constrained true-class 1 of the Jaguar S-type object images to unit correlation peak-height constraint, true-class 2 of the Ferrari Testarossa car to half-a-unit correlation peak-height constraint, and false-class 1 and false-class 2 to zero correlation peak-height constraints in the synthesis of the M-HONN system's composite image. Fig. 16 shows the locked window unit of chosen size 70x70 on top of the maximum correlation peak-height values. With the dashed line we have shown the secondary correlation peaks of the output plane and with the solid line we have shown the maximum correlation peak-height value of the output plane. M-HONN system successfully suppressed the unknown background clutter throughout the length of the video sequence and recognised correctly class 1 and class 2 objects. It is emphasised that we have not included any background information in the training set of the system.

**Class 1: Jaguar S-**

Fig. 15. (Adapted by Kypraios et al., 2009) It shows (a) for the first output layer neuron, and (b) for the second output layer neuron the isometric output correlation plane response of the M-HONN system for Class 1 (normalised to the maximum correlation plane peak-height value), and (c) and (d) the isometric output correlation plane response of the M-HONN system for Class 2 (normalised to the maximum correlation plane peak-height value).

Fig. 16. It shows indicatively four of the video frames from the recorded video sequence. The locked window unit is on top of the maximum correlation peak-height values. With the dashed line we have shown the secondary correlation peaks of the output plane and with the solid line we have shown the maximum correlation peak-height value of the output plane.
