Loading...

Modeling of Visual Attention Mechanism by Brain Signals

Pahlevan Aghababa, Fatemeh | 2018

482 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 50793 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Beigy, Hamid
  7. Abstract:
  8. Attention is a cognitive process in which the mind reacts to certain stimuli or stimuli of the environment while other environmental stimuli are ignored. Attention might be an overt or covert process. Overt attention is a process in which based on the purpose, we selectively choose an object or place among other objects and places to focus on and we are aware of it. However, the covert attention originates from hidden source, and we are not aware of it. In fact, the covert attention causes a clear and rapid movement of the eye toward the stimulus or space to be taken into consideration and the time when the movement of the eye it means overt attention has occurred. Visual attention is given to cognitive functions that are based on the selection of relevant information and the removal of irrelevant information, which solves the problem of limited brain capacity effectively. In this thesis, the neuronal infrastructure model of attention is proposed and implemented. To this end, neurology has been studied first and a model has been designed according to the knowledge derived from neurology and the signals of the various sectors of brain are involved in the progress of evaluation. Then, the computational model is implemented in accordance with the principles of large scale neural engineering. The output of the model is considered as a sequence of points of view that human beings will look at. In this project, the image of the input from the Kinect-v.1 is received by the pioneer robot (P3-AT), and the output, ie, the selected point for moving the eye at any moment, is sent through the neural model in accordance with the dynamics of human eye movement to the robot. In general, the final model of the mechanism of attention and its effect on It shows the different parts of the brain, which has been one of the major issues in recent years. After the implementation of the model, we need to test it in order to evaluate the results. For this purpose, the required data is acquired to evaluate the designed and implemented model. What is important in the process of data collection is the design of the experiment. The appropriate test for this thesis is that the images are shown to the subjects and they are free to look at any point they want. To give the subjects a chance to rest between the test images, full-black images are shown to them so that the large number of test data does not make the subjects tired. In this test, which is designed in three levels, the model evaluated by the performance of 105 people. At the first level, which includes 60 figures with dimensions of 64 x 64 pixels, with a rotation angle of zero degrees, which resulted in an average error of 1.3 pixels. At the second level, the images were shown with the same dimensions but with rotational angles that reached the average error of 2.1 pixels. At the final level of the test, in addition to the rotation of the noise, the images have been added to the images, which leads to the average error of estimation of 3 pixels
  9. Keywords:
  10. Brain Modeling ; Visual Attention ; Computational Method ; Brain Waves ; Covert Attention

 Digital Object List

 Bookmark

...see more