Human computer interaction_ 23CSM1R19.pptx

HUMAN COMPUTER INTERACTION

1. By: Sridhar Padala (23CSM1R19) Human Computer Interaction

2. Contents Introduction Procedure Basic flow of the system Software Requirements Results Conclusion

3. Introduction Nowadays personal computer systems are carrying a huge part in our everyday lives as they are used in areas such as work, education and enjoyment. While this is not a problem for a healthy individual, this may be an insurmountable bound for people with limited freedom of movement of their limbs. Camera is used to capture the image of eye movement. The eye tracker is based on images recorded by a mutated webcam to acquire the eye movements. These eye movements are then graphed to a computer screen to position a mouse cursor accordingly.

4. Procedure Video Recording: Using this module we will connect application to web cam using open cv built in function called video capture. Frame extraction: Using this module we will grab frames from web cam and then extract each picture frame by frame and send that frame to gaze tracking. Gaze tracking: Using this module we can detect the eye balls and the extract x and y coordinates of both left and right pupil. Move cursor: Using this module we will instruct mouse to change its current location to given new x and y location.

5. Basic flow of the system

6. Head Movement Initialization: head central coordinates ( Sx , Sy) of the standard head is calculated. Set threshold value : Determine the threshold value ( Kx , Ky) based on experience. Judge the head movements: The head central coordinates of one image is noted as ( Cx , Cy). We compare ( Cx , Cy) with ( Sx , Sy) to get the following conclusions: If Cx - Sx > Kx , head moves left. If Cx - Sx < - Kx , head moves right. If Cy - Sy < -Ky, up. If Cy - Sy> Ky, down. If | Cx - Sx | < Kx and | Cy - Sy | < Ky, standard head.

7. Eye Aspect Ratio (EAR) EAR helps us in detecting blinks and winks. EAR value drops whenever the eye closes.

8. HAAR CASCASDES Algorithm Face Detection : Haar cascades are used to detect faces in the image. Once a face is detected, a region of interest (ROI) containing the face is cropped for further processing. Eye Region Extraction : Haar cascades can be used to detect eyes within the ROI of the face. Once eyes are detected, a region of interest around the eyes is defined for blink detection.

9. Convolution Neural Network Head Pose Estimation : A Convolutional Neural Network (CNN) is trained to estimate the pose of the head. The CNN takes the cropped face image as input and outputs the head pose angles. Eye Blink Detection : CNN is trained for eye blink detection. The CNN takes the cropped eye region as input and outputs the probability of a blink. Cursor Movement : The output of the head pose estimation CNN is used to calculate the deviation of the head pose from a neutral position. This deviation is then mapped to cursor movement directions.

10. Software Requirements OpenCV is a Python open-source library, which is used for computer vision in Artificial intelligence, Machine Learning, face recognition, etc. The  Jupyter Notebook is an open-source web application that allows you to create and share documents that contain live code, equations, visualizations and narrative text.

11. Python is a computer programming language often used to build websites and software, automate tasks, and conduct data analysis. Python is a general-purpose language, meaning it can be used to create a variety of different programs and isn't specialized for any specific problems. NumPy is a Python library used for working with arrays. It also has functions for working in domain of linear algebra, fourier transform, and matrices. NumPy was created in 2005 by Travis Oliphant. It is an open source project and you can use it freely.

12. Results Right Movement Left Movement

13. Conclusion In this research, the experimental results provide objective eye-tracking evidence that confirms the hypotheses made based on the findings of existing research. Most students recognize beacons and pay more attention to these areas when debugging. Only significant statistical results have been reported in the conclusions, guaranteeing the conclusion validity. Previous research has revealed a relationship between working memory capacity and the cognitive activities related to debugging with regard to mental arithmetic, short-term memory, logical thinking, and problem solving. Thus, the eye ball movement tracking is applied to physically challenged peoples to obtain various results