Presentation is loading. Please wait.

Presentation is loading. Please wait.

` Tracking the Eyes using a Webcam Presented by: Kwesi Ackon Kwesi Ackon Supervisor: Mr. J. Connan.

Similar presentations


Presentation on theme: "` Tracking the Eyes using a Webcam Presented by: Kwesi Ackon Kwesi Ackon Supervisor: Mr. J. Connan."— Presentation transcript:

1 ` Tracking the Eyes using a Webcam Presented by: Kwesi Ackon Kwesi Ackon Supervisor: Mr. J. Connan

2 Recap Track the eyes Track the eyes Move cursor on the screen using the eyes Move cursor on the screen using the eyes

3 Changes No edge detection No edge detection Move from RGB colour space to HSV colour space Move from RGB colour space to HSV colour space White background White background

4 HSV (Hue, Saturation, Value) Space HSV (Hue, Saturation, Value) Space -H (hue): Ranges from 0-360. Hue represents the -H (hue): Ranges from 0-360. Hue represents the colour type (e.g. blue, red etc). colour type (e.g. blue, red etc). -S (saturation): Ranges from 0-100. It represents the purity of the colour: the higher saturation value is, the clearer the colour is. If saturation is low, the colour looks closer to gray. -S (saturation): Ranges from 0-100. It represents the purity of the colour: the higher saturation value is, the clearer the colour is. If saturation is low, the colour looks closer to gray. -V (value): This is the brightness of the colour, and it ranges from 0-100. -V (value): This is the brightness of the colour, and it ranges from 0-100.

5 HSV colour space represented as a cylinder HSV colour space represented as a cylinder Red pixel RGB space: 255 0 0 HSV space: 0˚ 100% 100%

6 Conversion from RGB to HSV Conversion from RGB to HSV

7 Progress Face detection implementation Face detection implementation Original Original image Detected skin pixels Detected skin pixels 0 < H < 50, 23 < S < 68 Level of accuracy 96.4%

8 Results for different skin types Results for different skin types Dark skin Light skin

9 Eye detection implementation Eye detection implementation y x y1 x1 Obtaining dimensions of eye rectangle: y = Half height of face rectangle x = Half width of face rectangle y1 = 0.10 * y x1 = 0.625 * x Width of eye rectangle = x1 Height of eye rectangle = 2 * y1

10 Results for eye detection Results for eye detection

11 Tools and Languages Dev-C++ 4.9.9.2 Dev-C++ 4.9.9.2 Visual C++ 6.0 Visual C++ 6.0 OpenCV 1.0.0 OpenCV 1.0.0

12 Plan Move cursor on screen using the eyes Move cursor on screen using the eyes

13


Download ppt "` Tracking the Eyes using a Webcam Presented by: Kwesi Ackon Kwesi Ackon Supervisor: Mr. J. Connan."

Similar presentations


Ads by Google