Gesture recognition1
Download as PPTX, PDF3 likes941 views
The document discusses gesture recognition systems, which allow humans to interact with machines through visible bodily motions or facial expressions. It describes how such systems work by capturing images of gestures via cameras, preprocessing the images, and identifying the gestures. Examples of applications mentioned include sign language recognition, game control through gestures, and using facial expressions for affective computing. Challenges with gesture recognition systems include the cost and difficulty of developing them, as each gesture must be assigned a specific command.
Gesture recognition1
- 2. The ability of a computer to scan, store, and recognize human gestures as the mode of interaction with machines. A gesture is a form of non-verbal communication in which visible bodily actions communicate particular messages, either in place of speech or together and in parallel with words. Gestures include movement of the hands, face, or other parts of the body.
- 4. User Normal User Physically Challenged User Perform Action Gesture Recognition System Check for Errors Conversion to Binary Image Noise Removal Resizing Picture Conversion to Grayscale Image Identify Gesture Zooming in Binary Picture Crop Image «extend» Update Background Picture «include» Web Cam Capture Image Transmit Image to System «extend» Locate Hand in Picture
- 5. Gesture Recognition System Hand motion Recognition System Face Recognition System Iris Recognition System
- 6. In order to detect hand gesture, data about hand will have to be collected. A decision has to be made as to the nature and source of the data. Two possible technologies to provide this information are: 1)A glove with sensor attached that measure the position of finger joints. 2)An optical method (Hand)
- 13. Task of identify an already detected face as a known or unknown face. In more advance case “Telling exactly who’s face it is?” Identify an object as a face and Decide if this face is locate it in input image some one known or unknown
- 16. Anger Fear Disgust Happy Sad Surprise
- 17. Iris recognition is an automated method of biometric identification that uses mathematical pattern-recognition techniques on video images of the irises of an individual's eyes, whose complex random patterns are unique and can be seen from some distance.
- 21. 1. Sign language recognition 2. Directional indication through pointing. 3. Control through facial gestures 4. Immersive game technology 5. Affective computing. 6. Remote control. 7. Alternative computer interfaces
- 22. • The cost of implementation • Such systems are difficult to develop as each gesture is assigned a specific control command, this system is not platform independent since certain control commands vary as the operating system varies.
- 23. • Control of consumer electronics • Computer games • Security System • Television • In ATM’s