Sign Language to English Text

Continuous recognition of sign language has many practical applications and it can help to improve the quality of life of deaf persons by facilitating their interaction with hearing populate. When somebody gets into the camera area and makes some hands gestures in front of the camera, the application should detect the type of the gesture, and raise an event. When a hands gesture is detected, the application could perform different actions depending on the type of the gesture.

This project introduces a hand gesture recognition system to recognize 'dynamic gestures' of which a single gesture is performed in complex background and better results in white background. Unlike previous gesture recognition systems, our system neither uses instrumented glove nor any markers. The new barehanded proposed technique uses only 2D video input. This technique involves detecting the hand location, its convex hull, and its defects. Then obtained information is been used in the recognition phase of the gesture.

Hence whenever a gesture is done the system should recognize what sign it is. The work presented here solves two major problems of hand pose recognition:

(A) Determining what pose is shown in a given, input picture by using a convex hull algorithm and convexity defects and

(B) Detecting the presence of a known input pose in a given input video. The proposed application aims in providing a computer-based sign-language synthesis output for the deaf and the hearing impaired.

 Moreover the application may be used as a teaching tool for deaf and initial step to communicate with the outside world. Hence to detect this we use convex hull hand recognition with skin color detection approach and to detect the finger count have used three logical conditions and for recognition of alphabet , we have used haar cascade classifier which gives us more optimal and efficient results.