REAL TIME RECOGNITION OF COLORED AIR WRITTEN CHARACTERS

Abstract

Character Recognition has been comprehensively studied in the last half century and has advanced to a level, adequate to produce technology driven applications. Now, the advancement in computational power enables the implementation iof the present Character Recognition methodologies and also creates an increasing demand ion many emerging application domains, which require more advanced methodologies. Researchers have worked ion many methodologies for Recognizing Text or Character from a handwritten or already computer printed piece of paper to store the data obtained in digital form.

In this project our main aim was on recognizing characters in real time from the user’s gesture when he is in his writing phase. For implementing the aforesaid work the user’s gesture needed to be traced on a real time basis for getting a base to recognize the letter which he is writing. The writing part is realized on a paperless scheme in which the user only need to air write the characters which he wants to write by just affixing any colored piece of object to his finger. Tracing part of letters has been deployed on the colored object which is being attached to the user’s finger. The gestures of hand (object attached to it) in real time is captured using camera and is simultaneously being fed to Matlab for further processing.

Our preliminary aim of detecting the colored object and then tracking is performed using the color identifying algorithm, which uses background subtraction strategy, noise filtering, binary image conversion and blob extraction to iv

recognize a specific color in the video feed. Then the corresponding pixel on the GUI (Graphic user interface) is being draw to track where all the color has been. When a complete character is drawn, a signal is send to Matlab by the user for the next part of recognizing that character. Further work of recognizing the letters is carried out by using the traced part of the object. This traced path on the GUI is sent in the form of an image for further processing to extract the letters written on it. The part of extracting characters from this image is performed using template matching technique. This technique uses a database of characters and numbers, which needs to be stored in their binary from in an M x N cell matrix to be used as templates for comparison purpose. Further the traced image is gone through various preprocessing steps such as Grayscale conversion, Filtering and Feature Extraction which further includes Row detection, Character boundary detection, segmentation and binary conversion. Finally the binary converted character is resized to M x N cell and then correlation method is used for matching this with saved templates. Finally the characters extracted from air written gestures is saved to a text file and also gets displayed simultaneously.

This work might have applications in various domains such as interactive learning sessions in classrooms which no longer will require tutor to be cling to board; effortlessly making notes or writing any information and then saving it only by air writing the gestures in one’s own way without even the need of touching the keyboard, Such applications are beneficial for disabled people; transmitting the relevant information from a distance in some form of encoded character or symbols in utter need of secrecy for military purpose and many more.