click here to download the abstract of report project
ABSTRACT
We are providing report project in this paper. On-Air painting is one of the many attractive and demanding research field in domain of pattern identification and image rectification. It contributes immensely to a new human machine interaction application. The traditional art of writing in the age of digital era is being replaced by digital art. For creating, rectifying, and visualizing paint in air, we are using hand gesture recognition with the use of machine learning algorithm by using python programming, which creates natural interaction between man and machine and allows the user to draw in the air in a natural way. Paint software have been in our life since 1985 with the first release of windows 1.0. Artists use paint to create beautiful canvas. With the profound growth in technology, new methods and devices have come up but requirement of another input device like mouse or a pencil are still there. We propose unified CNN-RNN approach for shade detection and segmentation strategies to accomplish this goal. Color detection is a shade handling strategy where we can identify any tone in each scope of HSV shading space which coordinates the advantages of both CNNs (Convolutional Neural Networks) and RNNs (Recurrent Neural Networks).
INTRODUCTION
The traditional art of writing in the age of digital era is being replaced by digital art. Digital art refers to the forms of speech and the transmission of art in digital form. Tracking an object is viewed as a significant importance inside the field of Computer Vision. The innovation of fast computers, the accessibility of affordable and excellent video cameras and the requirements of computerized video examination have given rise to importance in tracking methods. Free-to-air collaboration is a hotly debated topic in development of communication and release of consumer-level computer platforms such as Microsoft Kinect and other movement tracking advancements. In spite of recent advances in object detection and tracking, accurate and robust detection and tracking of the fingertip remains a challenging task, primarily due to small dimension of the fingertip. Moreover, the initialization and termination of mid-air finger writing is also challenging due to the absence of any standard delimiting criterion. To solve these problems, we propose a new writing hand pose detection algorithm for initialization of air-writing using the Faster R-CNN framework for accurate hand detection followed by hand segmentation and finally counting the number of raised fingers based on geometrical properties of the hand. Further, we propose a robust fingertip detection and tracking approach using a new signature function called distance-weighted curvature entropy. Finally, a fingertip velocity-based termination criterion is used as a delimiter to mark the completion of the air-writing gesture. Experiments show the superiority of the proposed fingertip detection and tracking algorithm over state-of-the-art approaches giving a mean precision of 73.1% while achieving real-time performance at 18.5 fps, a condition which is of vital importance to air-writing.
