As technology grows people are diverted and are more interested in communicating with machine or computer naturally. This will make machine more compact and portable by avoiding remote, keyboard etc. also it will help them to live in
an environment free from electromagnetic waves. This thought has made 'recognition of natural modality in human
computer interaction' a most appealing and promising research field. Simultaneously it has been observed that using
single mode of interaction limit the complete utilization of commands as well as data flow. In this paper a multimodal
platform, where out of many natural modalities like eye gaze, speech, voice, face etc. human gestures are combined
with human voice is proposed which will minimize the mean square error. This will loosen the strict environment
needed for accurate and robust interaction while using single mode. Gesture complement Speech, gestures are ideal for
direct object manipulation and natural language is used for descriptive tasks. Human computer interaction basically
requires two broad sections recognition and interpretation. Recognition and interpretation of natural modality in
complex binary instruction is a tough task as it integrate real world to virtual environment. The main idea of the paper is
to develop a efficient model for data fusion coming from heterogeneous sensors, camera and microphone. Through this
paper we have analyzed that the efficiency is increased if heterogeneous data (image & voice) is combined at feature
level using artificial intelligence. The long term goal of this paper is to design a robust system for physically not able or
having less technical knowledge.
Partial Differential Equation (PDE) based, non-linear diffusion approaches are an effective way to denoise the images. In this paper, the work is extended to include anisotropic diffusion, where the diffusivity is a tensor valued function, which can be adapted to local edge orientation. This allows smoothing along the edges, but not perpendicular to it. The diffusion tensor is a function of differential structure of the evolving image itself. Such a feedback leads to nonlinear diffusion filters. It shows improved performance in the presence of noise. The original anisotropic diffusion algorithm updates each point based on four nearest-neighbor differences, the progress of diffusion results in improved edges. In the proposed method the edges are better preserved because diffusion is controlled by the gray level differences of diagonal neighbors in addition to 4 nearest neighbors using coupled PDF formulation. The proposed algorithm gives excellent results for MRI images, Biomedical images and Fingerprint images with noise.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.