AIRCC's International Journal of Computer Science and Information Technology

Jagdish Lal Raheja ¹, Umesh Kumar ¹, K. C. Saravanan ¹

Affiliations
1 Digital Systems Group, Central Electronics Engineering Research Institute (CEERI)/ Council of Scientific and Industrial Research (CSIR), Pilani-333031, Rajasthan, IN

Abstract

In cartographic generalization process essential characteristics and behaviour of objects are to be preserved. When a map is represented graphically, if the represented scale is reduced, then some area features will become too insignificant to be represented, i.e. they will be too small to be viewed and cluttering the whole map making it illegible to view even according to the map's theme. These unimportant small area spatial objects are to be eliminated. This elimination procedure is part of generalization process called Selection. This paper presents a new approach to selection process of cartographic generalization. This technique includes three steps. These involve a process to calculate area of the spatial object i.e. polygon, drawing a virtual square, elimination of the spatial object after processing. Generally selection process doesn't consider the spatial density and eliminates all areas less than the threshold value. In virtual square method according to spatial density objects are eliminated. A virtual square is drawn around a spatial object and total number of spatial objects inside it is counted. If the count is greater than threshold then it is eliminated. This technique described in the paper has been tested using many examples and deployed in an application which is developed using Microsoft Visual C++, a robust platform for application development.

Keywords

Cartography, Elimination, Generalization, Map Object, Selection Process, Virtual Square.

Full Text

   

Jagdish Lal Raheja ¹, Umesh Kumar ¹

Affiliations
1 Digital Systems Group, Central Electronics Engineering Research Institute (CEERI)/Council of Scientific and Industrial Research (CSIR), Pilani-333031, Rajasthan, IN

Abstract

In the field of image processing it is very interesting to recognize the human gesture for general life applications. For example, observing the gesture of a driver when he/she is driving and alerting him/her when in sleepy mood will be quite useful. Human gestures can be identified by observing the different movements of eyes, mouth, nose and hands. In this paper we are focusing on the human face for recognizing expression. Many techniques are available to recognize face. In this paper, face is detected using the Viola and Jones techniques. This paper introduces a simple architecture for human facial expression recognition. The approach is based on add-boosted classifier for face detection and simple token finding and matching using back propagation neural network. This approach can be adapted to real time system very easily. The paper briefly describes the schemes of capturing the image from web cam, detecting the face, processing the image to recognize the gestures as well as few results.

Keywords

Add Boosted Classifier, Edge Detection, Face Detection, Gesture Recognition, Neural Network, Token Detection.

Full Text