Welcome to the upgraded BRAC University Institutional Repository. We are currently organizing collections after a recent system upgrade. Homepage category counters may temporarily show lower numbers while syncing, but over 27,000 repository items remain safe and accessible. Please use the search bar to find theses, scholarly outputs, and institutional documents.

An emergency based image filtering system

Citation

Abstract

With the invention of new technology day by day the rate of inhuman works is also getting increased as well which ,making our life easier but at the same time unsafe. The new advanced technologies are permitting us to realize real time smart system that helps to provide advanced services to the users by giving real time image processing and currently, this smart system is also being imbibed to build the model according to the users’ demand and interest. In this proposed model, an emergency image filtration system has introduced. Through our proposed model we tried to emphasis to implement it for security system. In low light or some other reasons image capturing devices failed to capture perfect or clear image. Insecurity system sometimes it is a must to get the clear image to identify the real fact. For that reason we proposed to filter noisy images in real time to check the fact on exact time. For noisy image we have taken ‘salt and pepper noise’ as a type of noise to check whether the received image is noisy or not. In addition, after assuring the presence of noise, an image filtering system is inaugurated which is suitable filtration for the specific noise category that can enhance the visualization of any degraded images in emergency basis in the server. After the filtration process is held, the denoised image is saved in the server again to share with other connecting devices through that server. As a result, the percentage of noise level for particular images can be identified. In particular, the proposed system relies on a smart device that assembles image filtration to deliberately provide the users with strained output image in an observed network. The final transmission of the refining data has done by the devices which are connected with virtual server. Finally, through running definite image filtering process, running in the system, that controls the smart environment security system and will help us to prevent various unwanted inhuman works. The system has been designed that can be easily extensible to other smart technologies and its effectiveness has been evaluated in various security as well as safety platform.

Description

Cataloged from PDF version of thesis.
Includes bibliographical references (pages 29-30).
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2018.

Publisher Link

Type

Thesis