Search

Image fusion technique has been widely in use in many applications such as computer vision, surveillance, robotics, medical imaging, remote sensing etc. Medical image fusion plays a vital role to deal with medical issues reflected through images of human body, organs and cells. It is necessary to preserve the fused image in order to keep the relevant information of input images. It is also necessary to keep the fusion process away from introducing any artifacts or inconsistencies. More over image fusion techniques must provide a good quality and must enhance the applications of recent data. This paper elucidates the survey of recent literatures, which dealt medical images like magnetic resonance imaging (MRI), Computed Tomography (CT), Single Photon Emission Computed Tomography (SPECT) and Positron Emission Tomography (PET) of brain. This paper reviews some of the recent medical image fusion algorithm such as Non Sampled Contourlet transform, Directive Contrast, Daubechies complex wavelet transform, Shift-invariant Shearlet transform etc. The merits and demerits of the various image fusion algorithm which developed by the authors is described in the paper. The survey emerges out the optimum fusion algorithm.

The assist device for blind people is much needed in recent days. The gadgets in recent trends are digitized that the blind people are not capable of handling digitized applications hence in our project we design text to voice converter, that converts the eBooks, audiobooks to voice format. In this project the audiobook eBooks are fed into SD card reader after that the sd card reader is interfaced and the Arduino UNO converts the text file to Audio output. The audio books can be heard in headphone\speaker using Arduino UNO. This project is low cost it will be more useful for blind people. Secure voting must be necessary to avoid the fake voting. The problem of fake voting can be solved by using Face detection and Finger vein based Electronics Voting Machine (EVM) system. In electronic voting system the details of the voters are stored; the voting date is recorded and processed digitally. Most of the existing Electronic voting machines has been developed using Radio Frequency ID. In developing countries RFID for each person is not possible due to high cost efficiency. Image processing based EVM also introduced, but it not provides accurate results for the twin persons. The EVM with finger print also not providing the accurate results. So the modified EVM with face and finger vein was introduced to obtain the satisfied result. The Raspberry Pi plays major roll in this project. It is act as a on board CPU work on the operating system called rasbian OS. The necessary hardwires like, camera, finger vein scanner, EVM are connected with Rasperry Pi. The datas of all the voters along with the images of the face and the finger vein are already stored in the system. The camera capture the picture of the person then compare with the stored data and find whether the person is authorized person or not. Once the person is authorized then the next section scan the finger and compare with the data and inform to the system that whether known or unknown. If both face and finger vein are recognized then the voter can register their vote. The fake voting can be completely avoid using this voting method.