Random sample measurement and reconstruction of medical image signal using Compressive Sensing

There is an enhancement of network and communication and other technologies, which leads to visualize various applications for common users. Medical systems are one of the very important aspects of the better Healthcare and services. In this regards, Extreme Telesurgery (ETS) is conceptualized that performs compression and transmission of the medical image on real time basis. The success of such remote surgery depends upon the optimal use of compression technique. Traditional compression techniques use various transformations schemes such as Discrete Cosine Transformation (DCT), Fast Fourier Transformation (FFT) and Discrete Wavelet Transformation (DWT), where the core objective is to get more and more zero values. So that encoding becomes more light weighted but these methods are sensitive to noises residing in the channel. Which makes it unsuitable for critical Region of Interest (ROI) compression to get higher visual perception, low Bits Per Pixel (BPP) and Error resilient. This paper illustrates a novel method of image signal measurement and reconstruction using Compressive Sensing (CS), which can be used for such real-time image compression requirements in specific applications.