Improvement of Image Classification by Multiple Optical Scattering

Multiple optical scattering occurs when light propagates in a non-uniform medium. During the multiple scattering, images were distorted and spatial information they carried became scrambled. However, image is not lost but presents form of speckle patterns (SPs). In this study, we built up an random system based on liquid crystal display (LCD) RGB laser source. We found that classification can be improved by help which considered as feedforward neural network to extracts features from image. Along with ridge deployed computer, achieved excellent accuracy higher than 94%, for variety data sets covering medical, agricultural, environmental protection other fields. addition, proposed has advantages high speed, low power consumption, miniaturization, suitable deploying edge computing applications.