We propose a deep-learning-based classification of data pages used in holographic memory. We numerically investigated the classification performance of a conventional multilayer perceptron (MLP) and a deep neural network, under the condition that reconstructed page data are contaminated by some noise and are randomly laterally shifted. When data pages are randomly laterally shifted, the MLP was found to have a classification accuracy of 93.02%, whereas the deep neural network was able to classify data pages at an accuracy of 99.98%. The accuracy of the deep neural network is 2 orders of magnitude better than the MLP.

We have developed an adaptive image enhancement architecture composed of new algorithm and new circuit for mobile system. The algorithm utilizes the scene change detection and realizes flicker-less enhancement of video images by a time-domain filter. The circuit is built in the LCD driver and enables real time enhancement of QVGA 30fps images with only 2.5mW power consumption.

No abstract

The brighter, more portable projectors that have emerged in recent years have driven an increase in opportunities to use projectors in well‐lit rooms and to project images on objects other than special screens. However, the color and tone of color images projected under such diverse environments are subject to degradation due to the effects of ambient light and of the projection surface. Therefore, we developed WallShot™, a technology for correcting the color and tone of a projected image based on detected environmental effects by color sensor. We validated the effect of the corrections through psychophysical experiments.