Abstract— In conventional LCDs, the backlight is set to maximum luminance regardless of the image. For dark scenes, this approach causes light leakage and power waste. Especially, light leakage in dark scenes degrades the contrast ratio of LCDs; to circumvent this problem, local‐dimming systems have been proposed. In these systems, the LED backlight is divided into several local blocks and the backlight luminance of each local block is controlled individually, and pixel values are adjusted simultaneously according to the luminance profile of the dimmed backlight. In this paper, a method of determining the LED backlight luminance of each local block depending on the image is proposed; this method significantly improves the image quality of LCDs. First, we introduce methods of quantifying light‐leakage at dark gray levels and clipping at bright gray levels. Then, the proposed method to determine the dimming duty, which controls the LED backlight luminance by compromising between these two measures, was derived. The proposed algorithm preserves the original image with little clipping distortion and effectively reduces light leakage.
The impression of quality of images can be enhanced on a high dynamic range (HDR) displays. Generally, a conventional 8‐bit image can be processed to an HDR image by inverse tone mapping operators. Among the operators, brightness discrimination mapping by applying brightness adaptation model attempted to mimic the human visual system. In this paper, we use a brightness adaptation model to derive a brightness discrimination mapping algorithm for HDR displays. The proposed algorithm maximizes a function, which represents the local and global brightness discrimination range by exploiting characteristics of the human visual system. Enhancement of details is verified by visualizing HDR images from dark to bright regions. Improvement of dynamic range is quantified by measuring increased discrimination ratio.
In many industries, prognostic health management (PHM) technology has become important as a key technology to increase reliability and operational efficiency. Recently, several methods using a deep learning architecture to estimate the remaining useful life (RUL) as a part of the PHM have been presented. However, the limitation of existing methods is that they do not explicitly capture the relationship among different time sequences, which reduces the accuracy of RUL estimation. This paper proposes a novel RUL estimation algorithm using the attention mechanism to solve this problem. The proposed method applies scaled dot product attention to the encoder and the decoder consisting of long short-term memory, convolutional neural network and fully connected layer. The encoder applies self-attention to extract the association between time sequences, and the decoder extracts the association between the target RUL value and the time sequences using the representative vector of the RUL. Therefore, the proposed model has better performance to capture the long-term dependency in the sequence data and outperforms other state-of-the-art models in the experimental results. In addition, the extracted attention map shows that our model has better interpretability for RUL estimation.
In various full HD video applications, high-level image enhancement requires localization of overlay text. In this paper, we propose text localization that uses a region-shrinking multistep process to achieve both high accuracy and fast processing in full HD videos.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.