Topic
Image conversion
About: Image conversion is a research topic. Over the lifetime, 2490 publications have been published within this topic receiving 19077 citations.
Papers published on a yearly basis
Papers
More filters
•
03 Mar 2010TL;DR: In this article, the input image signal is split into a regional contrast signal and a detail signal, followed by stretching separately the dynamic ranges for at least one of the signals, and highlights are identified, and for the highlights the dynamic range is stretched to an even higher degree than for the regional contrast signals.
Abstract: In a method, unit and display device, the input image signal is split into a regional contrast signal and a detail signal, followed by stretching separately the dynamic ranges for at least one of the signals. The dynamic range for the regional contrast signal is stretched with a higher stretch ratio than the dynamic range for the detail signal. The stretch ratio for the detail signal may be near 1 or 1. Further, highlights are identified, and for the highlights the dynamic range is stretched to an even higher degree than for the regional contrast signal.
21 citations
••
24 May 2018
TL;DR: This paper proposes a novel scheme based on fragment-to-grayscale image conversion and deep learning to extract more hidden features and therefore improve the accuracy of classification of file fragments.
Abstract: File fragment classification is an important step in digital forensics. The most popular method is based on traditional machine learning by extracting features like N-gram, Shannon entropy or Hamming weights. However, these features are far from enough to classify file fragments. In this paper, we propose a novel scheme based on fragment-to-grayscale image conversion and deep learning to extract more hidden features and therefore improve the accuracy of classification. Benefit from the multi-layered feature maps, our deep convolution neural network (CNN) model can extract nearly ten thousands of features through the non-linear connections between neurons. Our proposed CNN model was trained and tested on the public dataset GovDocs. The experiments results show that we can achieve 70.9% accuracy in classification, which is higher than those of existing works.
21 citations
•
23 Jun 2000TL;DR: In this article, the system has an image signal converting section 10 that is provided with an input change-over switch section 12 which takes in the frame image of an image to be displayed based on input image signals and input synchronization signals.
Abstract: PROBLEM TO BE SOLVED: To prevent deterioration in picture quality as far as possible. SOLUTION: The system has an image signal converting section 10 that is provided with an input change-over switch section 12 which takes in the frame image of an image to be displayed based on input image signals and input synchronization signals, input frame memories 131 to 13m which record the frame image taken in by the section 12, a black raster image generating section 14 which generates a black raster image, an image conversion processing section 15 which generates an interpolation image or insert the black raster image between frame images corresponding to image information based on the image information, the input synchronization signals and output synchronization signals or generates an output frame image from the input frame image recorded in the input frame memories by thinning out the frame images, output frame memories 171 to 17n which record the output frame images and an output control switch section 18 which takes out the output image signals and the output synchronization signals from the output frame image recorded in the output frame memories and transmits the signals to a display device 50. COPYRIGHT: (C)2002,JPO
21 citations
•
29 Sep 2017
TL;DR: In this article, an unpaired image conversion method using a cycle consistent adversarial network (CycleGAN) is proposed, which consists of a general module, a loss function module, an objective function module and a training network module.
Abstract: The invention provides an unpaired image conversion method using a cycle consistent adversarial network The main content of the unpaired image conversion method comprises a general module, a loss function module, an objective function module and a training network module The process is that firstly modeling of a discriminator is performed by using a generative adversarial network and a mapping function is designed for an original set domain X so that the generated image is enabled to have the image characteristics of a target set domain Y, secondary loss function modeling is performed on the conversion process, the classifier is enabled to be increasingly difficult to discriminate the generated image by minimizing the loss function and the success rate of unpaired image conversion can be enhanced Different styles of photos or images can be processed, the least square method and the maximum likelihood probability can be provided to minimize the loss function, and the simulation degree of image conversion can also be enhanced
21 citations
•
06 Mar 2018
TL;DR: In this paper, a generative neural network with combination of the image content characteristics and the style characteristics is used for image conversion, and the resolution of the converted image is enhanced by using a super-resolution neural network sothat the high-resolution converted image can be acquired.
Abstract: The invention provides an image processing method, processing device and processing equipment. Image conversion is realized by using a generative neural network with combination of the image content characteristics and the style characteristics, and the resolution of the converted image outputted by the generative neural network is enhanced accordingly by using a super-resolution neural network sothat the high-resolution converted image can be acquired. The image processing method comprises the steps that an input image is acquired; a first noise image and a second noise image are acquired; image conversion processing is performed on the input image by using the generative neural network according to the input image and the first noise image so as to output the converted first output image; and high-resolution conversion processing is performed on the first output image and the second noise image by using the super-resolution neural network so as to output a second output image, wherein the first noise image and the second noise image are different.
21 citations