scispace - formally typeset
Search or ask a question
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
More filters
Patent
06 Sep 2018
TL;DR: In this paper, a cell visualization system includes a digital holographic microscopy (DHM) device, a training device, and a virtual staining device, which produces DHM images of cells and colorizes the images based on an algorithm generated by the training device using generative adversarial networks and unpaired training data.
Abstract: A cell visualization system includes a digital holographic microscopy (DHM) device, a training device, and a virtual staining device The DHM device produces DHM images of cells and the virtual staining device colorizes the DHM images based on an algorithm generated by the training device using generative adversarial networks and unpaired training data A computer-implemented method for producing a virtually stained DHM image includes acquiring an image conversion algorithm which was trained using the generative adversarial networks, receiving a DHM image with depictions of one or more cells and virtually staining the DHM image by processing the DHM image using the image conversion algorithm The virtually stained DHM image includes digital colorization of the one or more cells to imitate the appearance of a corresponding actually stained cell

10 citations

Patent
09 May 2019
TL;DR: In this article, an image processing method consisting of acquiring an input image, acquiring a first noise image and a second noise image, and executing image conversion processing on the input image with the first image using a generative neural network, to acquire a first output image; and executing high resolution conversion on the first output images with the second noise images using a super-resolution neural network.
Abstract: There are provided an image processing method and an image processing device. The image processing method comprises: acquiring an input image; acquiring a first noise image and a second noise image; executing image conversion processing on the input image with the first noise image using a generative neural network, to acquire a first output image; and executing high resolution conversion processing on the first output image with the second noise image using a super-resolution neural network, to acquire a second output image, wherein the first noise image is different from the second noise image.

10 citations

Patent
30 Aug 2013
TL;DR: In this article, a birds-eye-view image generation device includes a captured image acquisition unit, an image conversion unit, and a joint setting unit, which sets a line which extends in any direction on an opposite side to the vehicle image from the end point between two radial directions directed to the end points from the two imaging devices.
Abstract: A birds-eye-view image generation device includes a captured image acquisition unit, an image conversion unit, a birds-eye-view image combining unit, and a joint setting unit. The joint setting unit sets any position of a rim of a vehicle image corresponding to a vehicle included in the birds-eye-view image as an end point in an overlapping imaging range in two birds-eye-view images corresponding to two imaging devices of which imaging ranges overlap each other, and sets a line which extends in any direction on an opposite side to the vehicle image from the end point between two radial directions directed to the end point from the two imaging devices, as a joint which joins two birds-eye-view images which are combined.

10 citations

Patent
13 Sep 1996
TL;DR: In this article, a general purpose shared system memory that is used for all processing, including video input/output operations and image conversion operations, is described in a computer system with a multimedia access and control module (MACM).
Abstract: A computer system having a shared system memory, and system software in the computer system, are described herein. One or more user applications execute in the computer system. The computer system has a general purpose, shared system memory that is used for all processing, including video input/output operations and image conversion operations. The computer system also has a multimedia access and control module (MACM), which is the input/output interface between the computer system and the external world. In operation, the MACM receives, at one of its video input ports, video data comprising a video image (such as a frame or a field). The MACM stores the video image in a first buffer contained in a first buffer pool of the system memory. The first buffer pool was previously created by a user application. The user application previously associated the first buffer pool with the MACM's video input port. A video imaging and compression module (VICM) performs image conversion operations. Each user application creates one or more converter contexts of the VICM. Each converter context is capable of performing an image conversion operation. In operation, a converter context of the VICM performs an image conversion operation on the video image stored in the first buffer. Then, the converter context stores the results of the image conversion operation in a second buffer contained in a second buffer pool of the system memory. The second buffer pool is also associated with the user application.

10 citations


Network Information
Related Topics (5)
Image processing
229.9K papers, 3.5M citations
84% related
Feature (computer vision)
128.2K papers, 1.7M citations
83% related
Pixel
136.5K papers, 1.5M citations
82% related
Feature extraction
111.8K papers, 2.1M citations
80% related
Image segmentation
79.6K papers, 1.8M citations
79% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202132
202074
2019117
2018115
2017100
2016107