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
Patent•
20 Mar 2014
TL;DR: In this paper, an image formation device capable of preventing erroneously recognizing an image of a printing original as an erasable image even if the image of the printing original is printed with a non-erasable color material was proposed.
Abstract: PROBLEM TO BE SOLVED: To provide an image formation device capable of preventing erroneously recognizing an image of a printing original as an erasable image even if the image of the printing original is printed with an erasable color material.SOLUTION: A image formation device, having a printing part to print the printing original on a sheet with a non-erasable color material, includes: an erasable color material determination part to determine whether or not the image of the printing original is the erasable color material; and a printing image conversion part to convert a color of the image to be printed to a different color from a color of the erasable color material if the erasable color material determination part determines that it is the erasable color material.
Patent•
25 Mar 2021
TL;DR: In this paper, an image conversion device for dividing an image into blocks of a prescribed size and converting an encoded picture including a slice that includes an integral number of rectangular areas into which the blocks are combined into one or more block lines.
Abstract: The present invention provides an image conversion device for dividing an image into blocks of a prescribed size and converting an encoded picture including a slice that includes an integral number of rectangular areas into which the blocks are combined into one or more block lines. If a slice boundary and a rectangular area boundary are the same when determining whether the encoded picture is to apply a loop filter, the device converts the encoded picture so as to reconstruct the relationship of the slice and the rectangular area included in the encoded picture, and if the slice boundary and the rectangular area boundary are not the same when determining whether the encoded picture is to apply a loop filter, the device converts the encoded picture so as not to change the relationship of the slice and the rectangular area included in the encoded picture.
Patent•
08 Nov 2019
TL;DR: In this article, a free viewpoint image generation method was proposed, which comprises the steps: collecting a plurality of first image frames comprising atarget user motion scene at plurality of viewpoints; identifying a first human body posture parameter of each first image frame in the plurality of image frames; acquiring a second human body position parameter of the newly added viewpoint; controlling the preset human body model to fit a second body posture parameters; and inputting the moving image frame into a pre-trained image conversion model, and obtaining a second image frame which corresponds to the new viewpoint and contains the moving scene
Abstract: The invention provides a free viewpoint image generation method and a free viewpoint image generation device. The method comprises the steps: collecting a plurality of first image frames comprising atarget user motion scene at a plurality of viewpoints; identifying a first human body posture parameter of each first image frame in the plurality of first image frames; acquiring a second human bodyposture parameter of the newly added viewpoint; controlling the preset human body model to fit a second human body posture parameter, and obtaining a moving image frame of the preset human body modelunder the newly added viewpoint; and inputting the moving image frame into a pre-trained image conversion model, and obtaining a second image frame which corresponds to the newly added viewpoint and contains the moving scene of the target user. According to the method, the image frames under the multiple viewpoints are obtained, the moving image frames under the newly-added viewpoints are obtainedaccording to the image frames under the multiple viewpoints, then the image frames containing the target user moving scene and corresponding to the newly-added viewpoints are calculated through the image conversion model, and the calculation amount and complexity of collecting the image frames are reduced.
Patent•
12 Jul 2018
TL;DR: In this article, the authors presented an image acquisition device and method capable of simultaneously acquiring a two-dimensional image and a 3D image through a one-time photographing step.
Abstract: The purpose of the present invention is to provide an image acquisition device and method capable of simultaneously acquiring a two-dimensional image and a three-dimensional image through a one-time photographing step. To this end, the present invention comprises: a control module for controlling a first photographing for acquiring a two-dimensional image and a second photographing for acquiring a three-dimensional image; an X-ray generation unit for irradiating an object, to be inspected, with X-rays in each of first and second doses at at least one position in accordance with the first photographing and at a plurality of second positions in accordance with the second photographing; an X-ray detector for receiving the X-rays by which the object to be inspected was irradiated, and acquiring data corresponding to the first and second photographings; and an image conversion unit for converting data of the first photographing into a two-dimensional image and converting data of the second photographing into a three-dimensional image, wherein the first dose is larger than the second dose, and the first position and the second positions are within a preset trajectory.