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•
26 Dec 2017
TL;DR: In this paper, an image conversion network acquisition method based on a trained first network is presented, which consists of two steps: a first image and a second image are acquired; and the inputting images are inputted to the first network respectively, according to a preset fusion weight.
Abstract: The invention discloses an image conversion network acquisition method, an acquisition device, computing equipment and a computer storage medium. The image conversion network acquisition method is executed based on a trained first network. The method comprises steps: a first image and a second image are acquired; and the first image and the second image are inputted to the first network respectively, according to a preset fusion weight, weighting operation is carried out on a weighting operation layer of the first network, and a second network corresponding to the style after the first image and the second image are fused is obtained. According to the technical scheme provided by the invention, by using the trained first network, the image conversion network corresponding to the style after the two style images are fused can be obtained quickly, the image conversion network efficiency can be effectively improved, and the image conversion network processing mode is optimized.
3 citations
Patent•
17 Feb 2005
TL;DR: In this article, a method for manufacturing the radiation image conversion panel by bonding a protective layer and a stimulable phosphor layer together with each other is characterized in that both layers are bonded to each other after ridding the surface of at least one chosen from the protective layer of dust by a dust removal method.
Abstract: PROBLEM TO BE SOLVED: To provide a method for manufacturing a radiation image conversion panel which is free from the adhesion of dust and dirt and makes it possible to obtain excellent images with less noise and the radiation image conversion panel. SOLUTION: The method for manufacturing the radiation image conversion panel by bonding a protective layer and a stimulable phosphor layer together with each other is characterized in that both layers are bonded to each other after ridding the surface of at least one chosen from the protective layer and the stimulable phosphor layer of dust by a dust removal method. COPYRIGHT: (C)2005,JPO&NCIPI
3 citations
Patent•
17 Feb 1998
TL;DR: In this article, the image manuscript data of stationary image captured by a computer is converted to pattern image data of a predetermined tone according to an image conversion program converting the arrangement of colors or hues and the pattern data is outputted to an output sheet 1 such as paper or a plastic film and a negative image embossed plate 3 is formed from the white and black image manuscript and the output sheet is successively superposed to be heated and pressed.
Abstract: PROBLEM TO BE SOLVED: To efficiently produce an image forming material capable of being produced even when there is no actual object of the original picture and having irregular surface imparting a surface quality feeling along the content of an image like writing touch in stable quality. SOLUTION: The image manuscript data of stationary image captured by a computer is converted to pattern image data of a predetermined tone according to an image conversion program converting the arrangement of colors or hues and the pattern image data is outputted to an output sheet 1 such as paper or a plastic film and a white and black image manuscript is formed from the image manuscript data or pattern image data and a negative image embossed plate 3 is formed from the white and black image manuscript and the output sheet 1, a transparent or translucent thermosetting film and the embossed plate are successively superposed to be heated and pressed.
3 citations
Patent•
12 Oct 2006
TL;DR: In this article, an image in which converted images D21" are composed adjacently to each other in a display device, is extracted from the distribution image as a transmission image D21 and transmitted to the display device.
Abstract: PROBLEM TO BE SOLVED: To distribute an image so as to be appropriately displayed even if the distribution image has a data amount beyond the bandwidth of a transmission line. SOLUTION: In a display device, an image quality deteriorated region caused by a tap structure is excluded from a converted image D21'-1 obtained by applying image conversion processing due to arithmetic using a tap coefficient to a transmission image, a converted image D21"-1 in the remaining high image quality region is composed at a position corresponding to the position on the distribution image, and a display image is generated. In a distribution device, an image in which converted images D21" are composed adjacently to each other in the display device, is extracted from the distribution image as a transmission image D21 and transmitted to the display device. The present invention may be applicable to a server which distributes an image. COPYRIGHT: (C)2008,JPO&INPIT
3 citations
Patent•
24 Jun 2014
TL;DR: In this paper, a video display system consisting of a vehicle information unit, a space generating unit, an image conversion unit, and a camera information unit is proposed to display a plurality of camera videos as input.
Abstract: Provided is a video display system which receives a plurality of camera videos as input, comprising a vehicle information unit, a space generating unit, an image conversion unit, and a camera information unit. According to information of a travel state which is acquired from the vehicle information unit, the space generating unit generates a periphery space of a range which it is possible to photograph with cameras, the image conversion unit creates an image based on images of the cameras, and projects the created image in the generated space. The image conversion unit creates a composite image of the images of a plurality of cameras viewed from virtual camera locations which the camera information unit has set, while changing either the virtual camera locations or a blend ratio when compositing the image.
3 citations