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
24 Aug 2009
TL;DR: In this paper, a method and an apparatus for displaying 3D images through additional information and a reference image was provided to realize a 3D image having superior presence feelings and reality feelings.
Abstract: A method and an apparatus for displaying 3D images are provided to obtain a 3D image through additional information and a reference image, thereby realizing a 3D image having superior presence feelings and reality feelings. A reference image and additional information indicating temporal and spatial difference with the reference image are obtained from a subject(S310). The reference image is transformed to a sub image through the additional information(S320). The sub image is converted into a pixel row according to an image conversion ratio(S330). The pixel row of the sub image is outputted as a 3D image by a parallax barrier(S360).

1 citations

Patent
17 Jul 2014
TL;DR: In this article, a synthesis system for synthesizing an image effect onto a video and a synthesis method are disclosed, which allows for the synthesis of video and image effects, thereby diversifying and enriching the color effects of a video.
Abstract: A synthesis system for synthesizing an image effect onto a video and a synthesis method are disclosed. Said synthesis system comprises: an image conversion unit, for converting one or a plurality of images into a single image supplemental-effect file; a video editing unit, for reading both the image supplemental-effect file and a video and then synthesizing said file onto a video frame and outputting the final video file. The synthesis system and synthesis method of the present invention allow for the synthesis of video and image effects, thereby diversifying and enriching the color effects of a video.

1 citations

Patent
15 Oct 2019
TL;DR: In this article, a target domain oriented unsupervised image conversion method based on a generative adversarial network is proposed, where a self-encoding reconstruction network is designed, and hierarchical representation of a source domain image is extracted by minimizing reconstruction loss of the source domain images; meanwhile, through a weight sharing strategy, the weights of network layers for encoding and decoding high-level semantic information in two groups of generative adversaries in the network model are shared, so that the output image can keep the basic structure and characteristics of the input image.
Abstract: The invention provides a target domain oriented unsupervised image conversion method based on a generative adversarial network, and belongs to the field of computer vision. The target domain orientedunsupervised image conversion method is used for realizing an unsupervised cross-domain image-to-image conversion task, and belongs to the field of computer vision. According to the target domain oriented unsupervised image conversion method, a self-encoding reconstruction network is designed, and hierarchical representation of a source domain image is extracted by minimizing reconstruction loss of the source domain image; meanwhile, through a weight sharing strategy, the weights of network layers for encoding and decoding high-level semantic information in two groups of generative adversarialnetworks in the network model are shared, so that the output image can keep the basic structure and characteristics of the input image; and then, the two discriminators are respectively used for discriminating whether the input image is a real image or a generated image in respective fields. According to the target domain oriented unsupervised image conversion method, unsupervised cross-domain image conversion can be effectively carried out, and a high-quality image is generated. Experiments prove that the method provided by the invention obtains a good result on standard data sets such as CelebA and the like.

1 citations

Patent
02 Jan 2007
TL;DR: An image conversion apparatus sharing a memory is provided to use the same memory when reducing images or converting the image into YUV420 video frames, thereby improving use efficiency of the memory as discussed by the authors.
Abstract: An image conversion apparatus sharing a memory is provided to use the same memory when reducing images or converting the image into YUV420 video frames, thereby improving use efficiency of the memory. An image conversion apparatus(210) comprises the followings: a reduction unit(111) which reduces YUV422 video frames, transmitted in an image sensor(103), n times; a YUV420 conversion unit(115) which converts the YUV422 video frames into YUV420 video frames; and a memory(201) which is combined with the reduction unit(111) and the YUV420 conversion unit(115) and temporarily stores data necessary for reducing the YUV422 video frame or converting the YUV422 video frame into the YUV420 video frame.

1 citations

01 Jan 2015
TL;DR: In this article, the colour nuances obtained by laser woodworking by measuring colour changes digitally were analyzed globally and colour by colour, and the results showed that the color nuances are represented to a more and less degree, according to the conversion method selected.
Abstract: All previous studies of pyrography have been focussed on colour obtained through modifying the work parameters. This paper analyses colour nuances obtained by laser woodworking by measuring colour changes digitally. The investigated parameter is colour reproduction by laser technology, using different image conversion methods (Halftone Round, Jarvis, and so on). The changes of image reproduction are analysed globally and colour by colour. The results show that the colour nuances are represented to a more and less degree, according to the conversion method selected. To evaluate the aesthetic changes, CIEL*a*b* colour measurements were applied. The results show that laser burning on wood surfaces has a great influence on wood colour. These findings will be useful to develop innovative design possibilities for wood surfaces for furniture and other products.

1 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