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•
23 Jun 2006TL;DR: An image conversion apparatus for geometrically converting input image data and outputting output image data, includes an inverse coordinate conversion unit configured to inversely convert coordinate values on the coordinate system of the output image from the input image into coordinate values based on the geometric conversion as discussed by the authors.
Abstract: An image conversion apparatus for geometrically converting input image data and outputting output image data, includes an inverse coordinate conversion unit configured to inversely convert coordinate values on the coordinate system of the output image data into coordinate values on the coordinate system of the input image data based on the geometric conversion. When a region between neighboring pixels of the coordinate system of the input image data is divided into a plurality of divisions, the inverse coordinate conversion unit changes the inversely converted coordinate values so that coordinate values which belong to an identical division of the inversely converted coordinate values have a random two-dimensional array.
Patent•
12 Mar 2020
TL;DR: In this paper, a method, device, and mobile platform for generating a dynamic image, and a storage medium is presented, which includes obtaining video data, the video data being configured to be output by at least one photographing device on a mobile platform.
Abstract: Disclosed are a method, device, and mobile platform for generating a dynamic image, and a storage medium. The method comprises: obtaining video data, the video data being configured to be output by at least one photographing device on a mobile platform; and performing image conversion processing on the video data, so as to generate a dynamic image corresponding to at least part of the video data. In the method, device, and mobile platform for generating a dynamic image, and the storage medium provided by the present invention, image conversion processing is performed on video data to generate a dynamic image corresponding to at least part of the video data, such that the existing issue of the prior art in which there are more restrictions on the use of video image data on the Internet is resolved, so as to improve the compatibility of the image data, expand the reach of the image data, and accordingly ensure a certain degree of convenience and flexibility for a user using the image data, thereby effectively improving the practicality of the method.
Patent•
20 Mar 2018
TL;DR: In this article, a top-view image conversion method and an automobile are presented. The method comprises the steps of: capturing a first image having conversion datum lines which are parallel to each other in a real environment in an original image shot by a vehicle device; performing conversion processing of the first image based on an image conversion rule; generating a top view image corresponding to the first images; and allowing the two or more than two conversion datuma lines to be parallel to another in the topview image.
Abstract: The embodiment of the invention discloses a top-view image conversion method and device, and an automobile. The method comprises the steps of: capturing a first image having conversion datum lines which are parallel to each other in a real environment in an original image shot by a vehicle device; performing conversion processing of the first image based on an image conversion rule; generating a top-view image corresponding to the first image; and allowing the two or more than two conversion datum lines to be parallel to each other in the top-view image. The top-view image conversion method and device, and the automobile can perform conversion of the original image shot by the vehicle device such as stretching, rotation and the like according to a parallel relation of the conversion datumlines in reality in the condition without measuring parameters of a vidicon or a camera such as the height, the focal length and the like, and can generate a top-view image, and therefore, the conversion process is simple and easy and can perform conversion of a top-view image for images with different sources.
Patent•
16 Aug 2019
TL;DR: In this article, a method for image conversion comprises the steps of: obtaining a bright-field image, performing preprocessing so that the outline of a cell for the bright field image is revealed using a first machine learning algorithm and converting the preprocessed bright field images into a fluorescence image revealing a nucleus of the cell.
Abstract: According to one embodiment of the present invention, a method for image conversion comprises the steps of: obtaining a bright-field image; performing preprocessing so that the outline of a cell for the bright-field image is revealed using a first machine learning algorithm and converting the preprocessed bright-field image into a fluorescence image revealing a nucleus of the cell; and correcting the converted fluorescence image using a second machine learning algorithm. The first machine learning algorithm may perform learning using a plurality of bright-field images. The second machine learning algorithm may perform learning using the bright-field images and a plurality of fluorescence images converted from the bright-field images by the first machine learning algorithm.
Patent•
08 May 2014
TL;DR: In this article, a coordinate conversion table for image conversion is stored in a work memory and the array data of M rows and N columns, which constitute one block, are stored in the work memory.
Abstract: PROBLEM TO BE SOLVED: To efficiently compress a coordinate conversion table for image conversion and to reduce cost of a required memory.SOLUTION: A data input section 210 inputs a coordinate conversion table for image conversion as original array data R. A block division section 220 divides the data into a plurality of blocks. Array data of M rows and N columns, which constitute one block, is stored in a work memory 231. A lateral direction first replacement section 232 performs processing for replacing a numerical value in individual cells constituting the array data with a differential value in a lateral direction, and a vertical direction second replacement section 234 performs processing for replacing the numerical value with a differential value in a vertical direction. An inter-block difference calculation section 240 performs differential calculation between blocks, and final compressed array data W is outputted from a data output section 250. An image conversion device stores the coordinate conversion table which is thus compressed in a memory, expands it if need and performs image conversion while referring to the table.