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
27 Apr 2011
TL;DR: In this article, an image conversion device which converts non-three dimensional image data into three-dimensional image data comprising left eye image data and right eye data is presented. But it is not shown in a 3D image.
Abstract: Disclosed is an image conversion device which converts non-three dimensional image data into three-dimensional image data comprising left eye image data and right eye image data. The image conversion device comprises an input unit which inputs the non-three dimensional image, and a conversion unit which generates and outputs the left eye image data and the right eye image data based on the non-three dimensional image input by the input unit. When displaying the three-dimensional image consisting of a left eye image and a right eye image on a display device capable of displaying a three-dimensional image, the conversion unit generates the left-eye image data and the right eye image data such that the user perceives predetermined regions in a horizontal direction of the displayed three-dimensional image, in a vertical direction on a display surface of the display device, as positioned at a position farthest from the user, and perceives regions other than the predetermined regions as positioned increasingly closer to the user as said regions approach the left and right edges of the three-dimensional image.

17 citations

Patent
26 Sep 1995
TL;DR: In this paper, an image synthesis method and the image synthesizer in which plural images having different image states due to difference from an image pickup condition or the like are synthesized in an excellent way.
Abstract: PROBLEM TO BE SOLVED: To obtain the image synthesis method and the image synthesizer in which plural images having different image states due to difference from an image pickup condition or the like are synthesized in an excellent way. SOLUTION: Gradation conversion sections 31, 32 correct input images a, b depending on image states in an overlapped image area. In this case, gradation conversion is applied to the input images a, b, to correct them so that the lightness in the overlapped image area of the two images is made equal. Furthermore, an image conversion synthesis section 50 conducts synthesis processing so that the center of the overlapped part comes to a joint and the input images a, b whose lightness is corrected by the gradation conversion sections 31, 32 are converted by a conversion parameter and the result is synthesized into one image.

17 citations

Patent
11 Jul 2003
TL;DR: In this paper, a method and a device for converting a perspective image obtained by the perspective of various monitor cameras so as to develop and display it on a plan view as expressed on a map is presented.
Abstract: A method and a device for converting a perspective image obtained by the perspective of various monitor cameras so as to develop and display it on a plan view as expressed on a map. From the perspective video obtained by an ordinary camera, information required for a plan-view development is read in, developed into a plan view such as a map by a mathematical expression, combined/concatenated into a large road surface development diagram. For example, a plurality of ordinary video cameras are attached around a bus so as to constitute the entire field of view and pick up images of a road outside the bus with a certain angle, i.e., a dip. The images of the road surface are developed as images of a map, which are processed and combined to generate a road image around the bus. This is obtained by calculating a mathematical expression.

17 citations

Patent
Osamu Wada1
25 Mar 2002
TL;DR: In this article, a conversion data generation block (130) for generating data for color conversion for each of the R, G, and B image signal values, a conversion storage block (123) for storing data for the color conversion, and a conversion block (125) for extracting desired color conversion data for each image signal value in accordance with a signal value input.
Abstract: An image processing system, an information storage medium, and an image processing method capable of image conversion with less storage capacity when image data is converted for reproducing a target color. The system comprises a conversion data generation block (130) for generating data for color conversion for each of R, G, and B image signal values, a conversion data storage block (123) for storing data for the color conversion, a conversion block (125) for extracting desired color conversion data for each of the R, G, and B image signal values in accordance with a signal value input, and a unification block (127) for unifying a plurality of extracted color conversion data into one and obtaining image signal values R3, G3, and B3.

17 citations

Patent
28 Oct 2009
TL;DR: In this paper, a method for measuring clothes dimension of human body online, comprising a network video transmission device, an image pre-processing device, image conversion device and a three-dimensional dimension measurement device, was proposed.
Abstract: The invention relates to a method for measuring clothes dimension of human body online, comprising a network video transmission device, an image pre-processing device, an image conversion device and a three-dimensional dimension measurement device; the network video transmission device is used for guiding the standing posture and position of the human to be measured; furthermore, the images of the human body on forward surface, side surface and back surface are captured; the human images of three angles are guided in the image pre-processing device, thus extracting human profile; the human profile is input to the image conversion device to generate and correct a three-dimensional human model; and the needed human dimension is extracted on the three-dimensional human model by the three-dimensional model dimension measurement device. The method has extremely strong applicability and operability, sufficiently utilizes the most common equipment such as household network platforms, general computers, general video devices and the like to measure the human body, needs no special hardware equipments, and has simple, convenient and quick operation procedure.

17 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