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
31 Mar 2003
TL;DR: In this paper, an image is generated by drawing an object other than a heat-haze polygon HPL (an object for conversion of an original image) in a drawing buffer.
Abstract: PROBLEM TO BE SOLVED: To provide an image-generating system which effectively realizes an image effect, such as a heat-haze effect with a less processing load, and also provide a program and an information storage medium therefor. SOLUTION: An original image is generated by drawing an object other than a heat-haze polygon HPL (an object for conversion of an original image) in a drawing buffer. The heat-haze polygon is perspectively converted, and texture coordinates are found based on a perspective projection position. A heat-haze image (image for original image conversion) is mapped to the heat-haze polygon, based on the original image designated by the texture coordinates and then drawn in the drawing buffer. The texture coordinates are found, by deviating the perspective projection position of the heat-haze polygon by a prescribed deviation quantity. The heat-haze polygon, which is located in a deeper side from viewpoint by a virtual camera, is deviated by a larger quantity. The depth value is set to the heat-haze polygon, and hidden surface deletion processing is executed. Parameters, such as size, position, moving speed, texture coordinate deviation quantity and so on are set to the heat-haze polygon. COPYRIGHT: (C)2005,JPO&NCIPI

8 citations

Patent
14 Jul 1994
TL;DR: In this article, the number of delay fields of the memory is controlled based on the motion vector of a motion vector detection circuit and also decides an input animation or an input still picture.
Abstract: PURPOSE:To artificially convert a two-dimensional image into a three- dimensional image. CONSTITUTION:One of both two-dimensional signals received from an input terminal 1 is supplied to a lin memory 3 and a field memory 2 respectively, and the other signal is supplied to a 1st selection circuit 7. A CPU 6 controls the number of delay fields of the memory 2 based on the motion vector of a motion vector detection circuit 5 and also decides an input animation or an input still picture. Then the CPU 6 selects the output of the memory 2 for the animation and selects the output of the memory 3 for the still picture respectively. A 2nd selection circuit 8 selects an input two-dimensional image signal or an input delay signal to output it to the output terminals 9 and 10 based on the direction of the motion vector.

8 citations

Patent
05 Jan 2005
TL;DR: In this article, a three-dimensional image display consisting of a spatial optical modulating element, a front-illumination optical system, and a lens serving as a reproduction image conversion optical system is presented.
Abstract: A three-dimensional image display having a simple structure enabling display of a high-quality reproduced image by effectively using the focal adjustment function of the eyes of the observer. The three-dimensional image display comprises a spatial optical modulating element, a front-illumination optical system, and a lens serving as a reproduction image conversion optical system. An image is reproduced on the back focal plane of the lens by the diffraction of specific order by the spatial optical modulation element. At least either the luminescent spot distance between the luminance spots constituting a target reproduced image to be displayed or the initial phase value of each luminance spot is set in such a way that peaks of reproducing light reaching within the region where the reproduced image can be observed are present in multiple positions. Therefore, a hologram by which the target reproduced image can be displayed is given to the spatial optical modulation element. The illuminating light incident on the spatial optical modulation element is amplitude- or phase-modulated in each pixel. To the modulated light, that is, reproducing light, wavefront transformation is applied by the lens and a reproduced image is formed. When the observer positions the pupils of the eyes near the aperture of a mask, the observer can view the displayed reproduced image through the aperture and a semitransparent mirror.

8 citations

Patent
23 Apr 2012
TL;DR: In this paper, a target fish-eye image (100) for object recognition is split into regions in accordance with the direction of distortion of the target fisheye image, and a detected coordinate transformation portion (150) restores the obtained position of an object into the original position by inverse rotation, and outputs a thus obtained result as a detection result.
Abstract: A target fish-eye image (100) for object recognition is split (120) into regions in accordance with the direction of distortion of the target fish-eye image (100). An object recognition portion (130) performs object recognition by using databases (140) prepared in accordance with the regions respectively. The same process is applied to a plurality of target fish-eye images (110) created by rotation of the target fish-eye image (100). A detected coordinate transformation portion (150) restores the obtained position of an object into the original position by inverse rotation, and outputs a thus obtained result as a detection result. Accordingly, detection accuracy in object recognition can be improved, and the quality of data in databases can be reduced. Rotated object images required for database creation are used for creation of databases for object recognition for the fish-eye image. Thus, it is possible to directly use a distorted fish-eye image for object recognition without projective conversion or image conversion based on corrective operation to the fish-eye image.

8 citations

Patent
14 Feb 1997
TL;DR: In this paper, the problem of providing an image processing unit, its control method, image processing system and an output device where a total throughput is improved without increasing the cost is addressed.
Abstract: PROBLEM TO BE SOLVED: To provide an image processing unit, its control method, an image processing system and an output device where a total throughput is improved without increasing the cost. SOLUTION: In a image processing system composed by connecting a digital camera and a printer, the digital camera communicates mutually with the printer by using an interface part 27 at the side of the digital camera and picture elements capable of recording by one scanning of a recording head of the printer are received via the interface section 27. Based on the number of the received picture elements, image data inputted to the digital camera are divided and compressed by an image conversion part 25. COPYRIGHT: (C)1998,JPO

8 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