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
Proceedings ArticleDOI
01 Dec 2015
TL;DR: Automatic technique of 2D to 3D image conversion is proposed using manifold learning and sequential labeling which generates very reliable and accurate 3D depth maps that are very close to ground truth depths.
Abstract: Automatic technique of 2D to 3D image conversion is proposed using manifold learning and sequential labeling which generates very reliable and accurate 3D depth maps that are very close to ground truth depths. In paper, LLE which is a non linear and neighborhood preserving embedding algorithm is used for depth estimation of a 2D image. And then, fixed point supervised learning algorithm is applied to construct consistent and smooth 3D output. The high dimensional data points or pixels of the input frames can be represented by a linear combination of its nearest neighbors and a lower dimensional point is reconstructed while preserving the local and geometric properties of the frames. The neighbors are assigned to each input point in the image data set and their weight vectors are computed that best linearly reconstruct the input point from its neighbors. To get the depth value of input point in new image, the reconstruction weights of its closest neighbors in training samples are multiplied with their corresponding ground truth depth values. The fixed point learning algorithm takes depths from manifold and other image features as input vectors and generates more consistent and accurate depth images for better 3D conversion.

2 citations

Patent
19 Mar 2009
TL;DR: In this article, a first address conversion coefficient constituted by determining a first horizontal scanning direction address conversion coefficients for converting a X direction address in output image data into a Y direction address of imaging data by being associated with difference between an optical axis center address of the imaging lens and a vertical scanning direction (Y direction) address in an image data address.
Abstract: PROBLEM TO BE SOLVED: To perform various kinds of image processing such as correction of image distortion resulting from an imaging lens, bird's-eye view shot, tilt and shift shot, mirror image inversion of a pickup image, electronic zoom processing by simple structure, inexpensively, and at high speed. SOLUTION: The image processing method is constituted so that a first address conversion coefficient constituted by determining a first horizontal scanning direction address conversion coefficient for converting a horizontal scanning direction (X direction) address in output image data into a horizontal scanning direction address of imaging data by being associated with difference between an optical axis center address of the imaging lens and a vertical scanning direction address in an output image data address, and similarly determining a vertical scanning direction (Y direction) address in the output image data is prepared, the address of the output image data is multiplied by the first address conversion coefficient, and image conversion processing is performed using data of the obtained imaging data address as the output image data. COPYRIGHT: (C)2009,JPO&INPIT

2 citations

Patent
14 Oct 2010
TL;DR: In this paper, a capturing device includes an image sensor (11) generating an image signal; a storage unit (15) setting a second region in a first region; a timing adjusting unit (16) adjusting a timing at which the image signal is read out to write the image signals in the storage unit, and a timing from the storage device to read out from the image sensor.
Abstract: A capturing device includes: an image sensor (11) generating an image signal; a storage unit (15) setting a second region in a first region; a timing adjusting unit (16) adjusting a timing at which the image signal is read out to write the image signal in the storage unit (15), and a timing at which the image signal is read out from the storage unit (15); an image conversion processing unit (131) performing a predetermined process on the image, alternately writing a first image signal corresponding to a full image or a second image signal corresponding to a partial image in the first region in a different frame period, and writing an image signal that is different from the image signal written in the first region in the second region; and an output unit (18) converting and outputting the first and second image signals into an image signal in a predetermined format.

2 citations

Patent
12 Jan 2006
TL;DR: In this article, the problem that an increased printing data quantity in a complicated printing page might lead to a reduction in throughput as a printing system was solved by generating an edge list from an application, and the generated edge list is scanned in the order of scan lines to extract edges.
Abstract: PROBLEM TO BE SOLVED: To solve the problem that an increased printing data quantity in a complicated printing page might lead to a reduction in throughput as a printing system. SOLUTION: Printing data from an application are analyzed to generate an edge list, and the generated edge list is scanned in the order of scan lines to extract edges. An edge list is regenerated from the extracted edges to determine whether image conversion is performed or not. The regenerated edge list is converted to image data, and the regenerated edge list or the image data are transmitted to a printer. COPYRIGHT: (C)2006,JPO&NCIPI

2 citations

Patent
Atsushi Sukenori1
28 Mar 2012
TL;DR: In this article, a display apparatus includes an image storage section that stores plural images; an image conversion section that selects an image from among the plural images and obtains a conversion image by converting the selected image; a schedule setting section that sets a schedule indicating an order and timings of displaying the images stored in the image storage and the conversion image obtained by the image conversion.
Abstract: A display apparatus includes: an image storage section that stores plural images; an image conversion section that selects an image from among the plural images and obtains a conversion image by converting the selected image; a schedule setting section that sets a schedule indicating an order and timings of displaying the plural images stored in the image storage section and the conversion image obtained by the image conversion section; a display section that sequentially displays the plural images and the conversion image in the order and the timings according to the schedule set by the schedule setting section; and a controller that controls the image conversion section to complete the conversion of the selected image before a display start timing of the conversion image, the display start timing set by the schedule setting section.

2 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