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
朴斗植, 白艾伦, 郑用柱, 郑英珠, 金智元 
17 Jun 2010
TL;DR: In this paper, an image conversion device and method converting a two-dimensional image into a three-dimensional (3D) image is presented, which may selectively adjust illumination within the 2D image, generate a disparity map for the illumination adjusted image, and selectively adjust a depth value of the disparity map based on edge discrimination.
Abstract: Disclosed is an image conversion device and method converting a two-dimensional (2D) image into a three-dimensional (3D) image. The image conversion device may selectively adjust illumination within the 2D image, generate a disparity map for the illumination adjusted image, and selectively adjust a depth value of the disparity map based on edge discrimination.
Patent
09 May 2013
TL;DR: In this article, a displacement measuring method capable of simultaneously measuring displacement of a plurality of evaluation points even in a measuring object in a red heat state was proposed, where image component determination was performed by dividing image data obtained by capturing images of the measuring object before and after read heat using a digital camera 2, into RGB components respectively.
Abstract: PROBLEM TO BE SOLVED: To provide a displacement measuring method capable of simultaneously measuring displacement of a plurality of evaluation points even in a measuring object in a red heat state.SOLUTION: Image component determination means 3b divides image data obtained by capturing images of a measuring object 1 before and after read heat using a digital camera 2, into RGB components respectively; and determines a component with the smallest change in a luminance value of the red heat area before and after the red heat. Image conversion means 3c converts the image data obtained by capturing the images of the measuring object 1 before and after deformation into image data of the component determined by the image component determination means 3b. Deformation computing means 3 performs pattern matching processing using the converted image data of the measuring object before and after the deformation and calculates the deformation.
Patent
31 Jul 2018
TL;DR: In this article, a character recognition method and device based on the principle of isomorphism, and terminal equipment is presented, which comprises the steps: obtaining a character image, and carrying out the preprocessing of the character image; converting a preprocessed character image into a structural map corresponding to the character images; removing a junction in a stacked-manner in the structural map, and carried out the merging of sides; converting the structural maps into a curve structural map after removing; extracting an isomorphic group which is isomorphic with a to-be-recognized curve
Abstract: The embodiment of the invention provides a character recognition method and device based on the principle of isomorphism, and terminal equipment. The method comprises the steps: obtaining a characterimage, and carrying out the preprocessing of the character image; converting a preprocessed character image into a structural map corresponding to the character image; removing a junction in a stackedmanner in the structural map, and carrying out the merging of sides; converting the structural map into a curve structural map after removing; extracting an isomorphism group which is isomorphic witha to-be-recognized curve structural map from the obtained training result set; obtaining a matched character group corresponding to the to-be-recognized curve structural map according to the extracted isomorphism group; selecting a matched character which has the minimum difference degree with the curve structural map from the obtained matched character group, and taking the matched character asa character represented by a to-be-processed character image. According to the character recognition scheme, the method achieves the recognition of the character image through the character image conversion, junction elimination, isomorphism detection and difference comparison, and improves the character recognition accuracy.
Patent
29 Mar 2006
TL;DR: In this paper, the size of excitation light d for reading the radiation image satisfies the expressions: d≧ 5 r and d≦ 3 p wherein r is the average column diameter of the columnar crystals in the phosphor layer of a radiation image conversion panel and p is the pixel size of the reproduced image.
Abstract: A phosphor layer of a radiation image conversion panel has a thickness of 100 to 300 μm and a relative density of 65 to 80%. When a radiation image taken on the conversion panel is reproduced, the size of excitation light d for reading the radiation image satisfies the expressions: d≧ 5 r and d≦ 3 p wherein r is the average column diameter of the columnar crystals in the phosphor layer of the radiation image conversion panel and p is the pixel size of the reproduced image. The radiation image conversion panel and a radiation image diagnostic system using such a conversion panel are suitable for an application such as mammography in which soft tissue is imaged as the principal subject with low radiation energy.
Patent
12 Jan 2017
TL;DR: In this article, the authors present a digital image conversion method and apparatus, which includes: acquiring an RGB indication signal of a forward-correlated pixel of a current pixel; comparing an RGB signal of the current pixel with the RGB indication signals of the forward correlated pixel; and assigning the YUV indication signal to a YUV signal.
Abstract: Embodiments of the present disclosure disclose a digital image conversion method and apparatus. The method includes: acquiring an RGB indication signal of a forward-correlated pixel of a current pixel; comparing an RGB signal of the current pixel with the RGB indication signal of the forward-correlated pixel; acquiring a YUV indication signal of the forward-correlated pixel and assigning the YUV indication signal to a YUV signal of the current pixel, if the RGB signal of the current pixel is identical to the RGB indication signal of the forward-correlated pixel; and recalculating the YUV signal of the current pixel according to the RGB signal of the current pixel, if the RGB signal of the current pixel is different from the RGB indication signal of the forward-correlated pixel. The digital image conversion method and apparatus disclosed in the embodiments of the present disclosure can effectively reduce the amount of calculation required for image data conversion.

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