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 Jan 2013
TL;DR: In this article, an image management apparatus is provided, in which an image conversion section is configured to generate a setup image, in setup image format, within a first image pyramid structure for display.
Abstract: There is provided an image management apparatus, in which an image conversion section is configured to generate a setup image, in a setup image format, within a first image pyramid structure for display, the setup image being converted from an object image, in an object image format, included within a second image pyramid structure in response to a request for the setup image.

2 citations

Patent
20 Dec 2002
TL;DR: In this article, a method for converting an image contrast pattern comprising many parallel lines includes a many parallel line management step, an image conversion step of applying image conversion to an image required to enhance the image quality of an output image on the many-parallel line parameter, and a many line pixel output step of generating the output pixel data from the manypar line parameter.
Abstract: PROBLEM TO BE SOLVED: To solve a problem that in a conventional method for converting an image contrast pattern comprising many parallel lines, the image quality is deteriorated due to moire or the like caused by incompatibility among a spatial frequency characteristic of an image scanner and an image printer, a spatial frequency characteristic of an image contrast pattern comprising many parallel lines and a spatial frequency characteristic of an image itself when the scanner captures an original including an image comprising many parallel lines and the printer prints out the received image. SOLUTION: The method for converting an image contrast pattern comprising many parallel lines includes a many parallel line management step of analyzing input pixel data to recognize many parallel lines in an image and managing the many parallel lines as a many parallel line parameter, an image conversion step of applying image conversion to an image required to enhance the image quality of an output image on the many parallel line parameter and a many line pixel output step of generating the output pixel data from the many parallel line parameter. Since this method can provide output pixel data suitable for a characteristic of the many parallel line image and a characteristic of an image output device, an image subjected to proper image conversion only to the many parallel line image can be outputted.

2 citations

Patent
14 Aug 2013
TL;DR: In this paper, the authors presented a method and an intelligent terminal for adaptively displaying images, which includes enabling power-saving business logics to detect the type of an image program which currently occupies the display screen; detecting the image movement corresponding to the image program and computing an image conversion region corresponding to image program.
Abstract: An embodiment of the invention provides a method and an intelligent terminal for adaptively displaying images. The method is applied to the intelligent terminal. The intelligent terminal comprises a display screen. The method includes enabling power-saving business logics to detect the type of an image program which currently occupies the display screen; detecting the type of movement of an image corresponding to the image program and computing an image conversion region corresponding to the image program; computing an invert color conversion gain according to the image conversion region; and performing invert color conversion for the image, which is positioned in a frame buffer, of the image program when the invert color conversion gain is higher than an invert color gain threshold value. The method and the intelligent terminal have the advantages that the image conversion region required by the image in the image program is found, the current invert color conversion gain of the image program is computed in the image conversion region, and as functions required for displaying different colors of the images are different, the power consumption for displaying the image again after the image is subjected to invert color conversion is reduced if the invert color conversion gain is higher than the invert color gain threshold value.

2 citations

Patent
09 Jan 2018
TL;DR: Zhang et al. as discussed by the authors provided a photovoltaic cell edge breakage and blunt and V-shaped notch detection algorithm, which is characterized by carrying out image correction and image conversion pretreatment one-ach collected frame image to obtain a target image of a PV-cell; carrying out gray top-hat transform to obtain an image of the photovortex cell only comprising a grid line portion, carrying out threshold segmentation, and filling the grid line portions, so that influence of the internal portion of grid lines on defect detection can be eliminated; obtaining a foreground image
Abstract: The invention provides a photovoltaic cell edge breakage and blunt and V-shaped notch detection algorithm, which is characterized by carrying out image correction and image conversion pretreatment oneach collected frame image to obtain a target image of a photovoltaic cell; carrying out gray top hat transform to obtain an image of the photovoltaic cell only comprising a grid line portion; carrying out threshold segmentation, and filling the grid line portion, so that influence of the internal portion of grid lines on defect detection can be eliminated; obtaining a foreground image only comprising the grid line portion, and carrying out threshold segmentation to obtain a background image; carrying out morphological close operation processing and filling the edge breakage and blunt and V-shaped notch portion; and comparing difference between the background image obtained after morphological processing and the unprocessed background image, so that detection of the edge breakage and bluntand V-shaped notch can be realized. The algorithm overcomes the defect of manual detection, can effectively improve accuracy of defect detection of the photovoltaic cell and has a huge application value for the photovoltaic industry.

2 citations

Patent
04 Sep 2018
TL;DR: In this article, an image collection system consisting of a fixed plate and multiple cameras arranged on the fixed plate is presented. And the camera model is based on a pre-calibrated camera model to obtain undistorted images at all the moments after the conversion.
Abstract: Embodiments of the invention provide an image collection system and method. The image collection system comprises an image collection device and a computer device which are in communication connectionwith each other. The image collection device comprises a fixed plate and multiple cameras arranged on the fixed plate; and the cameras continuously collect images of a target object in a predetermined moving direction and send the images collected at the same moment to the computer device. The computer device performs image conversion on pixel coordinates of the images at all the moments by the cameras based on a pre-calibrated camera model to obtain undistorted images at all the moments after the conversion, performs image splicing on the undistorted images at all the moments to generate first spliced images at all the moments, and performs image splicing on the first spliced images at all the moments to generate a spliced image of the target object. Therefore, complete image collectionin a narrow and small space is realized; and the collected images are high in resolution and high in robustness.

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