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
20 Dec 2002
TL;DR: In this paper, a linear stimulating light is projected by a stimulating light irradiation part 20 and travels in a horizontal scanning direction X is made incident on a surface of the radiation image conversion panel 10 at an incidence angle α of > 0° and
Abstract: PROBLEM TO BE SOLVED: To suppress an image signal, obtained by detecting stimulated luminescence generated by a radiation image conversion panel by irradiation with stimulating light, from decreasing in quality. SOLUTION: Linear stimulating light Le which is projected by a stimulating light irradiation part 20 and travels in a horizontal scanning direction X is made incident on a surface of the radiation image conversion panel 10 at an incidence angle α of >0° and COPYRIGHT: (C)2004,JPO&NCIPI

2 citations

Patent
29 Jan 2019
TL;DR: In this paper, an artificial intelligence-based conversion method and device for medical images of different modes and a storage medium is proposed. But the method is limited to the medical domain and cannot be applied to other medical applications.
Abstract: The invention belongs to the technical field of medical images, and relates to an artificial intelligence based conversion method and device for medical images of different modes and a storage medium.The method comprises the following steps: preparing a training data set; training neural network model; the first mode medical image after preprocessing is input into the trained depth convolution neural network model for forward computation and the second mode medical image is outputted. Through the conversion method of different modal medical images based on the neural network provided by the invention, images from the same imaging equipment and the same patient are adopted, so that the efficiency of depth learning is improved; in the process of preparing the training data set, three-dimensional reconstruction, registration and segmentation are used to ensure that the corresponding images of the first modal image and the second modal image are highly matched. In addition, the inventiondivides the training image into a plurality of image blocks, which reduces the requirement of the hardware device for the whole input training picture.

2 citations

Patent
16 Jul 1996
TL;DR: In this paper, an image consisting of 60 fields is converted into a progressive image of 24 frames and compressed by an image conversion means 11 before encoding, the resulting image is coded by an MPEG 2 encode means 12 and stored in a recording storage means 13.
Abstract: PURPOSE: To provide an image processor in which a compression rate is much more improved than that of conventional image data compression. CONSTITUTION: An original image A comprising 60 fields is converted into a progressive image of 24 frames and compressed by an image conversion means 11 before encoding, the resulting image is coded and compressed by an MPEG 2 encode means 12 and stored in a recording storage means 13. Image data sent through a transmission line 14 and compressed by the means 12 and obtained from the recording storage means 13 are restored to the original data by a reproduction means 15, decoded by an MPEG 2 decode means 16 to obtain the decoded image B of 60 fields from the progressive image of 24 frames.

2 citations

Patent
21 Nov 2012
TL;DR: An image processing device includes a display unit which displays images, an area designation unit which receives a target image area and an input image area both designated from the images, a tone function computing unit which computes a one-dimensional tone function of the target image and a 1D tone functions of the input image areas, a conversion information generating unit which generates conversion information to convert the one dimensional tone functions from the input images into the 1D tones from the target images, and a display control unit that displays the image containing the converted image data on the display unit.
Abstract: An image processing device includes a display unit which displays images, an area designation unit which receives a target image area and an input image area both designated from the images, a tone function computing unit which computes a one-dimensional tone function of the target image area and a one-dimensional tone function of the input image area, a conversion information generating unit which generates conversion information to convert the one-dimensional tone function of the input image area into the one-dimensional tone function of the target image area, an image conversion processing unit which converts image data of the input image area based on the conversion information, and a display control unit which displays the image containing the converted image data of the input image area on the display unit.

2 citations

Patent
21 Jul 1999
TL;DR: In this article, an image conversion processor detects distance data up to an original Sf corresponding to each pixel of a CCD and is used to correct the distortion of an original image which results when an image input device reads a bent document.
Abstract: PROBLEM TO BE SOLVED: To correct the distortion of an original image which results when an image input device reads a bent document. SOLUTION: This image conversion processor detects distance data up to an original Sf corresponding to each pixel of a CCD. Image data of the original Sf is detected from the pixels of line segments P0 and P9 on a light receiving plane. The bent original Sf is expanded linearly on the basis of distance data D1 to the original Sf corresponding to a pixel P1 (line segments Q0' and Q9'). Pixels (pixels on line segments P0' and P9') corresponding to the expanded original Sf (line segments Q0' and Q9') are calculated. The image data detected on the line segments P0 and P9 are made to correspond to pixels on the line segments P0' and P9' and are subjected to image change processing.

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