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
Masaaki Nakayama1, Kenji Maeda1
16 Mar 2005
TL;DR: An imaging apparatus capable of performing image conversion such as white balance with a simple operation to obtain image data suited to user's preference, includes an imaging section, an image divider, a calculator, and an image converter as discussed by the authors.
Abstract: An imaging apparatus capable of performing image conversion such as white balance with a simple operation to obtain image data suited to user's preference, includes an imaging section, an image divider, a calculator, and an image converter. The imaging section images a subject to generate image data. The image divider divides a whole region of the generated image data into plural regions, and outputs first data including data in at least one of the divided regions and second data including data in at least one of other divided regions. The calculator calculates a first set value (for example, for correcting white balance of the image data) based on the first data, and a second set value based on the second data. The image converter generates first converted image data (for example, with corrected white balance) based on the first set value, and generates second converted image data based on the second set value.

1 citations

Patent
14 Aug 2020
TL;DR: Zhang et al. as mentioned in this paper proposed an image defogging method and system based on domain self-adaption, which belongs to the field of pattern recognition, where the domain deviation between asynthetic domain and real domain is effectively reduced through an image conversion module, and the generalization of an imagedefogging model in the real domain was improved.
Abstract: The invention discloses an image defogging method and system based on domain self-adaption, and belongs to the field of pattern recognition. According to the invention, the domain deviation between asynthetic domain and a real domain is effectively reduced through an image conversion module, and the generalization of an image defogging model in the real domain is improved. A real foggy day imageis fused into the training of the synthetic domain and real domain defogging models to be used for constraining the training of models, so that the generalization of the models is further improved, and the defogged image is clearer. The total loss function comprises dark channel prior loss, total variation loss and consistency loss. The dark channel prior loss emphasizes that most pixel values ofthe dark channel of the restored image are 0 or close to 0; the total variation loss hopes that pixels of the defogged image are smoothly distributed, and the consistency loss ensures that the outputresults of the two defogging models can be consistent, so that the defogged image is clearer and more obvious in detail by taking the minimization of the total loss function as a target.

1 citations

Patent
28 Apr 2005
TL;DR: In this paper, a recording and reproducing device capable of recording image and sound information on a recording medium with a progressive image of 24 frames per second, reproducing the image and the sound information is presented.
Abstract: PROBLEM TO BE SOLVED: To provide a recording and reproducing device capable of recording image and sound information on a recording medium with a progressive image of 24 frames per second, and reproducing the image and sound information. SOLUTION: An image is obtained from an input part 103 with a progressive image of 24 frames per second, an encoding/decoding part 104 performs encoding and compressing processing, and a drive 107 records the image and sound information on a recording medium 108. When the image and sound information is reproduced, an image-converting part 105 performs image conversion on an interlaced image of 60 frames per second, and the encoding/decoding part 104 performs decoding and decompression processings, subsequently reproducing image and sound information. COPYRIGHT: (C)2005,JPO&NCIPI

1 citations

Patent
25 Feb 2000
TL;DR: In this paper, the problem of outputting edition data of optimum resolution at each time without previously generating and storing image data of low resolution by extracting image data from image data for providing plural resolution levels by respective low resolution image extraction means and converting the low-resolution image data into output raster image data by an image conversion means.
Abstract: PROBLEM TO BE SOLVED: To make it possible to directly output image data of optimum resolution at each time without previously generating and storing image data of low resolution by extracting image data of low resolution from image data for providing plural resolution levels by respective low resolution image extraction means and converting the low resolution image data into output raster image data by an image conversion means. SOLUTION: In the case of outputting edition data, low resolution image extraction means 2a to 2c execute processing for extracting image data of proper low resolution from original image data and transfer the extracted low resolution image data to a print server computer 3 through a LAN 6. An image conversion means 4 converts the low resolution image data transferred from client computers 1a to 1c into output raster image data. The computer 3 outputs the output raster image data to a prescribed one of plural image output means 5a to 5c through an interface 7.

1 citations

Patent
16 Apr 2015
TL;DR: In this article, the authors proposed a medical image display device capable of displaying medical images in proper gradation without using color management by hardware even if performing improvement corresponding to gradation correction to an individual application having a display function of the medical image.
Abstract: PROBLEM TO BE SOLVED: To provide a medical image display device capable of displaying a medical image in proper gradation without using color management by hardware even if performing improvement corresponding to gradation correction to an individual application having a display function of the medical image.SOLUTION: A viewer part 38b accesses an image viewer Web server 14 by a user terminal 16 installed with a medical image display program 38 to acquire at least medical image data 13a, input data received in a touch input part 21a are transmitted in an input transmission part 31 and are transferred to the image viewer Web server 14, the medical image data 13a outputted from the image viewer Web server 14 are acquired in a capture acquisition part 34, at least a medical image data 13a portion is image-converted in an image conversion part 35, and displaying image data after the conversion are outputted toa display part 23 in an output part 36.

1 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