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
Kazuteru Watanabe1, Kazunori Ozawa
07 Jan 2010
TL;DR: In this article, a decoding unit that decodes input encoded data into image data and a size conversion unit that converts size of the image data based on size conversion request received from outside and that expands/contracts, or splits/synthesizes motion vector or prediction mode of encoding parameters, received from the decoding unit, based upon a size converter request, and an encoding unit that encodes image data after size conversion using the prediction mode or motion vector converted and transmits the resulting encoded image data via a transmission buffer to outside.
Abstract: Disclosed is a conversion apparatus including a decoding unit that decodes input encoded data into image data, and a size conversion unit that converts size of the image data based on a size conversion request received from outside and that expands/contracts, or splits/synthesizes motion vector or prediction mode of encoding parameters, received from the decoding unit, based upon a size conversion request, and an encoding unit that encodes image data after size conversion using the prediction mode or motion vector converted and transmits the resulting encoded image data via a transmission buffer to outside.

2 citations

Patent
12 Aug 1997
TL;DR: In this article, a defect imaging device is used to accurately and automatically inspect a three-dimensional structure material without any manual work by stereo-imaging a defect with a camera.
Abstract: PROBLEM TO BE SOLVED: To accurately and automatically inspect without any manual work by stereo-imaging A defect with a camera. SOLUTION: A material defect 2 of a three-dimensional structure material 1 is stereo-imaged with a defect imaging device 3 provided with left and right cameras 6 and 7 and a camera 9 for recording photograph, and, through a cable 40, sent to an image recording device 4, and at this place, digital-converted with a image conversion part 16, and recorded in a record media 23. The record media 23 inputs to an image deciding device 5, and image-processed with a processing computer 25 for measuring three-dimensional form, and stared/ recorded in an image staring device 26 as an image file, and further, the image file is overwritten with the image for recording photograph, and outputted with a display and a printer as requirement.

2 citations

Patent
28 Dec 2015
TL;DR: In this paper, a method of processing an image in a diagnostic apparatus for diagnosing a lesion using a captured image of an affected area to be diagnosed, comprising the steps of: (i) classifying the captured image based on a stage of a progression of the lesion (step S13 and S14); and (ii) performing an image conversion processing, which corresponds to a classification obtained as a result of step (i), on the captured images to generate a converted image (Step S15-17).
Abstract: The invention provides a method of processing an image in a diagnostic apparatus 100 of diagnosing a lesion using a captured image of an affected area to be diagnosed, comprising the steps of: (i) classifying the captured image based on a stage of a progression of the lesion (Step S13 and S14); and (ii) performing an image conversion processing, which corresponds to a classification obtained as a result of step (i), on the captured image to generate a converted image (Step S15-17).

2 citations

Patent
27 Aug 2014
TL;DR: In this article, a system and method for identifying a finger print image of a sensor is described, which consists of a fingerprint image extractor, a feature point extraction module, a data storage module, and a fingerprint identification module.
Abstract: The invention discloses a system and method for identifying a finger print image of a sensor. The system comprises a finger print image extracting module, a feature point extraction module, a data storage module and a finger print identifying module. The feature point extraction module extracts a finger print image. The feature point extraction module judges whether a swirl print exists, and a feature point is extracted. The data storage module logs the feature point extracted by the data storage module in a data base. The finger print identification module is used in the identification state, after the input finger print image is subjected to feature point extraction, the distance of two input breakpoints is compared with the distance of two breakpoints in the data base, 2D image conversion of the input image and a template image is calculated, template image feature points obtained through calculation are converted into an input coordinate, the pixel difference of a template and input finger print feature points is calculated to obtain an error, and an error value is compared with a threshold to obtain an identification conclusion. The system and method for identifying the finger print image of a sensor solve the problem that finger print images input by different sensors are inconstant and greatly improve the finger print identification speed.

2 citations

Patent
Higashi Masafumi1, Aoki Reo1, Yoshida Yuya1
21 Sep 2017
TL;DR: In this article, an image conversion method that allows for the representation, on a display, the light and shade of a printed image obtained by printing the image on paper is presented.
Abstract: Provided is an image conversion method that allows for the representation, on a display, the light and shade of a printed image obtained by printing the image on paper The image conversion method includes a step of acquiring an illumination-light component and a reflectance component from an input image, a step of correcting the illumination-light component in accordance with display luminance information of a print mode in which the input image is to be printed, so that light and shade of the input image displayed on a display come close to light and shade of a printed image obtained by printing the input image in the print mode, and a step of acquiring a combined image by combining the corrected illumination-light component and the reflectance component or the corrected reflectance component

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