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 2018
TL;DR: In this paper, the authors proposed a captured image processing system which enables a user to easily recognize information related to oxygen deficit on a local biological tissue, by visualizing oxygen index distribution of a biological tissue including hemoglobin, so that the system materializes preferable color reproduction property in normal photographing.
Abstract: To provide a captured image processing system which enables a user to easily recognize information related to oxygen deficit on a local biological tissue, by visualizing oxygen index distribution of a biological tissue including hemoglobin, so that the system materializes preferable color reproduction property in normal photographing.SOLUTION: The captured image processing system comprises: an image processing apparatus 28 and a display unit 30 displaying a screen based on screen constitution information. The image processing apparatus 28 comprises: an illumination device 12 illuminating an object; an imaging apparatus 14 imaging the object; a color correction part 16 performing image correction; an image recording part 18 recording and reproducing the captured image; a color reproduction part 20 which makes the captured image have a prescribed color gamut, and generates a color reproduction image; an index image conversion part 22 generating an index image according to each pixel value; a color allocation part 24 which allocates any color to the pixel value of the index image, and generates the index display image; and a screen constitution part 26 generating screen constitution information. The prescribed color gamut is a color gamut of the display unit 30, and the imaging apparatus 14 outputs a Nch image (N is an integer equal to or larger than 3) of the object and linear combination of spectral sensitivity of each ch matches a color matching function.SELECTED DRAWING: Figure 1
Patent
11 Jan 2017
TL;DR: An energy saving electronic board and an energy saving method using a dual smart camera are disclosed in this paper, which consists of a smart camera for photographing an external image; a surrounding environment diagnosis unit for diagnosing a surrounding environments by analyzing the image transferred from the smart camera with a pre-stored reference image; an image conversion unit for converting an original image into an output image according to the diagnosed surrounding environment; and an electronic board controller for controlling an output of an electronic boards by receiving the image converted into the output image.
Abstract: An energy saving electronic board and an energy saving method using a dual smart camera are disclosed The energy saving electronic board comprises: a smart camera for photographing an external image; a surrounding environment diagnosis unit for diagnosing a surrounding environment by analyzing the image transferred from the smart camera with a pre-stored reference image; an image conversion unit for converting an original image into an output image according to the diagnosed surrounding environment; and an electronic board controller for controlling an output of an electronic board by receiving the image converted into the output image
Patent
22 Aug 2019
TL;DR: An image conversion unit according to an embodiment includes a gradation unit, a black line extraction unit, and a white line extraction units as discussed by the authors. But the gradient unit is not used in this paper.
Abstract: An image conversion unit according to an embodiment includes a gradation unit, a black line extraction unit, and a white line extraction unit. The gradation unit classifies a pixel of a pre-conversion image as one of four levels based on a brightness of the pixel, and expresses, in a color corresponding to the level as which the pixel has been classified, a corresponding pixel of a converted image. The black line extraction unit extracts pixels of an outline of an object in the pre-conversion image, and expresses corresponding pixels of the converted image in black. The white line extraction unit extracts pixels adjacent to an outline of an object in the pre-conversion image, and expresses corresponding pixels of the converted image in white.
Patent
01 Nov 2012
TL;DR: In this article, a living body authentication system for confirming an individual using living body information related to the vein of a finger of a human was proposed, which includes an imaging means for acquiring image information including the image information acquired from an authentication object; an image conversion means for converting the image image information to a polygonal line vector image and a binary bitmap image by executing polygonally line vectorization processing and bitmap processing to the acquired image information; and a determination means for determining whether the image is the information is the image acquired from the living body or the image
Abstract: PROBLEM TO BE SOLVED: To detect a pattern of a pseudo finger other than a living body by specifying whether or not a pattern of something other than the living body is included from a vein pattern of an imaged finger without using anything other than an imaging apparatus.SOLUTION: A living body authentication system for confirming an individual using living body information related to the vein of a finger of a human includes: an imaging means for acquiring image information including the living body information from an authentication object; an image conversion means for converting the image information to a polygonal line vector image and a binary bitmap image by executing polygonal line vectorization processing and binary bitmap processing to the acquired image information; and a determination means for determining whether the image information is the image information acquired from the living body or the image acquired from a pseudo finger on the basis of the polygonal line vector image and the binary bitmap image.
Patent
07 Jan 2020
TL;DR: In this paper, the face area is cut from the to-be-recognized face sketch to reduce the interference of the background area on face recognition, and meanwhile, the preset image conversion model is adopted to perform image conversion to convert heterogeneous face recognition into homogenous face recognition.
Abstract: The invention provides an image conversion model training method and device, a heterogeneous face recognition method and device and equipment, and the method comprises the steps: obtaining a to-be-recognized face sketch, and cutting the to-be-recognized face sketch to obtain a face region sketch; inputting the face region sketch into a pre-trained image conversion model for processing to generatea second face synthesis image; performing feature extraction on the second face synthesis image to obtain a feature vector of the second face synthesis image; and matching the feature vector of the second face synthesis image with feature vectors of a plurality of real face images stored in a database to obtain a face recognition result. Therefore, the face area is cut from the to-be-recognized face sketch to reduce the interference of the background area on face recognition, and meanwhile, the preset image conversion model is adopted to perform image conversion to convert heterogeneous face recognition into homogeneous face recognition, so that the accuracy of heterogeneous face recognition is improved.

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