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
Oh-Yun Kwon1, Heo Hye-Hyun1
23 Apr 2012
TL;DR: In this paper, a 3D-image conversion apparatus, a method of adjusting depth information of the same, and a storage method thereof are provided, which includes a depth information generator which generates depth information with regard to an input image; an object detector which detects an object having parallax exceeding a preset range in a left-eye image and a right-eye images corresponding to the input image based on the generated depth information; a depth-information adjuster which adjusts depth information, which adjusts the detected object to be within a preset-range.
Abstract: A 3D-image conversion apparatus, a method of adjusting depth information of the same, and a storage method thereof are provided. The three-dimensional (3D) image conversion apparatus includes a depth information generator which generates depth information with regard to an input image; an object detector which detects an object having parallax exceeding a preset range in a left-eye image and a right-eye image corresponding to the input image based on the generated depth information; a depth information adjuster which adjusts depth information of the object by adjusting the parallax of the detected object to be within a preset range; and a rendering unit which renders the input image according to the adjusted depth information. With this, a viewer's fatigue can be minimized in the case of converting a 2D image into a 3D image.

3 citations

Patent
08 Mar 2017
TL;DR: In this article, a method for detecting a parking space according to the present invention comprises: a photographing step of photographing the parking space into a YCbCr image, a transformation matrix production step of producing a transformation matrices to make a brightness difference between the ground and a parking line be the maximum in the parking spaces by applying linear discriminant analysis (LDA), an image conversion step of transforming the YCBCr image to a first gray scale image using the transformation matrix, and an image line detection step of detecting the parking line using the brightness difference in the
Abstract: A method for detecting a parking space according to the present invention comprises: a photographing step of photographing a parking space into a YCbCr image; a transformation matrix production step of producing a transformation matrix to make a brightness difference between the ground and a parking line be the maximum in the parking space by applying linear discriminant analysis (LDA) to the YCbCr image; an image conversion step of transforming the YCbCr image to a first gray scale image using the transformation matrix; and a parking line detection step of detecting the parking line using the brightness difference between the ground and the parking line in the parking space of the first gray scale image; an apparatus for detecting a parking space according to the present invention comprises: a photographing unit configured to photograph a parking space into a YCbCr image; a transformation matrix production unit configured to produce a transformation matrix which makes a brightness difference between the ground and a parking line in the parking space by applying LDA to the YCbCr image; an image conversion unit configured to convert the YCbCr image to a first gray scale image using the transformation matrix; and a parking line detection unit configured to detect the parking line using the brightness difference between the ground and the parking line in the parking space of the first gray scale image.

3 citations

Patent
23 Aug 2002
TL;DR: In this paper, a home page registration renewing method was proposed to reduce the burden for an information transmitter to renew a homepage quickly and attract high attention with respect to the renewal.
Abstract: PROBLEM TO BE SOLVED: To provide a home page registration renewing method capable of reducing a burden for an information transmitter to renew a home page quickly, and capable of attracting high attention with respect to the renewal. SOLUTION: In this home page registration renewing method, a mail server 34 receives an electronic mail or a facsimile attached with an image data from a user, and a database server 42 specifys the user based on a transmitter phone number of the facsimile or the electronic mail. An image conversion server 38 converts the image data or the facsimile into an image data adaptable to an image area of the home page of the user to be output to an image server 46. The image data is stored in the image server 46 as the image data linked to the image area in the home page of the user. A mail preparing server 40 prepares the electronic mail for notifying the renewal of the home page to be addressed to an electronic mail address assigned preliminarily by the user.

3 citations

Patent
05 Sep 2016
TL;DR: In this paper, an image processing system was proposed to generate an image for area specification suitable for specifying an area of interest in a fluorescent dyed sample based upon an image of the sample.
Abstract: PROBLEM TO BE SOLVED: To provide a technique for generating an area specifying image suitable for specifying an area of interest in a fluorescent dyed sample based upon an image of the sample.SOLUTION: There is provided an image processing system which generates an image for area specification suitable for specifying an area of interest in a fluorescent dyed sample. The image processing system comprises: fluorescent image conversion means for generating an alternative color fluorescent image by applying a first alternative color to a fluorescent image of the fluorescent dyed sample thereby to represent luminance information of the fluorescent image with the first alternative color; phase image conversion means for generating an alternative color phase image by applying a second alternative color different from the first alternative color to a phase image of the fluorescent dyed sample thereby to represent luminance information of the phase image with the second alternative color; and image generation means for generating an image for area specification by synthesizing the alternative color fluorescent image and the alternative color phase image.SELECTED DRAWING: Figure 5

3 citations

Patent
09 Mar 2018
TL;DR: In this paper, an image obtaining unit for obtaining a thermal image of an object, an image conversion unit for converting the thermal image into a binarized image, a distance-transformed image generation unit for generating a distance transformed image by applying distance transformation based on the binarised image, and a marker generation unit assigning a marker to each of the objects based on a distance transformed image; an image segmentation unit for performing watershed segmentation in cope with each object around the marker assigned to the object.
Abstract: The present invention relates to a device for tracking an object based on a thermal image, comprising: an image obtaining unit for obtaining a thermal image of an object; a binarized image conversion unit for converting the thermal image into a binarized image; a distance-transformed image generation unit for generating a distance-transformed image by applying distance transformation based on the binarized image; a marker generation unit for assigning a marker to each of the objects based on the distance-transformed image; an image segmentation unit for performing watershed segmentation in cope with each of the objects around the marker assigned to the object; and an object recognition unit for recognizing the object based on a result of the watershed segmentation, wherein the marker generation unit can update location of the marker corresponding to the object included in the thermal image to be updated, and can update the location of each of the objects by applying the watershed segmentation method around the updated marker.

3 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