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 published on a yearly basis
Papers
More filters
Patent•
12 Jul 2019
TL;DR: In this paper, an image conversion method based on the cyclic generative adversarial network (GAN) was proposed to solve the technical problems in the prior art that GAN often cannot focus on local features and has stripe-shaped noise in the image local feature migration process, and the overall color of a picture is easily changed.
Abstract: The invention discloses an image conversion processing method in the technical field of image processing. The image processing method aims to solve the technical problems in the prior art that an image processing method based on the cyclic generative adversarial network often cannot focus on local features and has stripe-shaped noise in the image local feature migration process, and the overall color of a picture is easily changed. The method comprises the following steps: acquiring a real image containing processing characteristics and a real image not containing the processing characteristics, and constructing a training sample; inputting a training sample into the cyclic generative adversarial network, and training the cyclic generative adversarial network by taking a pre-constructed loss function minimization as a target, the loss function comprising a total variation regularization loss function; and processing the to-be-processed image by adopting the trained cyclic generative adversarial network.
3 citations
Patent•
18 Feb 1998
TL;DR: In this paper, a lower-order digit data segmentation circuit was proposed to eliminate a conversion error in image data at a desired specific point by segmenting the image data into desired specific image data C 0, M, Y from which the density data C, M and Y were then converted into dot % data based on the image conversion table.
Abstract: PROBLEM TO BE SOLVED: To provide a method and a system to convert input image data into output image data with high accuracy according to a prescribed image processing condition, eliminating a conversion error in image data at a desired specific point. SOLUTION: A lower-order digit data segmentation circuit 22 segments lower- order digit data C 0 LSB, M 0 LSB, Y 0 LSB of desired specific image data C 0 , M 0 , Y 0 and the data C 0 LSB, M 0 LSB, Y 0 LSB are respectively subtracted from optional density data C, M, Y and each difference is fed to an image processing circuit 14. An image conversion table based on the specific image data C 0 , M 0 , Y 0 is set to the image processing circuit 14, the density data C, M, Y from which the lower-order digit data C 0 LSB, M 0 LSB, Y 0 LSB are subtracted area converted into dot % data C, M, Y, K based on the image conversion table. The dot % data C, M, Y, K obtained by conversion processing are interpolated further by an interpolation processing circuit 16. COPYRIGHT: (C)1999,JPO
3 citations
Patent•
01 Feb 2017
TL;DR: In this article, a method and device for constructing a classification model is presented, which consists of obtaining sample images respectively corresponding to a first image category and a second image category, and obtaining spectrograms corresponding to the sample images, wherein the spectrogram are obtained through image conversion of the sample image according to the bases with different sizes.
Abstract: The present invention provides a method and device for constructing a classification model. The method comprise: obtaining sample images respectively corresponding to a first image category and a second image category, and obtaining spectrograms corresponding to the sample images, wherein the spectrograms are obtained through image conversion of the sample images according to the bases with different sizes; determining the features respectively corresponding to the sample images according to the spectrograms, and constructing the sample image set according to the features respectively corresponding to the sample images and the sample images; and performing training of the sample images, and obtaining a classification model, wherein the classification model is configured to determine the image category corresponding to the images to be classified. According to the scheme, the spectrograms are obtained through image conversion of the sample images according to the bases with different sizes, and the features respectively corresponding to the sample images are obtained according to the spectrograms to construct the classification model so as to accurately detect the image category.
3 citations
Patent•
30 Mar 2016
TL;DR: In this article, a connection equipment and method for portable Wi-Fi wireless devices, where a portable wireless device can be simply and easily accessed to a wireless network and an internet-surfing approach is provided for mobile terminal devices.
Abstract: The invention provides connection equipment and method for portable Wi-Fi wireless devices, wherein a portable Wi-Fi wireless device can be simply and easily accessed to a wireless network and an internet-surfing approach is provided for mobile terminal devices. The connection equipment for portable Wi-Fi wireless devices is characterized by comprising a camera unit for shooting and acquiring a two-dimensional code image; a two-dimensional code image conversion unit for extracting the two-dimensional code image and converting the image into the information in the character format; and a Wi-Fi connection unit used for connecting the above information in the character format with the wireless network, wherein the information is set as network parameters.
3 citations
Patent•
20 May 2009
TL;DR: In this article, a camera and an image conversion device are used to obtain and display the rectified image, so as to enable the surveillant to make a correct judgment.
Abstract: The utility model discloses a camera and an image conversion device. The camera comprises a lens used for shooting video image information; the utility model also comprises an image collection module, an image rectification module and a rectification assignment module; wherein, the image collection module is connected with the lens and used for receiving image shot by the lens and analyzing the data information of the image; the image rectification module is connected with the image collection module and used for receiving the data information and calculating the conversion value of the image; the rectification assignment module is connected with the image rectification module and used for receiving the conversion value and processing rectification assignment towards the image and obtaining the rectified image. The image conversion device rectifies the distorted image to obtain and display the rectified image, so as to enable the surveillant to make correct judgment.
3 citations