Image conversion

About: Image conversion is a research topic. Over the lifetime, 2490 publications have been published within this topic receiving 19077 citations.

Image synthesis of monoenergetic CT image in dual-energy CT using kilovoltage CT with deep convolutional generative adversarial networks

Abstract: Purpose To synthesize a dual-energy computed tomography (DECT) image from an equivalent kilovoltage computed tomography (kV-CT) image using a deep convolutional adversarial network. Methods A total of 18,084 images of 28 patients are categorized into training and test datasets. Monoenergetic CT images at 40, 70, and 140 keV and equivalent kV-CT images at 120 kVp are reconstructed via DECT and are defined as the reference images. An image prediction framework is created to generate monoenergetic computed tomography (CT) images from kV-CT images. The accuracy of the images generated by the CNN model is determined by evaluating the mean absolute error (MAE), mean square error (MSE), relative root mean square error (RMSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mutual information between the synthesized and reference monochromatic CT images. Moreover, the pixel values between the synthetic and reference images are measured and compared using a manually drawn region of interest (ROI). Results The difference in the monoenergetic CT numbers of the ROIs between the synthetic and reference monoenergetic CT images is within the standard deviation values. The MAE, MSE, RMSE, and SSIM are the smallest for the image conversion of 120 kVp to 140 keV. The PSNR is the smallest and the MI is the largest for the synthetic 70 keV image. Conclusions The proposed model can act as a suitable alternative to the existing methods for the reconstruction of monoenergetic CT images in DECT from single-energy CT images.

Laplacian-guided image decolorization

Abstract: In this paper we introduce a novel decolorization strategy built on image fusion principles. Decolorization (color-to-grayscale), is an important transformation used in many monochrome image processing applications. We demonstrate that aside from color spatial distribution, local information plays an important role in maintaining the discriminability of the image conversion. Our strategy blends the three color channels R, G, B guided by two weight maps that filter the local transitions and measure the dominant values of the regions using the Laplacian information. In order to minimize artifacts introduced by the weight maps, our fusion approach is designed in a multi-scale fashion, using a Laplacian pyramid decomposition. Additionally, compared with most of the existing techniques our straightforward technique has the advantage to be computationally effective. We demonstrate that our technique is temporal coherent being suitable to decolorize videos. A comprehensive qualitative and also quantitative evaluation based on an objective visual descriptor demonstrates the utility of our decolorization technique.

Image conversion device

Abstract: An image conversion device connected to multiple image detection mechanisms generating field image data of the surroundings and having multiple input buffers for each of the multiple image detection mechanisms, which, in parallel, stores, moves, performs conversion processing and displays said field image data in 1 field units in accordance with a display template in pattern memory, thereby reducing the total delay time from field image generation to display to the driver.

Image converter and image conversion method

Abstract: PROBLEM TO BE SOLVED: To provide an image converter that applies special effects onto a natural image so as to allow the natural image to more effectively and quickly have a picture-like tone. SOLUTION: The image converter 10 is provided with a direction selection section 22, that selects a direction in which a pixel group forming a contour component among directions in which pixel groups including a prescribed pixel are arranged and with an averaging section 24, that averages pixel values of the pixel group arranged in the selected direction. The image converter 10 is also provided with a darkness degree emphasis section 28 that further lowers the pixel values of pixels, having low pixel values lower than those of the surrounding pixels in the image.

Image processing method, manipulation detection method, image processing device, manipulation detection device, image processing program, manipulation detection program, and image formation medium

Abstract: An image processing method for detecting alteration of data formed on an image formation medium on which a main data image and a copy detection latent image are formed. The method comprises a first image creation step of creating an image in a state identical to a state of an image which is obtained by scanning the image formation medium on which the main data image and the copy detection latent image are formed, a one-way value operation step of effecting a one-way value operation on the image created at the first image creation step to calculate a one-way value, an image conversion step of converting the one-way value into an image representing the one-way value, a second image creation step of creating an image by superimposing the image representing the one-way value, the main data image and the copy detection latent image.