An image colorizing method and device are provided, which relate to the field of image processing technology. The method includes acquiring a grayscale image to be colorized, classifying the grayscale image to determine the grayscale image is a human face image or a human image, providing the grayscale image to a neural network based image colorizing model corresponding to the type of the grayscale image to obtain color information for respective pixels in the grayscale image. The image colorizing model is a human face image colorizing model if the grayscale image is a human face image, the image colorizing model is a human image colorizing model if the grayscale image is a human image. The method further includes synthesizing the grayscale image and the color information to obtain a color image.

A method of visualization, characterization, and detection of objects within an image by applying a local micro-contrast convergence algorithm to a first image to produce a second image that is different from the first image, wherein all like objects converge into similar patterns or colors in the second image.

A method of displaying an image on a see-through display comprises: obtaining a first electro-magnetic radiation matrix of radiation intensity values of an object; dividing the first matrix into a second matrix representing a first subset of the radiation intensity values, and a third matrix representing a second subset of the radiation intensity values; generating a first grayscale image with an enhanced contrast representing the first subset of the radiation intensity values from the second matrix; colouring the first grayscale image with a first colourmap to obtain a first colour image; generating a second grayscale image representing the second subset of the radiation intensity values; colouring the second grayscale image with a second colourmap to obtain a second colour image; combining the first colour image and the second colour image; and displaying the combined colour image on the see-through display.

An image colorizing method and device are provided, which relate to the field of image processing technology. The method includes acquiring a grayscale image to be colorized, classifying the grayscale image to determine the grayscale image is a human face image or a human image, providing the grayscale image to a neural network based image colorizing model corresponding to the type of the grayscale image to obtain color information for respective pixels in the grayscale image. The image colorizing model is a human face image colorizing model if the grayscale image is a human face image, the image colorizing model is a human image colorizing model if the grayscale image is a human image. The method further includes synthesizing the grayscale image and the color information to obtain a color image.

An information processing apparatus sets a color mode in place of a monochrome mode on condition that the monochrome mode and multiplexing of additional information on a print target image are set as print settings based on an input image data; generates, based on the input image data, color image data corresponding to printing in a color mode which represents a color of the monochromated print target image by a value of a color signal; performs, for the color image data generated by the generation unit, processing for multiplexing the additional information on the print target image; and causes a printing apparatus to print, in the color mode, a multiplexed image on which the additional information is multiplexed.

Methods and systems for training and utilizing an artificial neural network (ANN) are provided. In an example method, a computing device could receive an input image comprising a plurality of channels and determine a saliency map for the input image. The computing device could also establish at least one of the plurality of channels as a training channel and at least some of the plurality of channels as one or more ground truth channels. Further, the computing device could train an ANN to predict one or more output channels from the one or more training channels, where the training involves computationally updating weights of the ANN based on a loss function that comprises a difference between the one or more output channels and the one or more ground truth channels, and where the difference is computationally biased based on values from the saliency map.

A medical device includes a sensor, a processor, and non-transitory computer readable medium storing imaging instructions. The sensor captures a first raw image into a first frame of raw pixel values including a plurality of first pixel values that represent pixels of a first color and a plurality of second pixel values that represent pixels of a second color. The sensor captures a second raw image into a second frame of raw pixel values including a plurality of third pixel values that represent pixels of the second color and a plurality of fourth pixel values that represent pixels of a third color. The processor convolves the first frame of raw pixel values with the second frame of raw pixel values to generate a first extrapolated frame of pixel values in a YCrCb format and creates a processed image from the first extrapolated frame of pixel values.

Methods and systems for training and utilizing an artificial neural network (ANN) are provided. In an example method, a computing device could receive an input image comprising a plurality of channels and determine a saliency map for the input image. The computing device could also establish at least one of the plurality of channels as a training channel and at least some of the plurality of channels as one or more ground truth channels. Further, the computing device could train an ANN to predict one or more output channels from the one or more training channels, where the training involves computationally updating weights of the ANN based on a loss function that comprises a difference between the one or more output channels and the one or more ground truth channels, and where the difference is computationally biased based on values from the saliency map.

Provided are embodiments for a method for performing colorization of scans. The method includes analyzing a scanner, a scan of an environment to identify one or more patterns within the scan, and obtaining a subset of colorization data of the environment. The method also includes predicting colors for the one or more patterns in the scan based on the subset of colorization data, and assigning the predicted colors to the one or more patterns in the scan to generate a colorized scan. The method includes displaying the colorized scan, wherein the colorized scan combines the scan and the predicted colorization data by assigning the predicted colorization data to the one or more patterns in the scan. Also provided are embodiments for a system for performing the colorization of scans.

In an image data conversion device, color image data is represented in gray scale, a histogram of brightness values is created for the gray-scaled image data, it is determined based on the created histogram which image pattern of a plurality of image patterns the gray-scaled image data is classified into, a range subjected to gamma correction and a range fixed to at least one of a minimum value and a maximum value of gray scale are set for each image pattern, and image data conversion including the gamma correction is performed on the gray-scaled image data.