An approach is provided for color clustering for preprocessing an image. A cross-product on values of pixels in a source image and a number of bits per channel is determined, rounded to integer values, and left aligned to specify a target image. The following actions are repeatedly performed until a count of colors in the target image equals a target: a least frequent color in the target image is identified, distances between the least frequent color and other colors in the target image are determined, a least distance among the distances is determined, where the least distance is between the least frequent color and a closest color, a merged color is generated by merging the least frequent color and the closest color, and the count of the colors in the target image is reduced by replacing the least frequent color and the closest color with the merged color.

A method of obtaining a plurality of infrared images of a banknote that involves simultaneously illuminating the banknote with infrared light at a first wavelength and infrared light at a second wavelength, capturing an image of the banknote with an RGB camera, obtaining from both a first output channel signal and a second output channel signal of the RGB camera sensor where the intensity distribution of the infrared light at the first wavelength and the intensity distribution of the infrared light at the second wavelength uses a first calibration coefficient and a second calibration coefficient of the RGB camera sensor, producing separate infrared images of the banknote at the first wavelength and the second wavelength from the respective intensity distributions.

An imaging apparatus includes a storage portion that stores captured image data obtained by imaging a subject by an imaging element and is incorporated in the imaging element, an output portion that is incorporated in the imaging element, and a plurality of signal processing portions that are disposed outside the imaging element, in which the output portion includes a plurality of output lines each disposed in correspondence with each of the plurality of signal processing portions and outputs each of a plurality of pieces of image data into which the captured image data stored in the storage portion is divided, to a corresponding signal processing portion among the plurality of signal processing portions from the plurality of output lines, and any of the plurality of signal processing portions combines the plurality of pieces of image data.

Image processing apparatus and image processing method are provided. The image processing apparatus may include an image sensor having a plurality of photodetectors and include a 3D image calculating module. The image sensor may be configured to generate a first set of input information at a first time/first location and a second set of input information at a second time/second location, where the first set of input information may be associated with a first weighting value, and the second set of input information may be associated with a second weighting value. The 3D image calculating module may be configured to generate output information based on the first and the second sets of input information and the first and the second weighting values, wherein at least one of the plurality of photodetectors includes germanium.

An electronic device is described, that includes a processing logic configured to receive input image data and generate output image data having a different format from the input image data using an artificial neural network model. The artificial neural network model includes a plurality of encoding layer units, including a plurality of layers located at a plurality of levels, respectively. The artificial neural network model also includes a plurality of decoding layer units including a plurality of layers and configured to form skip connections with the plurality of encoding layer units at the same levels. A first encoding layer unit of a first level receives a first input feature map and outputs a first output feature map. A first output feature map is based on the first input feature map, to a subsequent encoding layer unit and a decoding layer unit at the first level.

A training apparatus is provided. The training apparatus acquires a mosaic image, generates a demosaic image by subjecting the mosaic image to a demosaicing process in which a neural network is used, and detects a low-image-quality portion in the demosaic image as a detected region. The training apparatus acquires a training image including a region having a hue similar to a hue of the detected region, and incrementally trains the neural network using the training image.

An image processing apparatus is disclosed. The image processing apparatus acquires a mosaic image. The image processing apparatus generates a first demosaic image by subjecting the mosaic image to a first demosaicing process in which a neural network is used, and generates a second demosaic image by subjecting the mosaic image to a second demosaicing process that is different from the first demosaicing process. The image processing apparatus generates a composite image in which the first demosaic image and the second demosaic image are combined.

Systems and techniques are described for image processing. An imaging system can include an image sensor that captures image data. An image signal processor (ISP) of the imaging system can demosaic the image data. The imaging system can input the image data into one or more trained machine learning models, in some cases along with metadata associated with the image data. The one or more trained machine learning models can output settings for a set of parameters of the ISP based on the image data and/or the metadata. The imaging system can generate an output image by processing the image data using the ISP, with the parameters of the ISP set according to the settings. Each pixel of the pixels of the image data can be processed using a respective setting for adjusting a corresponding parameter. The parameters of the ISP can include gain, offset, gamma, and Gaussian filtering.

A method for contrast-based autofocus of an image capture device. The method includes obtaining sensor data representative of an image captured by the image capture device, wherein the sensor data comprises pixel values from respective sensor pixels of an image sensor of the image capture device. A subset of the pixel values is dynamically selected to generate selected sensor data representative of the subset of the pixel values. The selected sensor data is processed to generate contrast data representative of a contrast-based characteristic of at least a portion of the image. The contrast data is processed to determine a focus setting for the image capture device.

An image processing device includes: an image sensor configured to generate first image data by using a color filter array; and processing circuitry configured to select a processing mode from a plurality of processing modes for the first image data, the selecting being based on information about the first image data; generate second image data by reconstructing the first image data using a neural network processor based on the processing mode; and generate third image data by post-processing the second image data apart from the neural network processor based on the processing mode.