An image processing method and apparatus based on machine learning are disclosed. The image processing method based on machine learning, according to the present invention, may comprise the steps of: generating a first corrected image by inputting an input image to a first convolution neural network; generating an intermediate image on the basis of the input image; performing machine learning on a first loss function of the first convolution neural network on the basis of the first corrected image and the intermediate image; and performing machine learning on a second loss function of the first convolution neural network on the basis of the first corrected image and a natural image.

Exemplary embodiments of the present disclosure are directed towards a system and method for automatic enhancement of videos, comprising a computing device configured to establish communication with server over network; a video creating module configured to enable a user to record video segments or upload a pre-recorded video segments or photos, the video creating module configured to allow the user to select an option processing template, the video creating module configured to transfer the user recorded video segments to server over network, server comprises automated video enhancement module configured to perform an audio analysis, a video analysis on the user recorded video segments, automated video enhancement module configured to detect contexts of the user recorded video segments on the computing device and applying templates to the user recorded video segments based on the results of the audio analysis, the video analysis, the contexts of the user recorded video segments.

This disclosure provides methods, devices, and systems for low-light imaging. In some implementations, an image processor may be configured to reduce or remove noise associated with an image based, at least in part, on a neural network. For example, the neural network may be trained to infer a denoised representation of the image. In some aspects, the image processor may scale the brightness level of the image to fall within a normalized range of values associated with the neural network. In some other aspects, a machine learning system may scale the brightness levels of input images to match the brightness levels of ground truth images used to train the neural network. Still further, in some aspects, the machine learning system may scale the brightness levels of the input images and the brightness levels of the ground truth images to fall within the normalized range of values during training.

A device includes an encoder, decoder, codec or combination thereof and inline hardware conversion units that are operative to convert stored image data into one of: an HDR/WCG format and an SDR/SCG format during the conversion process. Each of the inline hardware conversion units is operative to perform the conversion process independent of another read operation with the memory that stores the image data to be converted. In one example, an encoding unit is operative to perform a write operation with a memory to store the converted image data after completing the conversion process. In another example, a decoding unit is operative to perform a read operation with the memory to retrieve the image data from the memory before initiating the conversion process. In another example, an encoder/decoder unit is operative to perform at least one of: the read operation and the write operation.

An image processing apparatus including at least one processor coupled to a memory, serving as a first obtainment unit to obtain a luminance value of image data corresponding to a first luminance range, a second obtainment unit to obtain information for a second luminance range that is less than the first luminance range, a classification unit to classify, based on a correspondence relationship of luminance value conversion from the first luminance range to the second luminance range, the first luminance range of the image data into a plurality of regions, and a display unit to cause a display device to display an image based on the image data such that a pixel of the image having a luminance value belonging to a region, in which a tone characteristic in the image data can be restored when the luminance value conversion is performed, can be specified in the displayed image.

Examples relate to an optical system and to a corresponding apparatus, method and computer program. The optical system comprises a display module for providing a visual overlay to be overlaid over an object in an augmented reality or mixed reality environment. The optical system comprises at least one sensor for sensing at least one optical property of the object. The optical system comprises a processing module configured to determine the at least one optical property of the object using the at least one sensor. The processing module is configured to determine a visual contrast between the visual overlay to be overlaid over the object and the object, as perceived within a field of view of the augmented reality or mixed reality environment, based on the at least one optical property of the object. The processing module is configured to selectively adjust an illumination of one of more portions of the field of view, or an optical attenuation of the one of more portions of the field of view, based on the determined visual contrast between the visual overlay to be overlaid over the object and the object.

One embodiment of an apparatus includes a reference position receiving unit configured to receive intermediate or end panorama reference position information input by a user, and a control unit configured to control an imaging device to begin generating a plurality of images to be used to generate a panoramic image based on the intermediate or end panorama reference position information input by the user after the reference position receiving unit receives the intermediate or end panorama reference position information.

A method for transforming high dynamic range (HDR) video data into standard dynamic range (SDR) video data and encoding the SDR video data so that the HDR video data may be recovered at the decoder includes generating a tone map describing a transformation applied to the HDR video data to generate the SDR video data. The generated tone map describes the transformation as the multiplication of each HDR pixel in the HDR video data by a scalar to generate the SDR video data. The tone map is then modeled as a reshaping transfer function and the HDR video data is processed by the reshaping transfer function to generate the SDR video data. The reshaping transfer function is then inverted and described in a self-referential metadata structure. The SDR video data is then encoded including the metadata structure defining the inverse reshaping transfer function.

An image processor performs a histogram acquisition step of acquiring a histogram representing a distribution of gradation values of pixels in a fundus color image captured by irradiating a fundus with a plurality of beams of single-color light having different wavelengths, the histogram being acquired for each channel corresponding to each beam of single-color light, a histogram correction step of acquiring a corrected histogram by correcting the histogram of each channel acquired in the histogram acquisition step, of which a target pattern is set for each channel in advance, so as to fit to the corresponding target pattern, and a color tone corrected image generation step of generating a color tone corrected image, in which a distribution of gradation values for each channel is represented by the corrected histogram, based on the corrected histogram of each channel.

An image processing method is performed by a processor. The image processing method includes following operations: generating an average brightness value of each of a plurality windows in image data; generating a pixel ratio value according to the image data; generating a weight value of the each of the windows according to the pixel ratio value, a first brightness weight, and a second brightness weight; generating an adjusted brightness value according to the average brightness values of the windows and the weight values of the windows; and performing an auto exposure process according to the adjusted brightness value to generate final image data. The final image data is for a display panel to display.