A method for processing an image includes: creating M first image sets based on M image frames to be processed; determining a fusion weight for each sub-image located in each layer in each first image set based on brightness information of each image frame; fusing sub-images located in each same layer in the M first image sets based on the fusion weight, to obtain N fused sub-images arranged in layers based on the preset order; adjusting a brightness of at least one fused sub-image of the N fused sub-images based on a preset brightness adjustment parameter; and obtaining a target image based on the fused sub-image after adjustment.

An optical processing apparatus and a light source luminance adjustment method adapted to detect a rotational displacement and a pressing state are provided. The optical processing apparatus includes a light source unit, a processing unit, and an image sensing unit, wherein the processing unit is electrically connected to the light source unit and the image sensing unit. The light source unit provides a beam of light. The processing unit defines a frame rate, defines a plurality of time instants within a time interval, and sets the light source unit to a luminance value at each of the time instants. A length of the time interval is shorter than the reciprocal of the frame rate. The luminance values are different and are within a range. The image sensing unit captures an image by an exposure time length at each of the time instants, wherein the exposure time lengths are the same.

There is provided an image processing device including a light sensor and a processor. The light sensor is used to detect light and output an image frame. The processor identifies intensity of ambient light according to an image parameter associated with the image frame. When the ambient light is identified to be strong enough, the processor performs an object identification directly using the image frame. When the ambient light is identified to be not enough, the processor firstly converts the image frame to a converted image using a machine learning model, and then performs the object identification using the converted image.

Systems and methods of the invention merge information from multiple image sensors to provide a high dynamic range (HDR) video. The present invention provides for real-time HDR video production using multiple sensors and pipeline processing techniques. According to the invention, multiple sensors with different exposures each produces an ordered stream of frame-independent pixel values. The pixel values are streamed through a pipeline on a processing device. The pipeline includes a kernel operation that identifies saturated ones of the pixel values. The streams of pixel values are merged to produce an HDR video.

A detector for object recognition includes an illumination source for projecting an illumination pattern on an area including at least one object; an optical sensor having a light-sensitive area and configured for determining a first image including a two-dimensional image of the area, and a second image including a plurality of reflection features generated in response to illumination, each reflection feature including a beam profile; an evaluation device for determining beam profile information for each reflection feature by analyzing their beam profiles, determining a three-dimensional image using the determined beam profile information, identifying the reflection features located inside and/or outside an image region, determining a depth level from the beam profile information of the reflection features located inside and/or outside of the image region, determining a material property of the object from the beam profile information, and determining a position and/or orientation of the object.

An electronic device includes a first camera module; a second camera module; and a processor configured to: perform video shooting by using the first camera module, receive a request to capture a picture image while the video shooting is performed by the first camera module, based on the request to capture the picture image, acquire at least one image frame by using the second camera module, and generate an image corresponding to the request to capture the picture image, based on an image frame acquired by using the first camera module and the at least one image frame acquired by using the second camera module while the video shooting is performed.

An image processing apparatus that composites a plurality of images that have been captured with different exposure amounts, the image processing apparatus comprising at least one processor and/or circuit configured to function as following units: a specification unit configured to specify a signal value indicating an upper limit value of an output dynamic range with respect to at least one of the plurality of images; and a decision unit configured to decide on composition percentages of the plurality of images based on the signal value specified by the specification unit.

Techniques are described for tailoring automatic exposure control (AEC) settings to specific patient anatomies and clinical tasks. According to an embodiment, computer-implemented method comprises receiving one or more scout images captured of an anatomical region of a patient in association with performance of a computed tomography (CT) scan. The method further comprises employing a first machine learning model to estimate, based on the one or more scout images, expected organ doses representative of expected radiation doses exposed to organs in the anatomical region under different AEC patterns for the CT scan. The method can further comprises employing a second machine learning model to estimate, based on the one or more scout images, expected measures of image quality in target and background regions of scan images captured under the different AEC patterns, and determining an optimal AEC pattern based on the expected organ doses and the expected measures of image quality.

An image processing apparatus according to the present disclosure includes: a photographing control unit configured to take a photographed image of a sample including a plurality of regions having different reflectances a plurality of times while a photographing condition that affects luminance of the photographed image is changed; a generation unit configured to generate a photographing condition map indicating a photographing condition under which luminance of a pixel in the photographed image exceeds a threshold; a determination unit configured to determine a photographing condition that is suitable for photographing of each of the regions based on the photographing condition map; and a composition unit configured to generate a composite image in which region images of the respective regions are combined by using the photographed image corresponding to the determined photographing condition.

A computer-implemented method for training a denoising model for a microscope includes obtaining a plurality of training images with different image acquisition settings taken with the microscope, the plurality of training images including noise caused by the microscope's hardware, and training the denoising model using the plurality of training images obtained with different image acquisition settings, thereby making the denoising model specific to the microscope's hardware.