In some embodiments, noise data may be used to train a neural network (or other prediction model). In some embodiments, input noise data may be obtained and provided to a prediction model to obtain an output related to the input noise data (e.g., the output being a prediction related to the input noise data). One or more target output indications may be provided as reference feedback to the prediction model to update one or more portions of the prediction model, wherein the one or more portions of the prediction model are updated based on the related output and the target indications. Subsequent to the portions of the prediction model being updated, a data item may be provided to the prediction model to obtain a prediction related to the data item (e.g., a different version of the data item, a location of an aspect in the data item, etc.).

An inspection apparatus includes a specimen stage configured to retain a specimen, at least three imaging devices arranged in a triangular array positioned above the specimen stage, each of the at least three imaging devices configured to capture an image of the specimen, one or more sets of lights positioned between the specimen stage and the at least three imaging devices, and a control system in communication with the at least three imaging devices.

A hand-held or otherwise portable or spatial or temporal performance-based image capture device includes one or more lenses, an aperture and a main sensor for capturing an original main image. A secondary sensor and optical system are for capturing a reference image that has temporal and spatial overlap with the original image. The device performs an image processing method including capturing the main image with the main sensor and the reference image with the secondary sensor, and utilizing information from the reference image to enhance the main image. The main and secondary sensors are contained together within a housing.

Method and related system (IPS) for visualizing in particular a volume of a substance during its deposition at a region of interest (ROI). A difference image is formed from a projection image and a mask image. The difference image is then analyzed to derive more accurate motion information about a motion or shape of the substance. The method or system (IPS) is capable of operating in an iterative manner. The proposed system and method can be used for processing fluoroscopic X-ray frame acquired by an imaging arrangement (100) during an embolization procedure.

An imaging device 10 according to one aspect of the present invention includes: a subject distance acquisition section 115; a movement amount acquisition section 120 that acquires an amount of movement of the subject on the basis of the subject distance; a restoration processing determination section 125 that determines, on the basis of the amount of movement acquired by the movement amount acquisition section 120, whether the restoration processing should be performed on the images through a restoration filter, a restoration strength of the restoration processing should be adjusted and the restoration processing should be performed on the images, or the restoration processing should not be performed on the images; and a restoration processing execution section 105 that performs the restoration processing on the images through the restoration filter or with the adjusted restoration strength, on the basis of the determination of the restoration processing determination section 125.

The present disclosure generally relates to a method and device for inverse-tone mapping a picture. The method comprising: —obtaining (20) a first component (Y) comprising: —obtaining a luminance component (L) from said color picture; —obtaining a resulting component by applying (20), a non-linear function on said luminance component (L) in order that the dynamic of the resulting component is increased compared to the dynamic of the luminance component (L)—obtaining (50) a modulation value (Ba) from the luminance of said color picture; —obtaining the first component (Y) by multiplying said resulting component by said modulation value (Ba); —obtaining two chrominance components (C1, C2) from said color picture; —obtaining (40) a first factor (r(L(i))) that depends on the value (L(i)) of a pixel (i) of said luminance component (L); —obtaining (30) at least one color component (Ec) from said first component (Y), said two chrominance components (C1, C2) and said first factor (r(L(i))); and—forming the inverse-tone mapped color picture by combining together said at least one color component (Ec).

For obtaining an good yet easy to use luminance dynamic range conversion, we describe an image color processing apparatus (200) arranged to transform an input color (R,G,B) of a pixel of an input image (Im_in) having a first luminance dynamic range into an output color (Rs, Gs, Bs) of a pixel of an output image (Im_res) having a second luminance dynamic range, which first and second dynamic ranges differ in extent by at least a multiplicative factor 2, comprising: a maximum determining unit (101) arranged to calculate a maximum (M) of color components of the input color, the color components at least comprising a red, green and blue component; —a uniformization unit (201) arranged to apply a function (FP) to the maximum (M) as input, which function has a logarithmic shape and was predetermined to be of a fixed shape enabling to transform a linear input to a more perceptually uniform output variable (u); a function application unit (203) arranged to receive a functional shape of a function, which was specified previously by a human color grader, and apply the function to the uniform output variable (u), yielding a transformed uniform value (TU); a linearization unit (204) arranged to transform the transformed uniform value (TU) to a linear domain value (LU); a multiplication factor determination unit (205) arranged to determine a multiplication factor (a) being equal to the linear domain value (LU) divided by the maximum (M); and a multiplier (104) arranged to multiply at least three linear color components (R,G,B) by the multiplication factor (a), yielding the output color.

Patch partition and image processing techniques are described. In one or more implementations, a system includes one or more modules implemented at least partially in hardware. The one or more modules are configured to perform operations including grouping a plurality of patches taken from a plurality of training samples of images into respective ones of a plurality of partitions, calculating an image processing operator for each of the partitions, determining distances between the plurality of partitions that describe image similarity of patches of the plurality of partitions, one to another, and configuring a database to provide the determined distance and the image processing operator to process an image in response to identification of a respective partition that corresponds to a patch taken from the image.

A method is disclosed that comprises mapping a high-dynamic range luminance picture to a standard-dynamic range luminance picture based on a backlight value Bac associated with the high-dynamic range luminance picture.

A real-time video enhancement method performed at a terminal includes: obtaining an average luminance of a current frame of an image; in accordance with a determination that the average luminance is less than the luminance threshold: obtaining a pixel range of an area of interest of the current frame; determining a local enhancement curve of the current frame according to the pixel range of the area of interest of the current frame; determining a first enhancement curve corresponding to the current frame according to the average luminance of the current frame; determining a second enhancement curve of the current frame according to the local enhancement curve of the current frame and the first enhancement curve of the current frame; and adjusting the current frame according to the second enhancement curve.