Abstract: A medical image processing apparatus includes: a receiver configured to obtain a captured image resulting from image capture of exciting light that is shed on an observed object and is provided by way of the observed object, and of fluorescent light that is excited by the exciting light and is provided from the observed object; and an image processor configured to perform image processing on the captured image. A light receiving surface of the image sensor is provided with a color filter. The captured image includes plural pieces of first component information about colors corresponding to the spectral characteristics of the plurality of filter groups, respectively. The image processor is configured to generate second component information by combining at least two pieces of first component information, and perform color correction processing that corrects the plural pieces of first component information based on the second component information.

Abstract: A display device includes: a display panel having a display region in which pixels are arranged; scan lines each coupled to the pixels arranged in a row direction; signal lines each coupled to the pixels arranged in a column direction; a signal line drive circuit; a scan line drive circuit selecting the scan lines; and a signal processing circuit. A second half period of a selection period of a first scan line overlaps a first half period of a selection period of a second scan line. The signal processing circuit adjusts a pixel gradation value of the pixel in an m-th column coupled to the second scan line when a difference value between the pixel gradation value of the pixel in the m-th column coupled to the first scan line and an average gradation value of the pixels arranged in the m-th column is larger than a predetermined value.

Abstract: A control method for generating a high quality HDR image is provided. A control device of the technique of this disclosure is a control device configured to control an image capturing element capable of controlling an exposure condition for each of areas, the device including: an acquisition unit configured to acquire an exposure value map obtained by preliminary exposure using the image capturing element; and a setting unit configured to set the exposure condition including a shutter speed and an ISO sensitivity for each of the areas based on the exposure value map.

Abstract: A messaging system performs image processing to relight objects with neural networks for images provided by users of the messaging system. A method of relighting objects with neural networks includes receiving an input image with first lighting properties comprising an object with second lighting properties and processing the input image using a convolutional neural network to generate an output image with the first lighting properties and comprising the object with third lighting properties, where the convolutional neural network is trained to modify the second lighting properties to be consistent with lighting conditions indicated by the first lighting properties to generate the third lighting properties.

Abstract: An input signal correction device includes an input circuit, extension circuit, degenerate circuit, separation circuit, recovery circuit and delay adjustment circuit that operate at an operating frequency f, demura circuit that operates at an operating frequency f/2, and adder circuit. The extension circuit extends the period of R and B input signals by a factor of 2 and outputs preprocessing signals, the degenerate circuit degenerates a G input signal, the demura circuit corrects preprocessing signals from the extension and degenerate circuits and outputs correction signals, the separation circuit reduces the period of the R and B correction signals to ½ and outputs differential signals, recovery circuit reduces the period of G correction signal to ½ and outputs the same differential signal over two periods, the delay adjustment circuit delays the input and output signals, and the adder circuit adds the differential signals to the delay signals and outputs output signals.

Abstract: A control device of a projection apparatus that projects an image from a display portion displaying the image based on input image data to a projection object through an optical system, includes: a correction portion that corrects the input image data by performing first processing of increasing pixel values of pixels of the input image data corresponding to a specific region determined by a light quantity distribution in a surface of the projection object in the image projected to the projection object, and second processing of uniformly decreasing each of pixel values of pixels of the input image data by a first pixel amount.

Abstract: An image capture device of the present invention is provided with: a first brightness adjusting unit which adjusts brightness when capturing an image of a subject; a second brightness adjusting unit which adjusts the brightness of an analog image signal of the subject captured with the brightness adjusted by the first brightness adjusting unit; an A/D conversion unit which subjects the analog image signal with the brightness adjusted by the second brightness adjusting unit to A/D conversion; a third brightness adjusting unit which adjusts the brightness of a digital image signal obtained by the A/D conversion; and a gain-up adjusting unit which raises the gain of a low-illuminance portion of the digital image signal with the brightness adjusted by the third brightness adjusting unit, by means of realtime modification adjustment using a gamma characteristic.

Abstract: An image capturing apparatus generates an image of a high dynamic range that takes into account gain in addition to a range of change of storage capacitance. The image capturing apparatus having an image capturing device of a structure in which blocks each configured by a plurality of photoelectric conversion elements are arranged, includes a first control circuit, a second control circuit, and a generating circuit. The first control circuit is configured to control sensitivity in units of the blocks. The second control circuit is configured to control a gain of a signal for each block obtained by the image capturing device. The generating circuit is configured to, by mapping image data of blocks obtained under the control of the second control circuit to a region that accords with sensitivity set for the blocks in a preset high dynamic range, generate image data of the high dynamic range.

Abstract: A backlight face recognition method, a terminal device using the same, and a computer readable storage medium are provided. The method includes: performing a face detection on each original face image in an original face image sample set to obtain a face frame corresponding to the original face image; capturing the corresponding original face images from the original face image sample set, and obtaining a new face image containing background pixels corresponding to the captured original face images from the original face image sample set; preprocessing all the obtained new face images to obtain a backlight sample set and a normal lighting sample set; and training a convolutional neural network using the backlight sample set and the normal lighting sample set until the convolutional neural network reaches a preset stopping condition. The trained convolutional neural network will improve the accuracy of face recognition in complex background and strong light.

Abstract: Methods and systems are described for processing an image captured with an image sensor, such as a camera. In one embodiment, an estimated ambient light level of the captured image is determined and used to compute an optical-optical transfer function (OOTF) that is used to correct the image to preserve an apparent contrast of the image under the estimated ambient light level in a viewing environment. The estimated ambient light level is determined by scaling pixel values from the image sensor using a function that includes exposure parameters and a camera specific parameter derived from a camera calibration.

Abstract: Disclosed is an electronic device which a camera, a memory, and a processor that is operatively connected with the camera and the memory. The processor performs photographing on an external object multiple times depending on a second exposure time shorter than a specified first exposure time by using the camera, obtains a first image set including a plurality of first images depending on the multiple photographing, composes the first image set to generate a second image, identifies a specific area around at least one light source corresponding to a light source included in the second image, and generates a third image where an image effect associated with the light source is added to the specific area, by using the second image. Moreover, various embodiment found through the present disclosure are possible.

Abstract: Provided are an imaging device and a control method thereof for calculating an amount of tilt of an image sensor and an amount of deviation in a flange focal distance and presenting the amounts to a user. The imaging device acquires, for every one of a plurality of small areas in an imaging region of the image sensor, data regarding a focus position and a focusing degree of a lens by performing AF demodulation following movement of the focus position manually operated by the user, and calculates an amount of tilt of the image sensor or an amount of deviation in a flange focal distance of the lens on the basis of a cross-correlation of the data regarding the focus position and the focusing degree between the plurality of small areas.

Abstract: The inventive concepts provide an auto-focus image sensor and a digital image processing device including the same. The auto-focus image sensor includes a substrate including at least one first pixel used for detecting a phase difference and at least one second pixel used for detecting an image, a deep device isolation portion disposed in the substrate to isolate the first pixel from the second pixel, and a light shielding pattern disposed on the substrate of at least the first pixel. The amount of light incident on the first pixel is smaller than the amount of light incident on the second pixel by the light shielding pattern.

Abstract: A method and an image processing device for image color enhancement are proposed. The method includes the following steps. An input image having input pixels is received, where each of the input pixels includes a luminance component and two chrominance components. A saturation gain of each of the input pixels is determined according to the chrominance components thereof. The chrominance components of each of the input pixels are adjusted according to the saturation gain thereof so as to generate enhanced pixels. An enhanced image is outputted according to the enhanced pixels.

Abstract: There is provided a method and apparatus for image color enhancement, wherein the method comprises the following steps: S1, collecting color components of an image, converting the color components from a RGB space into a HSV space, and obtaining parameters in the HSV space as hue, saturation, and value respectively; S2, performing gain operations selectively on the saturation and the value by judging the saturation in the HSV space; S3, converting the obtained parameters in the HSV space back into the RGB space. In the above method for image color enhancement, after the color components are converted into the HSV space, firstly, the saturation value is judged, and the gain operations are performed selectively by utilizing the gain function according to the judgment result.

Abstract: An image processing apparatus and method for generating high-sensitive, high-brightness color images are disclosed. A second image having a wider band and higher-sensitivity than those of a first image which includes color information may be acquired, wherein the first and second images are images captured from a scene. A first transformed image having high brightness may be generated by performing binning on the first image, and edge information being a high-frequency component may be extracted from the second image. A high-brightness, high-sensitive color image may be generated using the first transformed image and the edge information.

Abstract: There are provided an apparatus and a method for estimating edge areas of pixels in a digital image to thereby prevent an edge sharpening algorithm from being applied to non-edge area of the digital image. Therefore, the apparatus can accurately determine whether each pixel is in an edge area or in a non-edge area, by generating a binary mask obtained by using a luminance difference average between each pixel and each of neighboring pixels in the digital image. Moreover, the determination of an edge-area or a non-edge area may be applied to various digital images, by adjusting a level of edge-area determination.

Abstract: In an A/D conversion circuit and an imaging device, an upper counter acquires a first upper count value by performing counting using one output signal, which constitutes a first lower phase signal output from a delay circuit, as a count clock. After values of bits constituting the first upper count value are inverted, the upper counter acquires a second upper count value by performing counting using one output signal, which constitutes a second lower phase signal output from the delay circuit, as a count clock, and further performing counting based on an upper count clock output from a lower counter. A modification unit modifies a logic state of a count clock to a predetermined state when the count clock of the upper counter is switched.

Abstract: A computerized device for converting a color image data, indicative of a plurality of color image regions defining a two-dimensional color image, into a grayscale image data indicative of a plurality of grayscale image regions defining a two-dimensional grayscale image, with each of the color image regions corresponding to one of the grayscale image regions. A luminance information and a two-dimensional chromatic information is associated with each of the color image regions. The device includes a processor and a memory store. The memory store is adapted to store a program executable by the processor so as to perform the following steps: determining a principal chromatic component of each of the color image regions; determining a first correlation value; and generating the grayscale image data by reference to the first correlation value.