Abstract: The present disclosure relates to an image decoding device and method capable of suppressing an increase in an encoding or decoding load. The present disclosure includes: a decoding section configured to decode encoded data obtained by encoding image data for each of a plurality of certain areas obtained by dividing a picture using a plurality of blocks obtained by dividing the area as processing units, for each of the areas; a reordering section configured to reorder decoding results of the encoded data of the respective blocks obtained for the respective areas by the decoding section in a raster scan order of the entire picture; and a transform section configured to transform the decoding results of the respective blocks reordered in the raster scan order of the entire picture by the reordering section and generate decoded image data. The present disclosure can be applied to the image decoding device.

Abstract: In an example embodiment, a deep convolutional neural network (DCNN) is created to assign a professionalism score to an input image. The professionalism score indicates a perceived professionalism of a subject of the input image. The DCNN is designed to automatically learn features of images relevant to the professionalism through a training process.

Abstract: A system to measure effectiveness of displayed content includes a video processing service configured to receive and process a stream of video images captured by one or more video cameras, a display application service configured to produce display content to be displayed on one or more display monitors and to capture user interactions with the displayed content, and a display effectiveness service configured to correlate data received from the video processing service and the display application service and generate a display effectiveness measurement that is a measure of an effectiveness of the displayed content for specific periods of time.

Abstract: Methods and apparatus for image or video decoding in a video decoding system are disclosed. Input data associated with a current block coded with palette mode is received to parse a palette predictor run. A position of reused colors in a palette predictor table is computed according to the palette predictor run. A size of the palette predictor table is determined and compared with the position computed according to the palette predictor run to obtain a comparison result. The decoder applies palette decoding to the current block according to the comparison result. If the comparison result indicates the position computed according to the palette predictor run is not within the palette predictor table, the position is changed to a new position to indicate a corresponding reused color for the current block or a decoding process of palette predictor reuse flags is terminated.

Abstract: A system to measure effectiveness of displayed content includes a video processing service configured to receive and process a stream of video images captured by one or more video cameras, a display application service configured to produce display content to be displayed on one or more display monitors and to capture user interactions with the displayed content, and a display effectiveness service configured to correlate data received from the video processing service and the display application service and generate a display effectiveness measurement that is a measure of an effectiveness of the displayed content for specific periods of time.

Abstract: Systems and methods are provided for processing and extracting content from an image captured using a mobile device. In one embodiment, an image is captured by a mobile device and corrected to improve the quality of the image. The corrected image is then further processed by adjusting the image, identifying the format and layout of the DL, binarizing the image and extracting the content using optical character recognition (OCR). Multiple methods of image adjusting may be implemented to accurately assess features of the DL, and a secondary layout identification process may be performed to ensure that the content being extracted is properly classified.

Abstract: An image processing apparatus and image processing method enlarge an input image (Din) to generate a low-resolution enlarged image (D101). Depending on a result of identification of the pattern of the input image (Din), coefficient data (D108) for conversion to a high-resolution are selected, and a feature component (D102H) of a low resolution is converted to a feature component (D103H) of a high resolution. Decision as to whether or not the pattern of a local region of the input image (Din) is flat is made. If it is flat, the coefficient data are so selected that no substantial alteration is made to pixel values in a high-resolution conversion unit (103). It is possible to reduce the circuit size and the memory capacity, and to improve the noise immunity, and achieve conversion to a high resolution suitable for implementation by hardware.

Abstract: The subject technology provides embodiments for performing fast corner detection in a given image for augmented reality applications. Embodiments disclose a high-speed test that examines intensities of pairs of pixels around a candidate center pixel. In one example, the examined pairs are comprised of pixels that are diametrically opposite ends of a circle formed with the candidate center pixel. Further, a pyramid of images including four rings of surrounding pixels is generated. An orientation of the pixels from the four rings are determined and a vector of discrete values of the pixels are provided. Next, a forest of trees are generated for the vector of discrete values corresponding to a descriptor for a first image. For a second image including a set of descriptors, approximate nearest neighbors are determined from the forest of tree representing closest matching descriptors from the first image.

Abstract: Techniques for processing an image of a check captured using a mobile device are provided. The check image is processed to determine whether the check can be deposited at a bank via a mobile deposit process. The system can identify regions of the check—such as the endorsement area—to determine if the check has been properly endorsed. The system can be implemented on a mobile device and/or a server, where the mobile device routes the check image to the server for processing. If the check cannot be deposited, a rejection is forwarded in real time to the mobile device for possible correction.

Abstract: A computer program product includes instructions for a processor to perform a method of improving image structure and coherence, and/or for simplification/stylization. The method includes inputting the image, by: scanning the image; image capture using a camera; and/or image creation using a computer. Multi-channel images are converted into a single-channel image, which is separated into a first image component—the high spatial frequencies, and a second component image—the low spatial frequencies. The first and second component images are each formed by filtering to remove frequencies outside of respective upper and lower threshold frequencies. A gain multiplier is applied to the filtered first and second component images to control detail amplification. The first and second component images are each blurred at the respective upper and lower threshold frequencies.

Abstract: A method, image processing system, and computer-readable recording medium for item defect inspection are provided. The method is as follows. A test image and a reference image of a test item are received. A test block and a corresponding reference block are obtained from the test image and the reference image to generate a test block image and a reference block image. The test block image and the reference block image are respectively partitioned into multiple sub-blocks. All interfering sub-blocks are identified and filtered out from the test block image and the reference block image, and a shift calibration parameter is obtained accordingly. The test block in the test image is calibrated based on the shift calibration parameter to generate a calibrated test block image. The calibrated test block image and the reference block image are compared to obtain defect information of the test item corresponding to the test block.

Abstract: Smoothing images using machine learning is described. In one or more embodiments, a machine learning system is trained using multiple training items. Each training item includes a boundary shape representation and a positional indicator. To generate the training item, a smooth image is downscaled to produce a corresponding blocky image that includes multiple blocks. For a given block, the boundary shape representation encodes a blocky boundary in a neighborhood around the given block. The positional indicator reflects a distance between the given block and a smooth boundary of the smooth image. In one or more embodiments to smooth a blocky image, a boundary shape representation around a selected block is determined. The representation is encoded as a feature vector and applied to the machine learning system to obtain a positional indicator. The positional indicator is used to compute a location of a smooth boundary of a smooth image.

Abstract: HDR images are coded and distributed. An initial HDR image is received. Processing the received HDR image creates a JPEG-2000 DCI-compliant coded baseline image and an HDR-enhancement image. The coded baseline image has one or more color components, each of which provide enhancement information that allows reconstruction of an instance of the initial HDR image using the baseline image and the HDR-enhancement images. A data packet is computed, which has a first and a second data set. The first data set relates to the baseline image color components, each of which has an application marker that relates to the HDR-enhancement images. The second data set relates to the HDR-enhancement image. The data packets are sent in a DCI-compliant bit stream.

Abstract: A method, system, and computer program product that exploits motion hints associated with rendered video frames. These motion hints are provided to a video encoder to guide a motion-compensation prediction process performed by the video encoder. Specifically, these motion hints can be used to better position a search window in a reference video frame to better capture the motion of a block of pixels in the reference video frame. Because the search window is better positioned in the reference video frame, the memory required to perform the encoding process can be reduced without sacrificing the level of encoded image quality.

Abstract: This disclosure is directed to color matching with shade detection. A method of color matching can include: receiving a camera image of a target, the camera image being collected in the presence of flash illumination; receiving a color sensor spectral measurement of the target, the color sensor spectral measurement being collected in the presence of flash illumination; determining specular and diffuse fractions of a flash intensity profile of the camera image of the target; determining parallax based upon a detected location of a flash centroid within the camera image of the target; converting the parallax to a range measurement for the target; calculating an expected white level for the target based upon the specular and diffuse fractions and the range measurement for the target; and calculating a shade of a detected color based upon the color sensor spectral measurement and the expected white level for the target.

Abstract: A processing device receives input representing a selection of a first area of an image. The processing device determines whether the first selected area of the image corresponds to a blurred area previously created for a second selected area of the image. The blurred area is previously created for the second selected area of the image having a size that is less than a size of the image. The processing device replaces, responsive to determining that the first selected area of the image corresponds to the blurred area previously created for the second selected area of the image, the first selected area of the image with a corresponding portion of the blurred area previously created for the second selected area of the image.

Abstract: According to an example aspect of the present invention, there is provided an apparatus comprising at least one receiver configured to receive sensor information, at least one processing core configured to determine, based at least in part on the sensor information, a position of a device on a physical surface and to obtain or cause obtaining of an image relating to the determined position wherein obtaining the image comprises obtaining static content based on the position of the device on the physical surface and obtaining dynamic content based a virtual space associated with the physical surface.

Abstract: A method includes receiving a first image and a plurality of other images of a planar surface of a specimen. The method also includes identifying first scale-invariant features in the first image. The first scale-invariant features are based on a scale-invariant feature transform of the first image. The method includes storing the first scale-invariant features in a grouping. The method includes, for each respective image of the plurality of other images, identifying scale-invariant features based on a scale-invariant feature transform of the respective image; matching the scale-invariant features to the grouping; based on the matching, determining a planar homography of the respective image with respect to the grouping; and adding the scale-invariant features of the respective image to the grouping. The method also includes stitching the first image and the plurality of other images into a composite image based on the planar homographies.

Abstract: A computer-implemented method, computer program product, and system for detecting work-piece defects. The computer-implemented method may include: receiving a first image of a training work-piece captured using a non-destructive imaging process and a second image of the training work-piece captured using a destructive imaging process; receiving an image of a work-piece captured using a non-destructive imaging process, wherein the work-piece is substantially similar to the training work-piece, and the non-destructive imaging process used to capture the work-piece is substantially similar to the non-destructive imaging process used to capture the training work-piece; matching the image of the work-piece to the first image of the training work-piece; and enhancing the image of the work-piece using the second image of the training work-piece, in response to the image of the work-piece matching the first image of the training work-piece.

Abstract: Systems and methods are provided for processing and extracting content from an image of a driver's license captured using a mobile device. In one embodiment, an image of a driver's license (DL) is captured by a mobile device and corrected to improve the quality of the image. The corrected image is then further processed by cropping the image, identifying the format and layout of the DL, binarizing the image and extracting the content using optical character recognition (OCR). Multiple methods of image cropping may be implemented to accurately assess the borders of the DL, and a secondary layout identification process may be performed to ensure that the content being extracted is properly classified.