Abstract: A computer capable of recognizing gesture commands is disclosed. Suppose that a user makes a gesture of swinging a hand from side to side in front of a camera associated with a computer. A camera module receives frames with shots of the gesture in order. The camera module calculates a gradation difference between corresponding pixels of each frame and a background image to generate a set of binarized differential images. The camera module then combines differential images to generate composite images. In response to a determination that any of the composite images matches a reference pattern, the camera module outputs a computer command. The computer command can be used to control the power state of the computer or start a specific application within the computer.

Abstract: A system accesses an image with each pixel of the image having luminance values each representative of a color component of the pixel. The system generates a first histogram for aggregate luminance values of the image, and accesses a target histogram for the image representative of a desired global image contrast. The system computes a transfer function based on the first histogram and the target histogram such that when the transfer function is applied, a histogram of the modified aggregate luminance values is within a threshold similarity of the target histogram. The system modifies the image by applying the transfer function to the luminance values of the image to produce a tone mapped image, and outputs the modified image.

Abstract: A display device includes an image pickup device, a stroboscope, and a stroboscopic image prediction creation unit. The stroboscope applies stroboscopic light to a subject together with the photography by the image pickup device. The stroboscopic image prediction creation unit acquires distance distribution information showing the distribution of distance information relative to the subject of the photography of the subject together with the application of stroboscopic light, and predict in advance, on the basis of the distance distribution information, a stroboscopic image for the photography of the subject together with the application of the stroboscopic light.

Abstract: In an example, a method of coding video data includes determining, by a video coder and for a block of video data, a palette having a plurality of entries indicating a plurality of respective color values, wherein a first line of the block of video data includes a pixel located adjacent to an edge of the block of video data, and wherein a second line of the block of video data includes a pixel located adjacent to the edge of the block and adjacent to the pixel of the first line. In this example, the method also includes coding, in a scan order, index values that map pixels of the block to entries in the palette, wherein the pixel of the second line immediately follows the pixel of the first line in the scan order.

Abstract: A method includes receiving a stream of synthetic images from a synthetic vision system and receiving a stream of sensor images from at least one sensor. The method also includes performing, by a processing array including a plurality of parallel processing elements, one or more fusion operations on a particular synthetic image of the stream of the synthetic images and one or more particular sensor images of the stream of the sensor images. Upon performing one or more fusion operations on the particular synthetic image of the stream of the synthetic images and the one or more particular sensor images of the stream of sensor images, the method further includes outputting a combined image to a display for presentation to a user.

Abstract: A computing device of a first vehicle may receive a first image and a second image of a second vehicle having flashing light signals. The computing device may determine, in the first image and the second image, an image region that bounds the second vehicle such that the image region substantially encompasses the second vehicle. The computing device may determine a polar grid that partitions the image region in the first image and the second image into polar bins, and identify portions of image data exhibiting a change in color and a change in brightness between the first image and the second image. The computing device may determine a type of the flashing light signals and a type of the second vehicle; and accordingly provide instructions to control the first vehicle.

Abstract: A method for detecting a position of a sheet of light is described. A second derivative filter is applied to an intensity profile of a line of pixels. An ingress pixel position associated with an ingress zero-crossing second derivative value is determined. The ingress pixel position is between a first pixel position with a first minimum intensity value of the intensity profile and a second pixel position with a first maximum intensity value of the intensity profile. An egress pixel position associated with an egress zero-crossing second derivative value is determined. The egress pixel position is between a third pixel position with a second maximum intensity value of the intensity profile and a fourth pixel position with a second minimum intensity value of the intensity profile. A midpoint pixel position between the ingress pixel position and the egress pixel position is output as the position of the sheet of light.

Abstract: Various disclosed embodiments relate to video content analysis based in part upon the detection of shot transitions. In some embodiments, a process and computer system for detecting shot transitions in a video is used to separate a video sequence into a series of “shots” having multiple frames. These shots may then be used for additional processing, e.g., content detection within the video frames.

Abstract: A color chart detection apparatus that detects a color chart from an image representing the color chart having a plurality of palettes arranged in a predefined order is provided. The color chart detection apparatus: extracts any pixel having a color component corresponding to each designated one of a predetermined number of palettes; selects at least three palettes to form a first group and, when a combination of pixels selected on a palette-by-palette basis from among the pixels extracted for the respective palettes included in the first group is arranged in the predefined order, detects each of the pixels included in the combination as being a candidate pixel; and based on the candidate pixel, computes color information representing color of the palette corresponding to the candidate pixel on the image and position information representing position of the corresponding palette on the image.

Abstract: A method and apparatus for performing target detection. A potential object is detected within a candidate chip in an image. The potential object is verified as a candidate object. The candidate object is classified as one of a candidate target or a background in response to the potential object being verified as the candidate object. The candidate target is verified as a target of interest in response to the candidate object being classified as the candidate target.

Abstract: In accordance with the teachings described herein, systems and methods are provided for estimating or determining quantiles for data stored in a distributed system. In one embodiment, an instruction is received to estimate or determine a specified quantile for a variate in a set of data stored at a plurality of nodes in the distributed system. A plurality of data bins for the variate are defined that are each associated with a different range of data values in the set of data. Lower and upper quantile bounds for each of the plurality of data bins are determined based on the total number of data values that fall within each of the plurality of data bins. The specified quantile is estimated or determined based on an identified one of the plurality of data bins that includes the specified quantile based on the lower and upper quantile bounds.

Abstract: Image binarization methods and apparatus are described. A set of input image pixel values, e.g., a set of grayscale values corresponding to an input image, is processed to determine whether to recommend to use local binarization thresholds or a global binarization threshold. Edges including edge pixels are identified. A first histogram corresponding to edge pixel values and a second histogram corresponding to image pixel values are generated, subjected to one or more smoothing operations, and truncated, based on information derived from the edge histogram. Characteristics of the histograms including, e.g., minima, maxima, points of inflection, and hidden peaks, are determined, evaluated, and used to decide between local binarization thresholds and a global threshold. Based on the recommendation, a global threshold is used or local thresholds are used to process the set of input image pixel values and generate a corresponding set of bi-level values.

Abstract: Techniques for Aligned Run-Length Encoding (ARLE) are described. ARLE is an encoding scheme that transforms sets of same-valued consecutive rows into one or more runs, while enforcing boundaries between the runs at set intervals (e.g. every predetermined number of rows). Consecutive rows that contain the same value, but which cross one or more interval boundaries, are encoded as multiple runs that are divided along those interval boundaries. According to one technique, a database server accelerates query processing by setting the interval size to the word size of the processor performing the predicate comparisons. According to another technique, a database server accelerates row lookup by maintaining an offset array that stores the run offsets into the ARLE data of the run that begins each interval.

Abstract: A method and a system are provided for replacing the theme of a mobile terminal on the basis of a user's clothes color, including: setting an RGB value interval of clothes through analyzing the RGB values of all pixels of the clothes location in the obtained image and calculating the clothes RGB average, analyzing the RGB values of all pixels of every theme on a mobile terminal, calculating the theme RGB value average; when the theme RGB average is within the clothes RGB average interval, and replacing the theme of the mobile terminal by the theme corresponding to the theme RGB average. Thus, the mobile terminal becomes more interesting.

Abstract: Methods and systems for sequentially quantizing probability density functions for inkjet printing. In an example embodiment, an operation can be implemented to quantize probability density functions associated with larger drops among a plurality of drops provided by an inkjet printer. Non-quantized probability functions associated with remaining ink drops are then modified utilizing an error incurred at each quantization during quantization of the probability density functions associated with the larger drops. Quantizing the probability density functions and modifying the non-quantized probability functions continue until all drop size probability functions associated with the plurality of drops are quantized.

Abstract: A bilateral filtering method includes decomposing an image patch by pixel intensity to form a stack of patches; computing spatial filtering response of each intensity; multiplying the spatial filtering response of each intensity by corresponding intensity, thereby resulting in multiplied spatial filtering response of each intensity; and summing up the multiplied spatial filtering responses of different intensities weighted with corresponding range weights.

Abstract: Target initialization can dramatically change the performance of the tracker, since the initial window determines for the tracker what to track. In order to achieve a better tracking performance; The present invention relates to a method of semi automatic target initialization based on visual saliency for a given point coordinate in the vicinity of target by the user. Performance boost of tracker is mainly based on two key features of target initialization algorithm: It is capable of compensating erroneous user input; also selecting the most distinctive, salient part of object as target, so better discrimination is achieved between the target and background. Experimental results show that tracking performance is boosted in scenarios, in which the tracking is initialized by the proposed algorithm. Very low computational cost and requirement of only a point coordinate as input in the neighborhood of the target make this approach preferable in real time tracking applications.

Abstract: An image processing apparatus includes a histogram detecting unit that detects a luminance histogram from an input image. A determination unit determines control points for use in generation of a tone curve based on such a luminance that a percentage from a low-luminance side in the detected luminance histogram is equal to a first value, and a percentage from a high-luminance side in the detected luminance histogram is equal to a second value. A tone curve generating unit generates a tone curve based on the calculated control points. An image processing unit performs image processing based on the tone curve. A judgment unit judges whether illuminance of a shooting environment is low. A point light source detecting unit detects a component originating from a point light source from the luminance histogram. When the illuminance of the shooting environment is low, the determination unit makes the second value greater.

Abstract: An apparatus and method for extracting an object of interest from an image using image matting are disclosed herein. The apparatus for extracting an object of interest from an image using image matting includes a saliency map generation unit, a trimap generation unit, and an alpha map generation unit. The saliency map generation unit generates a saliency map corresponding to an object of interest inside an input image using a color space probability distribution corresponding to the input image. The trimap generation unit generates meta-trimaps using filters, and generates a trimap by clustering the meta-trimaps. The alpha map generation unit generates an alpha map using the trimap and a matting Laplacian matrix, and extracts the object of interest based on image matting using the alpha map and the input image.

Abstract: An image processing system and a method thereof is disclosed. A palette including an N number of index pixel values of a processing target image and corresponding index values is created. N is an integer equal to or smaller than 2. An image indexing process is performed on each processing target pixel. When a pixel value of the processing target pixel is a pixel value of one of the N number of index pixel values, a pixel data on a converted image corresponding to the processing target pixel is set as an index value on the palette corresponding to the pixel value of the processing target pixel. Otherwise, the pixel data on the converted image corresponding to the processing target pixel is set as an exceptional value, and the pixel value of the processing target pixel is stored in an exception buffer.

Abstract: In some embodiments, methods or systems may be provided for an imaging system including an imaging sensor, wherein frames or sub-frames of intensity data may be acquired from some or all pixels of the frame, and a moving kernel, smaller than the frame or sub-frame, is moved over the frame for analysis. The values of the center column of the kernel may be compared to the outer column values of the kernel and a column offset for the center column may be determined. Only one offset value may be stored at any one time for each pixel in the frame or sub-frame.

Abstract: Disclosed are a method and system for generating signatures and locating/executing associations for a game program. In this way, hints pertaining to particular gameplay contexts for the game program may be located for a user in an automatic manner without requiring the user to manually locate the hint.

Abstract: To make it possible to accurately grasp an exposure state even in the case where noise is included in captured image data. An input image data acquisition unit configured to acquire input image data including a chart, a noise reduction unit configured to perform noise reduction on the input image data, and a histogram generation unit configured to generate a histogram of luminance of the input image data based on noise reduced image data are included, and the noise reduction unit performs noise reduction on the chart area of the input image data in a degree greater than that in which noise reduction is performed on an area other than the chart.

Abstract: The present invention relates to a method for detecting a mark that is invisible in the visible light region. Here, the invisible mark is displayed on a card using a characteristic according to which the color of light is changed by means of a refractive index difference according to media in the visible light region. According to the method for detecting the invisible mark, it may be quickly determined whether the card is a counterfeit card in an investigation. In addition, since it is unnecessary to repeatedly inspect the card to be checked using various wavelengths, the time required for determining whether the card is a counterfeit card may be reduced.

Abstract: A method for detecting potential phishing URLs includes extracting a URL from a document, analyzing the URL context, and comparing the URL to stored trusted URLs and stored known phishing URLs. The URL context includes anchor text and surrounding content associated with the URL. The method further includes generating a phishing alert based on the comparing and the analyzing.

Abstract: The invention discloses an image restoration method and an imager processing apparatus using the same. The method includes the following steps: receiving a haze image comprising a plurality of pixels; detecting whether a color cast phenomenon occurs on the haze image; if yes, calculating a plurality of Laplacian distribution values respectively corresponding to the color channels; determining a maximum distribution value and a minimum distribution value among the Laplacian distribution values, and generating a self-adaptive parameter by comparing the maximum distribution value and the minimum distribution value; adjusting the transmission map by the self-adaptive parameter so as to generate a adjusted transmission map; calculating a plurality of color parameters respectively corresponding to the color channels according to the Laplacian distribution values; and restoring the haze image by using the color parameters and the adjusted transmission map so as to obtain a restored image.

Abstract: An image processing apparatus acquires a read image which has been obtained by reading one or a plurality of originals by a reading apparatus and includes an original region corresponding to each of the one or plurality of originals, and specifies an object corresponding to contents of the original in the read image based on a group of pixels corresponding to luminance values smaller than a predetermined luminance value in the acquired read image. If a plurality of objects are specified, it is determined whether the plurality of objects are included in one original region, thereby deciding a candidate region corresponding to each of the one or plurality of original regions.

Abstract: A computer-implemented method and system are described for deblurring an image. The method may include accessing an image having a first blurred region and a second blurred region, and generating a first blur kernel for the first blurred region and a second blur kernel for the second blurred region. Thereafter, the first blur kernel is positioned with respect to the first blurred region, and the second blur kernel is positioned with respect to the second blurred region based on the position of the first blur kernel. The image is then deblurred by deconvolving the first blurred region with the first blur kernel, and deconvolving the second blurred region with the second blur kernel.

Abstract: An image processing apparatus and image processing method are disclosed. The image processing apparatus includes an image input unit receiving input image data to obtain grayscale values of a display image, a modeling unit calculating a luminance change ratio for each grayscale value according to a change of an on-pixel ratio and a final luminance reflected by the luminance change ratio, a grayscale re-mapping unit determining a compensation grayscale value for compensating a luminance change ratio according to the on-pixel ratio of the input image data to display a target luminance corresponding to a predetermined grayscale value included in grayscale information of the input image data in the on-pixel ratio condition of the input image data, and an image output unit outputting an output image data compensating the input image data by the compensation grayscale value.

Abstract: An illumination system includes different color LEDs, a controller, and an input device. The controller controls intensities of the LEDs. The input device accepts an input corresponding to a total color of the LEDs. The input device includes a display, a pointer, and an output circuit. The display displays a chromaticity diagram. The pointer specifies a color point in the diagram. The output circuit detects the coordinates of the point and provides them to the controller. The controller includes a limiter, and a calculator. The limiter provides a limiter signal for limiting the maximum output the LED. The calculator calculates outputs of the LEDs based on the coordinates and the limiter signal so that the total color is adjusted to the point.

Abstract: An image processing system automatically segments and labels an image using a hierarchical classification model. A global classification model determines initial labels for an image based on features of the image. A label-based descriptor is generated based on the initial labels. A local classification model is then selected from a plurality of learned local classification model based on the label-based descriptor. The local classification model is applied to the features of the input image to determined refined labels. The refined labels are stored in association with the input image.

Abstract: Systems, methods, and articles to provide robust optical character recognition (OCR) for use in industrial environments. One or more implementations include utilizing Histogram of Oriented Gradients (HOG) features with a sliding window approach as a robust and computationally efficient method of OCR. The implementations are relatively simple to use because there are relatively few parameters to adjust, which allows a non-expert user to setup or modify the system and achieve desirable performance. One reason this is possible is because the implementations described herein do not require character segmentation, which can be difficult to optimize.

Abstract: Disclosed is an image distortion compensating apparatus and an operating method thereof. The image distortion compensating apparatus includes an image composing unit, an edge detecting unit, a first straight line calculating unit, an intersection point calculating unit, a parking space generating unit, a parking space setting unit, and a second straight line calculating unit. The apparatus removes or deduces inconsistency that occurs at a boundary between images for channels in an AVM system.

Abstract: An apparatus and method for recognizing motion by using an event-based vision sensor is provided. An apparatus for recognizing motion using an event-based vision sensor includes: a vision sensor to sense a movement-occurring part and output events; a movement type determiner configured to determine a type of movement using a frequency of occurrence of the events outputted through the vision sensor; a first motion determiner configured to track a movement trajectory of the movement-occurring part and determine a motion pattern based on the movement trajectory in response to a result of the movement type determination unit indicating a small movement; a second motion determiner configured to determine a direction of movement direction in which an object moves based on the events in response to a result of the movement type determination indicating a large movement; and a motion controller configured to output a control instruction to control a device.

Abstract: A method for analyzing spatial point patterns and visualizing the results is presented. The method includes simulating at least one point set within a region using a point process, dividing the region into a plurality of elements, determining scores for both real data and simulated data for each element by weighting the point sets within a domain of a predetermined kernel. The method further includes comparing scores for each element, computing confidence intervals for at least one confidence level having a predetermined statistical significance; and providing a visualization to identify clusters and exclusion zones.

Abstract: A laser scanner (10) detects and determines distances of objects comprises a light transmitter transmitting light in a plurality of consecutive individual pulses. A rotatable deflection unit (18) for the periodical deflection of the transmission light beam (16) into the monitoring zone (20) and an angular measurement unit (30) generates angular position signals (62) in dependence on an angular position of the deflection unit (18). An evaluation unit (32) identifies a received pulse associated with an object from a histogram (110) taken from a histogram memory (32a, 32b) to determine the distance of the object by means of a light propagation method. The histogram (110) is collected over a time interval which is associated with the angular position signal (62). In this connection at least two histogram memories (32a, 32b) are provided in order to collect a first histogram and a second histogram in overlapping time intervals.

Abstract: The enhanced detection of a circular engagement gesture, in which a shape is defined within motion data, and the motion data is sampled at points that are aligned with the defined shape. It is determined whether a moving object is performing a gesture correlating to the defined shape based on a pattern exhibited by the sampled motion data. An application is controlled if determining that the moving object is performing the gesture.

Abstract: A gesture input system with a two-dimension (2D) image sensor and a processing module is provided. The 2D image sensor obtains a plurality of images of a user. The processing module determines positions of an object and a face of the user in a first image of the plurality of images, and determines an operation area for the user according to the positions of the object and the face. Also, the processing module generates a control command according to the subsequent images to the first image of the user within the operation area.

Abstract: A system and method for gesture spotting and recognition are provided. Systems and methods are also provided employing Hidden Markov Models (HMM) and geometrical feature distributions of a hand trajectory of a user to achieve adaptive gesture recognition. The system and method provide for acquiring a sequence of input images of a specific user and recognizing a gesture of the specific user from the sequence of input images based on a gesture model and geometrical features extracted from a hand trajectory of the user. State transition points of the gesture model are detected and the geometrical features of the hand trajectory of the user are extracted based on the relative positions of the detected state transition points and a starting point of the gesture. The system and method further provide for adapting the gesture model and geometrical feature distribution for the specific user based on adaptation data.

Abstract: Systems and methods are provided for collecting image statistics using a pixel mask. In one example, statistics collection logic of an image signal processor may include a pixel weighting mask and accumulation logic. The pixel weighting mask may receive a first representation of a pixel that includes a luma and chroma representation of the pixel. The pixel weighting mask may output a pixel weighting using first and second chroma components of the luma and chroma representation of the pixel. The accumulation logic may receive the first or a second representation of the pixel and the pixel weighting value. Using these, the accumulation logic may weight the second representation of the pixel or the first representation of the pixel using the pixel weighting value to obtain a weighted pixel value, adding the weighted pixel value to a statistics count.

Abstract: A method for filtering a digital image, comprising segmenting the digital image into a plurality of tiles; computing tile histograms corresponding to each of the plurality of tiles; deriving a plurality of tile transfer functions from the tile histograms preferably using 1D convolutions; interpolating a tile transfer function from the plurality of tile transfer functions; and filtering the digital image with the interpolated tile transfer function. Many filters otherwise difficult to conceive or to implement are possible with this method, including an edge-preserving smoothing filter, HDR tone mapping, edge invariant gradient or entropy detection, image upsampling, and mapping coarse data to fine data.

Abstract: A display apparatus and a Non-Photorealistic Rendering process (NPR) are provided. The display apparatus includes: an image processor which processes an NPR with respect to an image so that brightness of a pixel having a brightness value less than a predetermined brightness value is reduced and a brightness of a pixel having a brightness value greater than the predetermined brightness value is increased. Accordingly, a cartoon effect can be maximized.

Abstract: A system for recognizing various human and creature motion gaits and behaviors is presented. These behaviors are defined as combinations of “gestures” identified on various parts of a body in motion. For example, the leg gestures generated when a person runs are different than when a person walks. The system described here can identify such differences and categorize these behaviors. Gestures, as previously defined, are motions generated by humans, animals, or machines. Multiple gestures on a body (or bodies) are recognized simultaneously and used in determining behaviors. If multiple bodies are tracked by the system, then overall formations and behaviors (such as military goals) can be determined.

Abstract: A system for image processing that matches a model image with an input image. The matching process includes using a feature location index for the model image.

Abstract: A method for providing a mechanism for gesture recognition may include causing down-sampling of image data received to generate down-sampled image blocks for a plurality of image frames, causing extraction of a plurality of features from the down-sampled image blocks, determining a moving status of the down-sampled image blocks based on changes in values of respective features in consecutive frames, and determining a direction of motion of an object in the image data based on movement of a first border and a second border of a projection histogram determined based on the moving status of respective down-sampled image blocks. A corresponding apparatus and computer program product are also provided.

Abstract: An image rendering method comprising the steps of: (a) performing a noisy estimation of a given view of a given scene of said image using a Monte-Carlo stochastic renderer, wherein general information of each ray sample, such as color and position in the image plane, is stored, (b) calculating a similarity measure between two sets of samples cast from two pixels of said scene and their neighbors, and (c) generating an output image wherein each pixel color is a weighted combination of the pixel colors generated from (a) with weights based on the similarity measure of (b) between the respective set of samples cast from the pixels and their neighbors.

Abstract: Certain aspects relate to systems and techniques for compressing image data using mixed mode compression schemes. A mixed mode compression scheme can reduce the amount of data stored in a frame buffer to reduce power costs of an image display system. In some implementations, mixed mode compression can be suitable for compression of pixel blocks having one or two color channels exhibiting a relatively low variation in pixel intensity with the remaining channel or channels exhibiting a relatively high variation. The pixel values in each color channel of an RGB or YCoCg image can be analyzed to determine how many channels are a smooth component and how many channels are a variant component, and mixed mode compression can be selected and implemented based on the color channel analysis to adaptively and individually compress the color channels.

Abstract: There are provided a histogram stretching apparatus and a histogram stretching method. The histogram stretching apparatus includes: an image analyzing unit; a histogram generating unit; an extension level setting; and a histogram stretching unit, wherein the histogram generating unit adds a preset reference image level to the minimum image level to calculate the first image level and subtracts the preset reference image level from the maximum image level to calculate the second image level.

Abstract: The adaptive contrast enhancer uses an adaptive histogram equalization-based approach to improve contrast in a video signal. For each video frame, the histogram of the pixel luminance values is calculated. The calculated histogram is divided into three regions that are equalized independently of the other. The equalized values are averaged with the original pixel values with a weighting factor that depends on the shape of the histogram. The weighting factors can be also chosen differently for the three regions to enhance the darker regions more than the brighter ones. The statistics calculated from one frame are used to enhance the next frame such that frame buffers are not required. Many of the calculations are done in the inactive time between two frames.

Abstract: A data processing apparatus obtains an input pixel region contained in image data, inputs a pixel value contained in the input pixel region into an image processor, obtains the image-processed pixel value from the image processor, and outputs an output pixel region. Data of the input pixel region and data of the output pixel region are temporarily stored, and the size of an input area that stores the data of the input pixel region and the size of an output area that stores the data of the output pixel region are set based on the number of pixels in the input pixel region and the number of pixels in the output pixel region.