Abstract: Assessing color digitally can include imaging digitally a custom color calibration chart under a set of lighting conditions; imaging digitally a workpiece under approximately identical lighting conditions; and comparing color measurement data from the custom color calibration chart to color measurement data from the workpiece to characterize the workpiece.

Abstract: Devices, computer-readable media, and methods for exporting text captured from a video program presented on a display screen using optical character recognition to an alternate destination are disclosed. For example, a processor may present a video program via a display screen, receive, from a control device associated with the display screen, a request to capture text from the video program, and identify text from a frame of the video program via optical character recognition. When the text from the frame is identified via optical character recognition, the processor may present, via the display screen, the text in a selectable format, receive, from the control device, a selection of at least a portion of the text that is presented in the selectable format, and send the at least the portion of the text to an alternate destination in accordance with the selection of the at least the portion of the text.

Abstract: An example method for estimating an emotion based upon a facial expression of a user can include: receiving one or more captured facial expressions from the user at a visual computing device; comparing the one or more captured facial expressions to one or more known facial expressions; and assigning an emotion to the plurality of captured facial expressions based upon the comparing.

Abstract: The present invention provides a facial recognition method, including: obtaining a target facial image; determining a covered region and a non-covered region of the target facial image; calculating the weight of the covered region, and calculating the weight of the non-covered region; extracting feature vectors of the covered region, and extracting feature vectors of the non-covered region; comparing the target facial image with each template facial image in a facial database according to the feature vectors of the covered region, the feature vectors of the non-covered region, the weight of the covered region, and the weight of the non-covered region, to calculate a facial similarity between each template facial image and the target facial image; and determining, when at least one of the facial similarities between the template facial images and the target facial image is greater than or equal to a similarity threshold, that facial recognition succeeds.

Abstract: To provide an image processing system, an image processing method, and a program, capable of detecting a group with high irregularity. An image processing system is provided with: a group detector that detects a group based on an input image captured with an image capturing at a first time; a repeating group analyzer that determines that a detected group has been previously detected; and an alert module that reports when the detected group has been determined by the repeating group analyzer to have been previously detected.

Abstract: A sensing method of a fingerprint sensor is provided. The fingerprint sensor includes a plurality of sensing pixels arranged in an array, and the sensing pixels respectively have a sensing electrode. The sensing method includes following steps. A required resolution of an identification requirement is determined; here, the identification requirement is received by the fingerprint sensor. If the number of pixels of the required resolution is less than or equal to the number of the sensing pixels, self-capacitance sensing is performed on the sensing pixels to provide a first fingerprint pattern. If the number of pixels of the required resolution is greater than the number of the sensing pixels, the self-capacitance sensing and mutual capacitance sensing are performed on the sensing pixels to provide a second fingerprint pattern.

Abstract: A method includes receiving a user input (e.g., a one-touch user input), performing segmentation to generate multiple candidate regions of interest (ROIs) in response to the user input, and performing ROI fusion to generate a final ROI (e.g., for a computer vision application). In some cases, the segmentation may include motion-based segmentation, color-based segmentation, or a combination thereof. Further, in some cases, the ROI fusion may include intraframe (or spatial) ROI fusion, temporal ROI fusion, or a combination thereof.

Abstract: The present invention contributes to decreasing false recognition due to the lighting environment. A facial recognition apparatus comprises a photographing parameter input unit that receives a photographing parameter(s); a lighting information estimation unit that estimates lighting information based on the photographing parameter(s); and a recognition accuracy control unit that controls a recognition accuracy parameter(s) based on the lighting information.

Abstract: Disclosed is a fingerprint detection circuit and a display device. The fingerprint detection circuit comprises at least one fingerprint detection unit, the fingerprint detection unit comprising a switch transistor and a sensor capacitor, the fingerprint detection unit further comprising an output amplification element and a data input terminal for receiving a data signal, wherein a control terminal of the output amplification element is coupled with a terminal of the sensor capacitor, an output terminal of the output amplification element functions as an output terminal of the fingerprint detection unit, an input terminal of the output amplification element is coupled with the data input terminal, the output amplification element is configured for amplifying and outputting a current input to the output amplification element via the data input terminal.

Abstract: Three dimensional (3D) scanning including dynamic detector pose identification utilizing fiducials is provided. Two or more fiducials are operatively coupled to a first body. Configuration data is provided with an identifier and a first position of the two or more fiducials. A detector captures 3D data of the first body. A creator identifies at least two fiducials within the captured 3D data. The creator determines a first observed position of each identified fiducial relative to the detector and compares the first observed position to the configuration data. The creator dynamically identifies the pose of the detector relative to the first body based on the comparison and augments the 3D data with first pose data corresponding to the first pose of the detector. The pose of the detector relative to the body may be undefined and/or unknown during the capture of 3D data without affecting the quality of the model produced from the captured 3D data.

Abstract: The invention relates to a skin print sensor (120) comprising a plurality of elementary acquisition cells (121) which are arranged in and/or on a substrate and each of which includes: a pyroelectric conversion element (PYR) comprising first and second electrodes that are separated by a layer of pyroelectric material, the first electrode being connected to a node (GND) applying a reference potential of the sensor, and the second electrode being connected to a reading node (SN) of the cell; and a third electrode (EL) which is connected to the reading node (SN), is coated with a dielectric layer and is designed to form a capacitance along with the skin of a user.

Abstract: According to a first aspect of the present disclosure, a fingerprint processing system is provided, which comprises: a set of sensor plates; a measurement unit configured to measure one or more capacitances on the sensor plates; a processing unit configured to process the measured capacitances; wherein the measurement unit is configured to concurrently measure capacitances on subsets of the set of sensor plates; wherein the processing unit is configured to process the concurrently measured capacitances. According to a second aspect of the present disclosure, a corresponding method of processing a fingerprint in a fingerprint processing system is conceived. According to a third aspect of the present disclosure, a corresponding computer program is provided.

Abstract: Techniques for converting mechanical markings on hardcopy textual content into digital annotations in a digital document file. In accordance with some embodiments, the techniques include identifying at least one block of text in a digital (scanned) image of a hardcopy document, and identifying at least one mechanical marking in the digital image of the hardcopy document. The mechanical marking, such as an underline, strike-through, highlight or circle, covers or lies adjacent to the corresponding block of text. An annotated digital document file is generated from the digital image of the hardcopy document. The annotated digital document file includes computer-executable instructions representing the original text of the hardcopy document and at least one annotation corresponding to the mechanical marking in the hardcopy document.

Abstract: A machine includes an enclosure having a double layer wall including an outer wall that provides mechanical protection and protection from dust, fluids and environmental factors and an inner wall having a gradient change in reflectance with height within the enclosure; a lens coupled to the enclosure, the lens defining an optic axis-within the enclosure parallel to the gradient change in reflectance with height; a camera coupled to the lens; an image processing circuit coupled to the camera; and a plurality of light sources coupled to the enclosure, the plurality of light sources defining a plurality of illuminant axes located substantially symmetrically around and parallel to the optic-axis. Each of the plurality of light sources includes a plurality of independently controllable segments located along the illuminant axes so an angle of illumination from the plurality of light sources to the optic axis can be controlled.

Abstract: A method, computer system, and a computer program product for identifying sections in a document based on a plurality of visual features is provided. The present invention may include receiving a plurality of documents. The present invention may also include extracting a plurality of content blocks. The present invention may further include determining the plurality of visual features. The present invention may then include grouping the extracted plurality of content blocks into a plurality of categories. The present invention may also include generating a plurality of closeness scores for the plurality of categories by utilizing a Visual Similarity Measure. The present invention may further include generating a plurality of Association Matrices on the plurality of categories for each of the received plurality of documents based on the Visual Similarity Measure. The present invention may further include merging the plurality of categories into a plurality of clusters.

Abstract: Systems and methods of generating a compact visual vocabulary are provided. Descriptor sets related to digital representations of objects are obtained, clustered and partitioned into cells of a descriptor space, and a representative descriptor and index are associated with each cell. Generated visual vocabularies could be stored in client-side devices and used to obtain content information related to objects of interest that are captured.

Abstract: A curved-surface OLED display device with fingerprint identification includes a substrate, a thin film transistor layer, a pixel electrode layer, an OLED display material layer, a common electrode layer, an encapsulation layer, a curved touch detection and fingerprint detection layer and a curved protective layer. The thin film transistor layer includes plural thin film transistors, plural scan lines, and plural data lines. The pixel electrode layer includes plural pixel electrodes. The curved touch detection and fingerprint detection layer includes plural sense electrodes and plural traces for performing the touch detection operation and fingerprint identification operation. A partial area of the curved touch detection and fingerprint detection layer and the curved protective layer exhibits a curved-surface shape.

Abstract: According to the aspect of the present invention, an image processing device capable of absolutely removing noises in each frame forming a live image can be provided. Specifically, according to the aspect of the present invention, a target block T can be set in the original image It and it is searched out where such target block T is imaged in the superimposition target image Ot?1. According to the aspect of the present invention, a tracking of the subject image is executed per block, so that reliability thereof can be extraordinarily improved compared to the conventional method searching the destination every individual pixel.

Abstract: A fingerprint sensor includes a pixel array, an analog-to-digital converter, and a reference signal generator. The pixel array includes a plurality of unit pixels arranged in rows and columns, and each of the plurality of unit pixels generates an analog signal by detecting a fingerprint of a user. The analog-to-digital converter performs an analog-to-digital conversion operation on the analog signal to generate a digital signal. The analog-to-digital converter is configured to perform the analog-to-digital conversion based on a reference signal. The reference signal generator generates the reference signal such that the reference signal decreases at a first rate from a start voltage, and adjusts a magnitude of the start voltage based on the digital signal.

Abstract: A pattern-measuring apparatus and a semiconductor-measuring system are provided which are able to obtain an evaluation result for suitably selecting processing with respect to a semiconductor device. In particular, there is proposed a pattern-measuring apparatus including an arithmetic device which compares a circuit pattern of an electronic device with a reference pattern, in which the arithmetic device classifies the circuit pattern in processing unit of the circuit pattern on the basis of a comparison of a measurement result between the circuit pattern and the reference pattern with at least two threshold values.