Abstract: Systems and methods for providing micro defect inspection capabilities for optical systems are disclosed. Each given wafer image is filtered, treated and normalized prior to performing surface feature detection and quantification. A partitioning scheme is utilized to partition the wafer image into a plurality of measurement sites and metric values are calculated for each of the plurality of measurement sites. Furthermore, transformation steps may also be utilized to extract additional process relevant metric values for analysis purposes.

Abstract: Biometric authentication devices, systems and methods are provided. The authentication device includes biometric reader configured for generating raw biometric data indicative of a physiological characteristic of a user; and processor operatively coupled to the biometric reader, the processor being configured for: receiving the raw biometric data, generating derivative biometric data by processing a portion of the raw biometric data relating to a pre-selected aspect of the physiological characteristic, the pre-selected aspect being suitable for identifying the user, the derivative biometric data being indicative of a plurality of instances of the pre-selected aspect in the raw biometric data, generating biometric identification data from the derivative biometric data, the biometric identification data being based upon relationships between the plurality of instances of the pre-selected aspect in the raw biometric data, and using the biometric identification data to identify the user.

Abstract: Unlabeled samples are added to existing samples. Candidate samples for new support vectors are extracted from the added unlabeled samples using a plurality of existing support vectors. The new support vectors are selected from the candidate samples using the plurality of existing support vectors.

Abstract: In accordance with some embodiments, wireless devices may automatically form ad hoc networks to enable more efficient sharing of media between the devices and in some cases more efficient facial recognition of captured media. In some embodiments, automatic story development may be implemented at the local level without involving backend servers.

Abstract: A maximum hypersphere is created in the feature space according to support vectors, wherein the support vectors are one or more feature vectors in a feature space. A center of the created maximum hypersphere is calculated according to the support vector(s). A decision hyper sphere is created with the same center as the calculated center of the created maximum hypersphere. Feature vector(s) are classified within the decision hypersphere, as positive feature vector(s). False positive rate is kept to a predetermined level to provide effective object detection.

Abstract: An electronic device (100) includes a first processor (802) and a second processor (804) coupled to the first processor. The first processor (802) is to receive image data from a first imaging camera (114, 116) and to determine two-dimensional (2D) spatial feature data representing one or more 2D spatial features identified from the image data. The second processor (804) is to determine three-dimensional (3D) spatial feature data representing one or more 3D spatial features identified based on the 2D spatial feature data. Further, the first processor (802) can initiate detection of one or more 2D spatial features from a portion of an image frame prior to receiving the entire image frame.

Abstract: An image generation apparatus stores a plurality of selection condition rows including a plurality of selection conditions used for selecting an image from a plurality of material images, selects at least one material image from the plurality of material images as a first material image, obtains a feature quantity of the first material image, selects a selection condition row which is stored in the storage unit and includes a selection condition including the obtained feature quantity, selects a second material image from the plurality of material images based on a selection condition row which has been selected, and generates an image based on the first and the second material images which have been selected and the selection condition row which has been selected.

Abstract: A computer implemented method for extracting meaningful text from a document of unknown or unspecified format. In a particular embodiment, the method includes reading the document, thereby to extract raw encoded text, analysing the raw encoded text, thereby to identify one or more text chunks, and for a given chunk, performing compression identification analysis to determine whether compression is likely. The method can further include performing a decompression process, performing an encoding identification process thereby to identify a likely character encoding protocol, and converting the chunk using the identified likely character encoding protocol, thereby to output the chunk as readable text.

Abstract: Disclose a system for recording ridge patterns comprising a light source, a component which determines the position of a scanning surface, an optical system, a multi-element image sensor, an electronic memory and a processing device, wherein the output electronic image from the system is linked by means of merging in the processing device to at least two intermediate images which are linked to the optical image from the scanning surface.

Abstract: A method, system, and computer program product for evaluating digital images of handwritten documents comprising handwritten symbols are disclosed. A set of symbols from the digital image is determined by applying a first predefined technique. If the set of symbols determined by applying the first predefined technique does not match with a predefined set of symbols, a second predefined technique is applied to determine the set of symbols from the digital image. Thereafter, an evaluation report is created based on the determining by applying the first predefined technique or the determining by applying the second predefined technique.

Abstract: In accordance with various aspects of the disclosure, a detecting engine for detecting targets/materials in hyperspectral scenes is disclosed. The detecting engine combines data partitioning and dimensionality reduction to reduce the number of computations needed to identify in which pixels in a hyperspectral scene a given material is present. Computation reduction (in some instances, by two fold) greatly impacts the speed of and power consumed by the detecting engine making the engine suitable for hyperspectral imaging of large scenes, processing using many filters per pixel, or missions requiring testing large numbers of reference spectra to see which are present in a scene.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, are disclosed for reducing the impact of lighting conditions and biometric distortions, while providing a low-computation solution for reasonably effective (low threshold) face recognition. In one aspect, the methods include processing a captured image of a face of a user seeking to access a resource by conforming a subset of the captured face image to a reference model. The reference model corresponds to a high information portion of human faces. The methods further include comparing the processed captured image to at least one target profile corresponding to a user associated with the resource, and selectively recognizing the user seeking access to the resource based on a result of said comparing.

Abstract: An information processing system is configured for automated diagnostic analysis of digital images. The system comprises an image classifier implementing an image processing engine for performing at least a portion of a classification operation on at least a portion of an image. The image processing engine comprises an interconnection of at least one image planner element, a plurality of image scrutinizer elements and at least one image aggregator element. The image planner element is configured to organize the plurality of image scrutinizer elements into two or more logical groups of image scrutinizer elements based at least in part on one or more criteria to be used in performing the classification operation.

Abstract: A video processing apparatus includes a first storage means unit which stores, in correspondence to a viewer, frame feature values to characterize each frame of scenes constituted by a series of frames in a video content viewed by the viewer; a second storage means unit which stores, as scene groups classified by attributes of the scenes, the frame feature values of scenes constituted by the series of frames; an interest level accumulation means unit which compares the frame feature values stored in the first storage means unit with the frame feature values stored in the second storage means unit, and in case the compared frame feature values match, increases a score about the viewer which represents the interest level with respect to the scene group of which the frame feature values match; and a viewer preference determination means unit which determines that the scene groups of the which the scores are higher are the scene groups preferred by the viewer.

Abstract: A technique is provided for efficiently process three-dimensional point cloud position data that are obtained at different viewpoints. A projecting plane is set in a measurement space as a parameter for characterizing a target plane contained in plural planes that form an object. The target plane and other planes are projected on the projecting plane. Then, a distance between each plane and the projecting plane is calculated at each grid point on the projecting plane, and the calculated matrix data is used as a range image that characterizes the target plane. The range image is also formed with respect to the other planes and with respect to planes that are viewed from another viewpoint. The range images of the two viewpoints are compared, and a pair of the planes having the smallest difference between the range images thereof is identified as matching planes between the two viewpoints.

Abstract: A method for environmental representation, in which two images of an environment (U) are taken respectively and a disparity image is determined by means of stereo image processing. An unobstructed free space (F) is identified in the disparity image, in that each pixel of the disparity image is allocated either to the unobstructed ground surface (B) or to one of several segments (S11 to Snu) depending on disparity values of the respective pixel. Segments (S11 to Snu) of the same width are formed from pixels of the same or similar distance to an image plane. An object (O1 to Ok) located outside of the free space (F) is modelled in the environment (U) using one segment (S11 to Snu) or several segments (S11 to Snu).

Abstract: Vision based tracking of a mobile device is used to remotely control a robot. For example, images captured by a mobile device, e.g., in a video stream, are used for vision based tracking of the pose of the mobile device with respect to the imaged environment. Changes in the pose of the mobile device, i.e., the trajectory of the mobile device, are determined and converted to a desired motion of a robot that is remote from the mobile device. The robot is then controlled to move with the desired motion. The trajectory of the mobile device is converted to the desired motion of the robot using a transformation generated by inverting a hand-eye calibration transformation.

Abstract: A method and apparatus for determining a geographic location of a scene in a captured depiction comprising extracting a first set of features from the captured depiction by algorithmically analyzing the captured depiction, matching the extracted features of the captured depiction against a second set of extracted features associated with reference depictions with known geographic locations and when the matching is successful, identifying the geographic location of the scene in the captured depiction based on a known geographic location of a matching reference depiction from the reference depictions.

Abstract: A sales data processing apparatus which registers and processes sales data on a transaction-by-transaction basis. The apparatus includes: an imaging module that images a customer who is waiting for registration; a manipulation determination module that determines whether or not a prescribed one of a series of manipulations for registration of sales data of one transaction was performed; and a generation module that generates customer identification image data based on an image taken by the imaging module if the manipulation determination module determines that the prescribed manipulation was performed.

Abstract: The classification and segmentation system of the current invention makes use of information from pixels of an image, namely the magnitude of the pixels, to run specific analytics to classify and segment the image pixels into different groups. This invention includes a system for processing an image, the system including an input device, a processor, a memory and a monitor. The input device is configured to receive image data, where the image data includes pixels and each pixel has a magnitude. The memory has instructions stored in it that, when executed by the processor, cause the processor to run calculations. The calculations include: calculating the log-magnitudes from the magnitudes of at least a plurality of the pixels, calculating standard deviations of the log-magnitudes for subsets of the plurality of pixels and compute an integral of the standard deviations over a desired range. The pixels are classified into different groups based on a value of the integral relative to one or more integral values.