Abstract: One aspect comprises obtaining one or more image regions from a first image of an eye. Each of the image regions may include a view of a respective portion of the white of the eye. The aspect may further comprise applying several distinct filters to each of the image regions to generate a plurality of respective descriptors for the region. The several distinct filters may include convolutional filters that are each configured to describe one or more aspects of an eye vasculature and in combination describe a visible eye vasculature in a feature space. A match score may be determined based on the generated descriptors and based on one or more descriptors associated with a second image of eye vasculature.

Abstract: A data-processing method includes providing a parametric map including a plurality of parameter values, each one characterizing a corresponding location of a body-part. The method includes determining at least one statistical indicator of at least one distribution of a plurality of analysis parameter values corresponding to selected analysis locations, each statistical indicator being indicative of a condition of an analysis region of the body-part defined by the analysis locations.

Abstract: Embodiments of the subject technology provide for a hybrid OCR approach which combines server and device side processing that can offset disadvantages of performing OCR solely on the server side or the device side. More specifically, the subject technology utilizes image characteristics such as glyph details and image quality measurements to opportunistically schedule OCR processing on the mobile device and/or server. In this regard, text extracted by a “faster” OCR engine (e.g., one with less latency) is displayed to a user, which is then updated by the result of a more accurate OCR engine (e.g., an OCR engine provided by the server). This approach allows factoring in additional parameters such as network latency and user preference for making scheduling decisions. Thus, the subject technology may provide significant gains in terms of reduced latency and increased accuracy by implementing one or more techniques associated with this hybrid OCR approach.

Abstract: Disclosed are a homography estimation apparatus and method. A down-sampling unit reduces the reference image and the target image to the same size to generate down-sampled images. A feature point extraction unit extracts feature points from the reference image and the target image down-sampled to the same size, respectively. An outlier removal unit matches the feature points extracted from the reference image with the feature points extracted from the target image, and detects and removes outliers, which are feature points that do not match, from the matched feature points. A homography estimation unit estimates a homography using feature points from which outliers are removed. A reference image correction unit corrects the reference image using the estimated homography.

Abstract: A method and associated systems for object identification and subsequent processing based on digital imaging and physical attributes. An object-identification system receives, in a materials-handling environment, a digital image and physical attributes that characterize an unidentified object. An attempt is made to identify the object by matching the image and attributes to those of known objects stored in an image database, an attribute database, or another external source. The object is associated with a label that identifies the actual object, associates the object with a similar object that may be substituted for the actual object in a desired application, or designates the object as unidentifiable. The digital image, label, and external sources used to identify the object may be updated by associating them with metadata gathered during the identification process. Subsequent processing is governed by business rules that operate as functions of the label data.

Abstract: A game apparatus obtains a captured image captured by a camera. First, the game apparatus detects an object area of the captured image that includes a predetermined image object based on pixel values obtained at a first pitch across the captured image. Then, the game apparatus detects a predetermined image object from an image of the object area based on pixel values obtained at a second pitch smaller than the first pitch across the object area of the captured image.

Abstract: A biometric authentication device uses IR-VCSELs as light sources for performing a better biometric authentication by providing clearer images. A light guide module is introduced to minimize the size of the device. Moreover, the biometric authentication device uses a single image sensing module to gather the vein image and the fingerprint image into the same detection signal which is then analyzed and compared with the pre-stored vein feature data and fingerprint feature data. Therefore, the biometric authentication device can achieve an approach in lowering hardware costs, simplifying circuit designs and providing an outstanding performance.

Abstract: A device for checking a secured object provided with at least one security element for generating sequential or dynamic optical effects according to the orientation thereof and/or the movements applied thereto, has a display screen, a position and/or motion sensor and a device for generating and displaying on the screen a simulation of the nominal security element associated with the secured object, the display depending on the orientation of the device as determined by the position and/or motion sensor, so as to be able to compare the security element of the object to be checked and the simulation according to the respective orientations or movements thereof. A method for checking the secured object is by means of such a device.

Abstract: An image processing apparatus comprises: an image acquisition unit for acquiring a plurality of original images acquired by imaging a specimen including a structure in various focal positions using a microscope apparatus; an image generation unit for generating, on the basis of the plurality of original images, a first image on which blurring of an image of the structure has been reduced in comparison with the original images; and an analysis unit for obtaining information relating to the structure included in the first image by applying image analysis processing to the first image. The image generation unit selects a part of the original images having focal positions included within a smaller depth range than a thickness of the specimen from the plurality of original images obtained from the specimen, and generates the first image using the selected original images.

Abstract: An optimal recognition for handwritten input based on receiving a touch input from a user may be selected by applying both a delayed stroke recognizer as well as an overlapping recognizer to the handwritten input. A score may be generated for both the delayed stroke recognition as well as the overlapping recognition and the recognition corresponding to the highest score may be presented as the overall recognition.

Abstract: A scanned image of a document includes a pair of fiducial marks, and a code mark between and at least substantially collinear with the pair of fiducial marks. A location of a feature within the scanned image of the document, other than the pair of fiducial marks and the code mark, is determined based on the pair of fiducial marks and the code mark within the scanned image.

Abstract: A system and method are provided for learning part-based object models during a learning phase from training images and applying the learned object models to an input image during runtime. The learned part-based object models are augmented by appearance-based models of the objects. The part-based object models correspond to the shapes of the parts of an object. The appearance-based models provide additional appearance cues to the object models for object classification. The approach to learning part-based object models has the capability of learning object models without using viewpoint labels of the objects. The learning is also invariant to scale and in-plane rotation of the objects.

Abstract: Corresponding partial features are extracted from an input pattern and a registration pattern as a preregistered pattern. A plurality of combinations of the partial features are generated as composited partial features. One of registration pattern classes to which the input pattern corresponds is identified by using the plurality of composited partial features. The identification is performed based on the result of evaluation of the partial features which belong to the composited partial feature and correspond to each other in the input pattern and the registration pattern. In the evaluation, the composited partial feature is evaluated based on the measurement result of the quantity of partial features meeting a predetermined criterion.

Abstract: A method for reconstructing an image of an object that includes a plurality of image elements. The method includes accessing image data associated with a plurality of image elements, and reconstructing an image of the object by optimizing an objective function, where the objective function is optimized by iteratively solving a nested sequence of approximate optimization problems. The algorithm is composed of nested iterative loops, in which an inner loop iteratively optimizes an objective function approximating the outer loop objective function, and an outer loop that utilizes the solution of the inner loop to optimize the original objective function.

Abstract: A variety of methods and systems involving sensor-equipped portable devices, such as smartphones and tablet computers, are described. One particular embodiment decodes a digital watermark from imagery captured by the device and, by reference to watermark payload data, obtains salient point data corresponding to an object depicted in the imagery. Other embodiments obtain salient point data for an object through use of other technologies (e.g., NFC chips). The salient point data enables the device to interact with the object in a spatially-dependent manner. Many other features and arrangements are also detailed.

Abstract: A method (100) and system (300) is described for processing video data comprising a plurality of images. The method (100) comprising obtaining (104, 106), for each of the plurality of images, a segmentation in a plurality of regions and a set of keypoints, and tracking (108) at least one region between a first image and a subsequent image resulting in a matched region in the subsequent image taking into account a matching between keypoints in the first image and the subsequent image. The latter results in accurate tracking of regions. Furthermore the method may optionally also perform label propagation taking into account keypoint tracking.

Abstract: Patient radiation exposure during computerized tomography (CT) scans is estimated. More specifically, efficient approaches for generating a suitable patient model which may be used for estimating the radiation dose absorbed by a patient receiving a CT scan, for estimating a patient dose by interpolating the results of multiple simulations, and for a service provider to host a dose estimation service made available to multiple CT scan providers.

Abstract: An image processing apparatus that converts a frame rate by creating a sub-frame from an input frame and outputting the sub-frame, the image processing apparatus includes a generation unit configured to generate the sub-frame from the input frame, a calculation unit configured to calculate a feature amount of brightness of the input frame, and a control unit configured to perform control so as to reduce luminance of the sub-frames generated by the generation unit based on the feature amount calculated by the calculation unit.

Abstract: Patient radiation exposure during computerized tomography (CT) scans is estimated. More specifically, efficient approaches for generating a suitable patient model which may be used for estimating the radiation dose absorbed by a patient receiving a CT scan, for estimating a patient dose by interpolating the results of multiple simulations, and for a service provider to host a dose estimation service made available to multiple CT scan providers.

Abstract: A method and system for achieving accurate segmentation of characters with respect to a license plate image within a tight bounding box image. A vehicle image can be captured by an image capturing unit and processed utilizing an ALPR unit. A vertical projection histogram can be calculated to produce an initial character boundary (cuts) and local statistical information can be employed to split a large cut and insert a missing character. The cut can be classified as a valid and/or a suspect character and the suspect character can be analyzed. The suspect character can be normalized and passed to an OCR module for decoding and generating a confidence quote with every conclusion. The non-character images can be rejected at the OCR level by enforcing a confidence threshold. An adjoining suspect narrow character can be combined and the OCR confidence of the combined character can be assessed.