Abstract: Systems and associated methods for coin discrimination are disclosed herein. Disclosed methods for discriminating coins include recognizing strings of alphanumerical characters of the coin using Optical Character Recognition (OCR). The methods can include recognizing colors and/or reflectivity of the coin using, for example, pixel thresholding algorithms. The methods can further include adding a line to an image of the coin, and measuring angles between the line and the edges on the coin. The methods can also include generating a rectangular image of the coin using, for example, a log-polar transform, generating a series of, for example, Fourier transforms from the rectangular image, and identifying spectral peak locations and intensities in the Fourier transform results.

Abstract: A magnet is disposed on one side of a conveyance plane in which a sheet-like medium to be read is conveyed and generates a magnetic field in a direction perpendicular to the conveyance plane. A magnetoresistive effect element is disposed between the magnet and the conveyance plane, and detects an intensity variation in a conveyance direction component of the magnetic field in a magnetic reading area. An imaging optical system and a light receiver are disposed on the side opposite to the magnet side with respect to the conveyance plane. The imaging optical system forms an image of an optical reading area on the light receiver, the optical reading area including at least a portion in the conveyance direction of the magnetic reading area of the conveyance plane.

Abstract: Methods and apparatus for detecting labels included in a document or other binarized image, and for extracting and/or using information associated with a label, are described. A nodal structure modeling objects, e.g., characters, character strings or words, which make up various label aliases are described. The nodal structure is used to generate a score for portions of a binarized document with the scores being used to determine the presence or absence of one or more label aliases. When a label alias is determined to be present, information is extracted from the document and used as information corresponding to a label to which the identified label alias corresponds. Multiple different label aliases may correspond to a single label allowing multiple different aliases to be used to identify the same information. The label aliases and information extraction can be and sometimes used to extract information from scanned forms.

Abstract: A method to create a photo diary includes creating an entry for a time period in the photo diary. Creating the entry includes selecting candidate frames from digital videos created or received in the time period. Selecting the candidate frames includes performing people and pet detection on the digital videos, extract frames with people and pets from the digital videos perform people recognition on the frames with people to identify frames with recognized persons. The method further includes sorting the candidate frames with recognized persons and pets into groups based on criteria, selecting representative frames from the groups, and presenting the representative frames in the entry.

Abstract: In a method, device and system for obtaining a medical image data set, a raw data stream is produced by a data acquisition device, the raw data stream including at least digital data of a medical raw data image set. The raw data stream is provided to a data compression device, wherein it is compressed. The compressed raw data stream is transferred to a data decompression device, wherein it is decompressed. The decompressed raw data stream is transferred to an image calculation tool, which produces a medical image data set operating on the decompressed raw data stream.

Abstract: There is provided an image processing apparatus that includes a depth-adjustment-amount determination section configured to determine a depth adjustment amount of an input image, an evaluation function storage section configured to store an evaluation function, the evaluation function representing a relationship of a subjective depth amount of the image to a color-saturation component thereof, the subjective depth amount being a depth amount subjectively felt by a user, an input-value-adjustment-amount determination section configured to determine an input-value adjustment amount based on the evaluation function, the input-value adjustment amount representing a retina's response to the color-saturation component corresponding to the determined depth adjustment amount, an adjustment gain calculation section configured to calculate each spatial-frequency-component adjustment gain based on the determined input-value adjustment amount, and a gain superimposition section configured to superimpose each of the calcu

Abstract: The present invention discloses a method of retrieving a plurality of data slices from a medical image data set (5), the method comprising the steps of: a) displaying an indicator (10, 20) associated with the plurality of data slices; b) selecting the indicator (10, 20) based on a user input; and c) retrieving the plurality of data slices (1, 2) associated with the indicator when said indicator is selected; wherein the association between the indicator and the plurality of slices is based on segmentation of the medical image data set, the indicator representing an object obtained in the segmentation of the medical image data set, the plurality of data slices comprising the object data. The method of the invention reduces the amount of data transfer because it allows for retrieving only those data slices which comprise relevant data relating to the object of interest.

Abstract: An information-presentation device (100) contains a viewing screen (108) and an image-gathering component (106). The viewing screen presents first and second reference icons (136 and 138) having an adjustable reference characteristic controlled with substantially only a single adjustable parameter. The image-gathering component provides the screen with frames of a video image of a scene in which first and second scene locations (152 and 154) have a scene characteristic whose value is to be approximately determined. A user first causes the first reference icon to be approximately superimposed on the first scene location in a captured frame of the image. The user then causes the second reference icon to be approximately superimposed on the second scene location in the captured frame as the adjustable parameter is adjusted to enable the reference characteristic to approximately match the scene characteristic and thereby provide a measurement of the scene characteristic.

Abstract: A method for identifying synonymous expressions includes determining synonymous expression candidates for a target expression. A plurality of target images related to the target expression and a plurality of candidate images related to each of the synonymous expression candidates are identified. Features extracted from the plurality of target images are compared with features extracted from the plurality of candidate images using a processor to identify a synonymous expression of the target expression.

Abstract: A feature point matching device includes a position feature generation unit for generating a position feature quantity for a feature point based on a position of the feature point included in an image, a pixel value feature generation unit for generating a pixel value feature quantity for the feature point based on a pixel value of the feature point included in the image, and a feature matching unit for matching a first feature point and a second feature point based on a degree of matching between a first position feature quantity generated from a first image and a second position feature quantity generated from a second image and a degree of matching between a first pixel value feature quantity generated from the first image and a second pixel value feature quantity generated from the second image.

Abstract: Techniques for performing continuous enrollment for face verification are provided. In one embodiment, a computing device can receive, from a user, an indication that the user wishes to authenticate himself/herself with the computing device via face verification. In response to the indication, the computing device can capture, using a camera, a series of images of the user's face and can authenticate the user by evaluating each of the series of images against a face template for the user, where the user is authenticated based on an N-th image in the series. Once the user has been authenticated, the computing device can select one or more images from the series prior to the N-th image and can add the selected images to the user's face template.

Abstract: An image processing apparatus, which analyzes retina layers of an eye to be examined, comprising, means for extracting a feature amount, which represents an anatomical feature in the eye to be examined, from a projection image obtained from a tomogram of the retina layers and a fundus image of the eye to be examined, means for determining a type of the anatomical feature based on the feature amount, means for deciding layers to be detected from the retina layers according to the determined type of the anatomical feature, and detecting structures of the decided layers in the tomogram, and means for modifying the structure of the layer included in a region having the anatomical feature of the structures of the layers detected by the layer structure detection means.

Abstract: A method for controlling a light emission of at least one headlight of a vehicle, which has a traffic sign recognition device. The method includes receiving at least one traffic sign recognition signal from an interface to the traffic sign recognition device. In this instance, the at least one traffic sign recognition signal represents a traffic sign recognized in a course of the road currently being traveled by the vehicle. The method also includes setting a debounce time and/or a debounce stretch for a change in the light emission of the at least one headlight between first and second radiation characteristics as a function of the at least one traffic sign recognition signal. Finally, the method includes delaying the change in the light emission of the at least one headlight by the debounce time set and/or the debounce stretch set, to control light emission of the at least one headlight.

Abstract: A moving object detection method according to an embodiment includes evaluating an average value, instead of a median value, of pixel values at the same pixel positions across multiple superposed images. A threshold value obtained by multiplying the average value by a predetermined number is employed to distinguish space debris from an object which emits light at a higher luminance than the space debris. In order to detect the space debris accurately, an average value of the pixel values that are equal to or less than the threshold is employed as an evaluation value for the space debris detection.

Abstract: Methods, systems, and computer-readable mediums are presented that process and store images efficiently in a memory system. When a new image is received, it is compared to a plurality of reference images. The most similar reference image is located, and a delta image is generated representing a difference between the reference image and the new image. Instead of storing the entirety of the new image, the delta image can be stored along with a reference to the corresponding reference image, such that the new image can be restored from the delta image and the reference image. The total number of reference images and delta images can be dynamically balanced such that predetermined ratios of image numbers or image sizes can be maintained.

Abstract: An evaluation value calculation unit is configured to compare an edge image and virtual image for each particle, assigns a higher evaluation value if there are more overlapping edges between the images, and assigns a higher evaluation value if there are more edges that are not overlapping edges and for which an edge-to-edge distance, which is the distance between an edge in the edge image and an edge in the virtual image, is less than or equal to a prescribed value. A position and orientation estimation unit is configured to estimate the position of a vehicle based on the evaluation value for each particle.

Abstract: A process for treating samples of biological, microbiological and/or chemical material, comprising at least a step of arranging a plurality of samples of biological, microbiological and/or chemical material on a corresponding plurality of housing seats (4) of a transportable support body (3) of a support device (2), further comprising a step of projecting (3) onto the support body (3) at least a light signal (18), during the step of arranging the plurality of material samples, at the effective position or housing seat or seats (4) wherein each sample of material is arranged, such as to guide the positioning or to indicate the positioning visibly.

Abstract: A method of measuring lean on a container driven in rotation comprises: taking at least one image of the container to obtain images of the left and right edges of the ring, the matrix images of the left and right edges of the heel, of the shoulder, and/or of the base of the neck; analyzing the images of the left and right edges of the ring to determine the real position of the ring; and the matrix images of the left and right edges to determine a left positioning point Tg and right positioning point Td; and determining the theoretical position of the ring on a perpendicular to the straight line segment passing through the left and right positioning points; and based on variations in the differences between the real position and the theoretical position of the ring, deducing a measurement of the lean of the container.

Abstract: Disclosed are a method and an apparatus for tracking a marker. The method of tracking a marker by an electronic device includes: detecting a position of a marker in a first frame; tracking a position of the marker in a second frame based on the position of the marker detected in the first frame; and estimating a 3D position based on the tracked position of the marker. Further, the method of tracking a marker is implemented through various embodiments.

Abstract: Aspects of the disclosure relate to identifying construction objects. As an example, an image captured by a camera associated with a vehicle as the vehicle is driven along a roadway may be received. This image may be converted into a first channel corresponding to an average brightness contribution from red, blue and green channels of the image. The image may also be converted into a second channel corresponding to a contribution of a color from the red and the green channels of the image. A template may then be used to identify a region of the image corresponding to a potential construction object from the first channel and the second channel.