Abstract: Described is an approach to gesture interaction that is based on user interface widgets. In order to detect user gestures, the widgets are provided with hotspots that are monitored using a camera for predetermined patterns of occlusion. A hotspot is a region where a user interacts with the widget by making a gesture over it. The user's gesture may be detected without the user physically touching the surface displaying the widget. The aforesaid hotspots are designed to be visually salient and suggestive of the type of gestures that can be received from the user. Described techniques are advantageous in relation to conventional systems, such as systems utilizing finger tracking, in that they can better support complex tasks with repeated user actions. In addition, they provide better perceived affordance than conventional systems that attempt to use widgets that are not designed for gesture input, or in-the-air gesture detection techniques that lack any visual cues.

Abstract: Disclosed in an ultrasonic diagnostic apparatus for appropriately evaluating the image quality of a elastic image with high reliability and accuracy, the ultrasonic diagnostic apparatus including: a probe (12) that transmits and receives ultrasonic waves to and from an object; an elasticity information calculating unit (32) that calculates elasticity information on the basis of the ultrasonic waves received by the probe (12); an elastic image constructing unit (34) that generates an elastic image on the basis of the elasticity information; an image display device (display) (26) that displays the elastic image; and an elastic image evaluating unit (40) that detects the fluctuation cycles in the elasticity information, finds the fluctuation patterns in the elasticity information for each predetermined section in the fluctuation cycles, and evaluates the stability of the elastic image on the basis of the fluctuation patterns.

Abstract: Systems and methods are disclosed herein for improving customer service. A video feed of a camera viewing a POS queue is analyzed to identify customers and measure customer biometric data. The biometric data is analyzed and used to generate customer service actions such as alerting a representative or calling in additional staff if the data indicates customer dissatisfaction. The biometric data of a customer may be correlated to transaction data of the customer in order to detect changes of the purchase habits of the customer due to dissatisfaction. Changes in purchase habits, such as a loss of a customer, may be used in combination with the biometric data to establish thresholds of biometric data used to generate customer service actions.

Abstract: A method and an apparatus for reconstructing a three dimensional model of an object are provided. The method includes the following steps. A plurality of first depth images of an object are obtained. According to a linking information of the object, the first depth images are divided into a plurality of depth image groups. The linking information records location information corresponding to a plurality of substructures of the object. Each depth image group includes a plurality of second depth images, and the substructures correspond to the second depth images. According to the second depth image and the location information corresponding to each substructure, a local module of each substructure is built. According to the linking information, the local models corresponding to the substructures are merged, and the three-dimensional model of the object is built.

Abstract: A device that combines a first image photographed with a first amount of exposure and a second image photographed with a second amount of exposure lower than the first amount of exposure, thereby generating a combined image having a wider dynamic range than a dynamic range for the amounts of exposure of the first and second images, the device includes a motion region extraction unit configured to extract at least one motion region in which an object moving between the first image and the second image is shown; a combining ratio determining unit configured to increase a combining ratio of the second image to the first image for a pixel in a background region outside of the at least one motion region such that the higher a luminance value of a pixel of the first image, the higher the combining ratio.

Abstract: An optical coherence tomography system having real-time artifact and saturation correction includes an optical coherence tomography unit, and a signal processing and display system adapted to communicate with the optical coherence tomography unit to receive imaging signals therefrom. The optical coherence tomography system is a Fourier Domain optical coherence tomography system. The signal processing and display system includes a parallel processor configured to correct the imaging signals, in real time, to at least partially remove image artifacts and saturation based on a subset of image data within an image frame.

Abstract: Various techniques are provided to process infrared images. In one implementation, a method of processing infrared image data includes receiving infrared image data associated with a scene. The infrared image data comprises a plurality of pixels arranged in a plurality of rows and columns. The method also includes selecting one of the columns. The method also includes, for each pixel of the selected column, comparing the pixel to a corresponding plurality of neighborhood pixels. The method also includes, for each comparison, adjusting a first counter if the pixel of the selected column has a value greater than the compared neighborhood pixel. The method also includes, for each comparison, adjusting a second counter if the pixel of the selected column has a value less than the compared neighborhood pixel. The method also includes selectively updating a column correction term associated with the selected column based on the first and second counters.

Abstract: A classification apparatus includes: a spectrogram generation unit that generates a spectrogram of a time variation signal of a classification object by processing the time variation signal of the classification object obtained by a sensor; a two-dimensional Fourier transform calculation unit that calculates a two-dimensional Fourier transform of the generated spectrogram; a similarity calculation unit that calculates a similarity between an template image and an image of the obtained two-dimensional Fourier transform, for each template image corresponding to each phenomenon stored in the template image memorizing unit; and a determination unit that determines whether the time variation signal of the classification object conforms to any of one or more phenomena, on the basis of the calculated similarity.

Abstract: A pixel set formation unit in an image analysis unit of an image processing device forms pixel sets from original images subject to analysis. A principal analysis unit of the image analysis unit performs principal component analysis in units of pixel sets. A synthesis unit synthesizes results of analysis in units of pixel sets so as to generate images of eigenvectors of a size of the original images. An image generation unit displays the images of the eigenvectors and stores data for an image generated by using the images of the eigenvectors in a generated image storage unit.

Abstract: Image analysis includes: determining, using one or more processors, an image quality score associated with an image, including: determining a foreground and a background in the image; calculating a set of one or more characteristic parameters of the image based on the determined foreground and background; calculating the image quality score based at least in part on the set of characteristic parameters, wherein calculating the image quality score comprises using an image quality computation model that has been pre-trained; and in response to a search query, generating a set of search results that includes a set the images, wherein inclusion of the images or ranking of the search results is based at least in part on image quality scores associated with the set of images.

Abstract: Three-dimensional coordinates of feature points of an object to be measured are back-projected to a frame image photographed from a specific position, and image coordinates of the back-projected feature points and the feature points in this frame image are compared. In this case, the feature points, which are mismatched, are removed as feature points which are mistracked between plural frames. In this case, two processing systems, of which initial conditions of calculation for obtaining the back-projected coordinates are different from each other, are performed, and the detection of the above mistracked points is performed on each of the two back-projected coordinates. The mistracked points detected in at least one of the processing systems are removed, and are not succeeded to the following processing.

Abstract: An image of real world is processed to identify blocks as candidates to be recognized. Each block is subdivided into sub-blocks, and each sub-block is traversed to obtain counts, in a group for each sub-block. Each count in the group is either of presence of transitions between intensity values of pixels or of absence of transition between intensity values of pixels. Hence, each pixel in a sub-block contributes to at least one of the counts in each group. The counts in a group for a sub-block are normalized, based at least on a total number of pixels in the sub-block. Vector(s) for each sub-block including such normalized counts may be compared with multiple predetermined vectors of corresponding symbols in a set, using any metric of divergence between probability density functions (e.g. Jensen-Shannon divergence metric). Whichever symbol has a predetermined vector that most closely matches the vector(s) is identified and stored.

Abstract: A finger biometric sensor may include an array of finger biometric sensing pixels, and processing circuitry coupled to the array of finger biometric sensing pixels. The processing circuitry may be capable of collecting initial enrollment finger biometric data sets and generating an initial enrollment criteria based thereon, collecting at least one additional enrollment finger biometric data set, and adapting the initial enrollment criteria based thereon to define an additional enrollment criteria. The processing circuitry may also be capable of flagging the initial enrollment finger data sets and the at least one additional enrollment finger data set as sufficient if the additional enrollment criteria meets an acceptance condition, and collecting further enrollment finger biometric data and adapting the additional enrollment criteria if the additional enrollment criteria fails to meet the acceptance condition.

Abstract: A method and apparatus for tracking passengers at a travel facility and may include receiving captured facial recognition features of a passenger using a first facial recognition camera at a first known location, determining if the captured facial recognition features of the passenger are stored in a database, wherein if the captured facial recognition features of the passenger are not stored in the database, starting a timer, receiving captured facial recognition features of the passenger using a second facial recognition camera at a second known location, stopping the timer, determining the amount of elapsed time between the received captured facial recognition features of the passenger using the first facial recognition camera at the first known location and the receiving captured facial recognition features of the passenger using the second facial recognition camera at the second known location, outputting the determined amount of elapsed time to at least one or more.

Abstract: Systems, devices and methods are described including receiving a depth image and applying a template to pixels of the depth image to determine a location of a human head in the depth image. The template includes a circular shaped region and a first annular shaped region surrounding the circular shaped region. The circular shaped region specifies a first range of depth values. The first annular shaped region specifies a second range of depth values that are larger than depth values of the first range of depth values.

Abstract: Image analysis techniques applicable to mammograms and other types of images may include image normalization, image segmentation, forming a prediction bias image, and creating an equalized image based on the prediction bias image. Creation of the equalized image may include subtraction of the prediction bias image from the original image. Forming the prediction bias image may involve the use of trained predictors.

Abstract: Disclosed are methods and systems for monitoring and reporting road violations of vehicles sharing roads with responding emergency vehicles. According to an exemplary method video is captured from a forward and/or rear facing camera mounted to an emergency vehicle, and the video is processed to identify any vehicles in violation within a prescribed distance from the emergency vehicle. A license plate id of a vehicle determined to be in violation is identified and communicated to the appropriate authorities.

Abstract: An adequate solution for computer vision applications is arrived at more efficiently and, with more automation, enables users with limited or no special image processing and pattern recognition knowledge to create reliable vision systems for their applications. Computer rendering of CAD models is used to automate the dataset acquisition process and labeling process. In order to speed up the training data preparation while maintaining the data quality, a number of processed samples are generated from one or a few seed images.

Abstract: A linear mark detection system includes a filter value calculation unit, a filter value threshold processing unit, and a feature value output unit. The filter value calculation unit calculates, for each pixel of an image, filter values corresponding to each of a plurality of linear mark widths using pixel values inside and outside the linear mark. The filter value threshold processing unit selects the most suitable value from filter values corresponding to each of the plurality of linear mark widths as a feature value. The feature value output unit outputs, for each pixel of the image, the feature value computed by the filter value threshold processing function as the feature value corresponding to the linear mark.

Abstract: Methods and devices for optimizing classification tree evaluation for online and real-time characterization of tissue by using GPUs are disclosed that give a significant improvement in run time compared to data decomposition. The methods and devices use a parallel algorithm designed for single instruction, multiple data (SIMD) architectures commonly found in GPUs. Various optimizations and their effects are also disclosed.