Abstract: A compact device for capturing an imprint of a body part working by total reflection with dark background. The device includes a plurality of optically coupled elements including: a first transparent plate including a top face on which the body part bearing the imprint to be imaged can rest; a light source; a screen opaque to light situated below the first transparent plate including a network of holes; a second transparent plate situated below the opaque screen; and a sensor capable of generating an imprint image situated below the second transparent plate; each transparent plate having a refractive index greater than a refractive index of air, and the light source being able to be positioned at the level of the screen to directly illuminate the top face or below the screen to illuminate the top face through the holes.

Abstract: The present disclosure relates to detection of obstacles by an autonomous vehicle in real-time. An obstacle detection system of an autonomous vehicle obtains point cloud data from single frame Light Detection and Ranging (LIDAR) data and camera data, of the surroundings of the vehicle. Further, the system processes the camera data to identify and extract regions comprising the obstacles. Further, the system extracts point cloud data corresponding to the obstacles and enhances the point cloud data, with the detailed information of the obstacles provided by the camera data. Further, the system processes the enhanced point cloud data to determine the obstacles along with the structure and orientation of obstacles. Upon determining the details of the obstacles, the system provides instructions to the vehicle to manoeuvre the obstacle. The disclosed obstacle detection system provides accurate data about a structure, an orientation and a location of the obstacles.

Abstract: Embodiments include methods, systems, and computer program products for remediating a color vision deficiency. Aspects include receiving a time dependent location information for a user. Aspects also include receiving images of a plurality of objects, wherein each of the plurality of objects corresponds to the time dependent location information and, for each of the plurality of objects, identifying an object type and an object color. Aspects also include determining a number of distinguishable colors required to remediate a color vision deficiency and a number of available colors and overlaying one of the plurality of objects with an available color responsive to a determination that the number of distinguishable colors does not exceed the number of available colors.

Abstract: According to one embodiment, a work support system includes an imager, a storage part, and a processor. The imager is configured to image a first transfer object after the first transfer object is transferred into a structural object and arranged inside the structural object. The storage part stores first three-dimensional data. The first three-dimensional data includes three-dimensional data of the structural object and three-dimensional data of the first transfer object. The three-dimensional data of the first transfer object is overlaid at a first position inside the structural object of the three-dimensional data. The processor detects a displacement of the first transfer object of second three-dimensional data with respect to the first transfer object of the first three-dimensional data. The second three-dimensional data is obtained by imaging the first transfer object arranged inside the structural object.

Abstract: A method of calibrating a camera and a laser scanner for their sensor fusion is provided whereby the camera records a camera image of a scene and the laser scanner at least partly scans the scene with a scanning beam and records a remission image from the respective angular position of the scanning beam and from the intensity determined at the angular position of the scanning beam remitted from the scene, wherein an offset and/or a relative orientation between the camera and the laser scanner is determined from a comparison of the camera image and the remission image. Distances with respect to the remission image are here also determined by the laser scanner and distances with respect to the camera image are reconstructed; and in that a correspondence search of corresponding features in the camera image and in the remission image is carried out in three-dimensional space for the comparison.

Abstract: A method for generating a language model for an organization includes: receiving, by a processor, organization-specific training data; receiving, by the processor, generic training data; computing, by the processor, a plurality of similarities between the generic training data and the organization-specific training data; assigning, by the processor, a plurality of weights to the generic training data in accordance with the computed similarities; combining, by the processor, the generic training data with the organization-specific training data in accordance with the weights to generate customized training data; training, by the processor, a customized language model using the customized training data; and outputting, by the processor, the customized language model, the customized language model being configured to compute the likelihood of phrases in a medium.

Abstract: Methods, systems, and techniques for sharing layers between convolutional neural networks (CNNs). A data processing system may include a first and a second CNN that share a first group of layers. The first CNN may include the first group of layers in series with a second group of layers and be configured such that data for the first CNN is input to the first group of layers. The second CNN may include the first group of layers in series with a third group of layers and be configured such that data for the second CNN is also input to the first group of layers.

Abstract: A method and an apparatus for processing high-precision map data, a storage medium and a device. The method includes: performing at least twice collection on map data along a target trajectory so as to respectively acquire at least twice original map data; recognizing an object in the original map data respectively, and extracting an object feature; matching the object feature in each of the original map data; considering an object with the matched object feature as a reference object; and performing fusion processing on each of the original map data. An object in original map data is recognized and an object feature is extracted, then the object feature in each of the original map data is matched and the object obtained after the matching is considered as a reference object, and the reference object is utilized to perform fusion processing on the original map data.

Abstract: A fingerprint enrolling method, a fingerprint enrolling apparatus, and a terminal device are provided. The method includes the following operations. Whether an image-quality fluctuation amplitude of fingerprint images of a user exceeds a preset image-quality fluctuation threshold or image-quality fluctuation threshold range is determined according to image quality of a current fingerprint image of the user currently acquired and image quality of a historical fingerprint image of the user previously acquired. The current fingerprint image is enrolled into a fingerprint database based on a determination that the image-quality fluctuation amplitude does not exceed the image-quality fluctuation threshold or the image-quality fluctuation threshold range.

Abstract: Providing unique prompts for script, comprising sequencing, by a processor, at least one script in a design order having at least one prompt, identifying, by the processor, duplicate prompts of the at least one prompt, identifying, by the processor, unique prompts of the at least one prompt, translation tagging, by the processor, the identified unique prompts and replicating, by the processor, the translation tagged unique prompts to the identified duplicate prompts.

Abstract: A computer-implemented method for lane detection includes receiving a road image from an image capture device, detecting a first solid line marking and a second solid line marking outside of the first solid line marking in the binary road image. The first solid line marking and the second solid line marking are non-parallel lines. The method includes calculating a first distance between a first point of the first solid line marking and a first point of the second solid line marking. The first points being in a top portion of the binary road image. The method includes calculating a second distance between a second point of the first solid line marking and a second point of the second solid line marking. The second points being in a bottom portion of the binary road image. Further, the method includes determining a merging lane based the first distance and the second distance.

Abstract: The present disclosure provides a method of correcting for a turbulence effect in a video comprising a plurality of frames. The method comprises determining a first background region and a region corresponding to a moving object in a first frame of the plurality of frames using a predetermined background model. A second background region in a second frame of the plurality of frames is then determined using the predetermined background model. A turbulence-corrected background region from the first background region and the second background region is generated and the region corresponding to the moving object and the turbulence-corrected background region is fused to form a turbulence-corrected frame. The method then updates the predetermined background model based on the turbulence-corrected frame and corrects for the turbulence effect in the second frame using the updated predetermined background model.

Abstract: An image correction device includes a line segment detection module, a shape specification module and an image correction module. The line segment detection module detects from a captured image obtained by photographing a document a plurality of line segments that correspond to the notation on the surface of the document. The shape specification module specifies shape approximation lines that approximate the surface shape of the document from the plurality of line segments. The image correction module utilizes the shape approximation lines specified by the shape specification module to correct the captured image.

Abstract: A spine measurement system comprises an optical measurement probe, one or more targets, a fluoroscope, and a remote station. A-P and lateral images of the spine are taken using the fluoroscope and provided to the remote station. The remote station includes computer vision that can identify endplates and pedicle screws in the spine. The computer vision in the remote station is further used to identify vertebra and bone landmarks of the spine. The remote station can generate quantitative measurement data such as Cobb angles and axial rotation of the spine from the fluoroscope images that correspond to the spine deformity. The optical measurement probe can send images of the spine with pedicle screw extenders extending from the pedicle screws to the remote station. The remotes station using computer vision can provide spine metrics in real-time by tracking position of the pedicle screw extenders.

Abstract: A method includes obtaining data associated with an electronic component. The method also includes conducting a multi-tier inspection process to verify a conformance of the electronic component. Each of the tiers includes a different type of identification test, and at least one of the tiers is configured to provide fuzzy outputs. The method further includes analyzing the data associated with the electronic component using one or more first tests associated with a first of the tiers to determine whether the electronic component conforms to a pre-specified requirement. In addition, the method includes generating an output based on the analysis and determining whether additional testing is required using one or more next-level tests associated with another of the tiers.

Abstract: Techniques related to a system, article, and method of real-time image segmentation for image processing.

Abstract: Systems and methods of script identification in audio data obtained from audio data. The audio data is segmented into a plurality of utterances. A script model representative of a script text is obtained. The plurality of utterances are decoded with the script model. A determination is made if the script text occurred in the audio data.

Abstract: To quickly specify a region of a character group included in an image, image obtaining means of an image processing device obtains the image data. Expansion means expands and unites a plurality of regions respectively indicating objects included in an image indicated by the image data obtained by the image obtaining means. Character region determining means determines whether all or some of the regions, which are expanded and united by the expansion means, are character regions. Processing performing means performs predetermined processing on a region that is determined by the character region determining means as a character region.

Abstract: A first image and a second image of a scene are obtained for use in detecting the location of the floor in the scene. A first of the images is mapped onto a candidate plane that is perpendicular to a gravity vector, thereby creating a texture-mapped plane. The texture-mapped plane is projected into the geometry of the camera utilized to take the second image to create an artificial first image. A comparison is then performed between the first image and the artificial first image to generate a similarity score. Multiple candidate planes are processed in this manner for the first and second images, and the candidate plane generating the highest associated similarity score is chosen as the floor. This process can be repeated for multiple sets of stereo images.

Abstract: A method, apparatus and non-transitory computer readable storage medium, in one embodiment, interpreting at least one input from a user via a wireless device, receiving at least one user account with the at least one input, deriving at least one representation of user intent, identifying at least one task based on the at least one representation of user intent, contacting at least one service to perform the identified at least one task and synthesizing speech to communicate a result of the contact to the wireless device.