Abstract: A method for improving classification results of a classifier including receiving classification results for a plurality of elements that have been classified by a classifier as one of a plurality of classes, constructing a graph having a plurality of nodes, each node corresponding to one of the elements, and a plurality of labels, each label corresponding to one of the classes, adding edges between nodes corresponding to related elements, adding edges between each node and each label, and using a graph cut algorithm to cut edges to a node and partition the graph into classes, the graph cut algorithm using as input the classification results for the element corresponding to that node and related elements.

Abstract: A face detection device for detecting the face of a person in an input image includes the a face detection circuit, a signal processing circuit, and a controller. The face detection circuit includes a hardware circuit that is configured to detect a face in an input image. The signal processing circuit is configured to perform signal processing based on an input image signal in accordance with a rewritable program including a face detection program for detecting a face in an input image. The controller is configured to allow the face detection circuit and the signal processing circuit to perform face detection on an image of a frame or on respective images of adjacent frames among consecutive frames, and to control face detection by the signal processing circuit on the basis of a face detection result obtained by the face detection circuit.

Abstract: A method for studying the behavior of an animal in an experimental area including stimulating the animal using a stimulus device; collecting data from the animal using a data collection device; analyzing the collected data; and developing a quantitative behavioral primitive from the analyzed data. A system for studying the behavior of an animal in an experimental area including a stimulus device for stimulating the animal; a data collection device for collecting data from the animal; a device for analyzing the collected data; and a device for developing a quantitative behavioral primitive from the analyzed data. A computer implemented method, a computer system and a nontransitory computer readable storage medium related to the same. Also, a method and apparatus for automatically discovering, characterizing and classifying the behavior of an animal in an experimental area. Further, use of a depth camera and/or a touch sensitive device related to the same.

Abstract: Joint depth estimation and semantic labeling techniques usable for processing of a single image are described. In one or more implementations, global semantic and depth layouts are estimated of a scene of the image through machine learning by the one or more computing devices. Local semantic and depth layouts are also estimated for respective ones of a plurality of segments of the scene of the image through machine learning by the one or more computing devices. The estimated global semantic and depth layouts are merged with the local semantic and depth layouts by the one or more computing devices to semantically label and assign a depth value to individual pixels in the image.

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: A method, product and system for implementing liveness detector for face verification. A method comprising detecting a symmetry line of the face; and verifying that the subject moved the mouth by computing a score based on values of a pair of images in the symmetry lines, wherein the score is indicative to a difference in the shape of the mouth between the pair of images. Another method comprises: verifying identity of a subject based on facial recognition and voice recognition, said verifying comprise determining there is mouth movement in an image sequence, wherein said determining comprises: in each image of the sequence, detecting a symmetry line of the face; and verifying that the subject moved the mouth, wherein said verifying comprises: computing a score based on comparison of symmetry lines of the face in different images of the set of images; and comparing the score with a threshold.

Abstract: A method, system and product for locating facial features using symmetry line of the face. The method comprises: obtaining an image of a face of a subject; automatically detecting a symmetry line of the face, wherein the symmetry line intersects at least a mouth region of the face; and automatically locating a facial feature of the face using the symmetry line. Optionally, a rotation of the symmetry line is used to select a template, to rotate a template or to rotate the image. Optionally, the facial feature is symmetrical and the facial feature is searched for using a symmetrical template. Optionally, the automatic locating comprises performing a one dimension correlation of an intensity cross section defined by the symmetry line with a cross section template. Optionally, the automatic location comprises correlating a curve defined by the symmetry line with a template curve.

Abstract: A capacitive fingerprint sensing device and method therein for noise detection are disclosed. The capacitive fingerprint sensing device comprises a plurality of sensing elements, each comprising a sensing structure and configured to sense a capacitive coupling between the sensing structure and a finger. The fingerprint sensing device further comprises sensing circuitry and timing circuitry configured to control a timing of a drive signal. The fingerprint sensing device is controllable to operate in a noise-detection mode and in a fingerprint mode. In the noise-detection mode, the fingerprint sensing device is configured to control the timing circuitry such that no drive signal is provided. The fingerprint sensing device senses a capacitive coupling between the finger and at least one sensing structure and provides a sensing signal indicative of the capacitive coupling between the finger and the sensing structures by means of said sensing circuitry.

Abstract: One embodiment provides a method, including: receiving, from an audio capture device, speech input; converting, using a processor, the speech input to machine text; receiving, from an alternate input source, an input comprising at least one character; identifying, using a processor, a location associated with the machine text to insert the at least one character; and inserting, using a processor, the at least one character at the location identified. Other aspects are described and claimed.

Abstract: A system, article, and method of feature matching for multiple images.

Abstract: A method, which is performed by an electronic device, for obtaining a speaker-independent keyword model of a keyword designated by a user is disclosed. The method may include receiving at least one sample sound from the user indicative of the keyword. The method may also generate a speaker-dependent keyword model for the keyword based on the at least one sample sound, send a request for the speaker-independent keyword model of the keyword to a server in response to generating the speaker-dependent keyword model, and receive the speaker-independent keyword model adapted for detecting the keyword spoken by a plurality of users from the server.

Abstract: An image guidance system for tracking a surgical instrument during a surgical procedure. The image guidance system includes a plurality of cameras adapted to be located external to a surgical area for capturing images of optically visible patterns. A processing system receives and processes the images to recognize the patterns and triangulate the locations and orientations of each pattern relative to a camera. The processing system uses a reference dataset to recognize the patterns.

Abstract: A method and apparatus for (a) receiving a three-dimensional (3D) point cloud from a depth sensor that is oriented towards an open end of a shipping container, the point cloud comprising a plurality of points that each have a respective depth value, (b) segmenting the received 3D point cloud among a plurality of grid elements, (c) calculating a respective loaded-container-portion grid-element volume for each grid element, (d) calculating a loaded-container-portion volume of the shipping container by aggregating the calculated respective loaded-container-portion grid-element volumes, (e) calculating an estimated fullness of the shipping container based on the loaded-container-portion volume and a capacity of the shipping container; and (f) outputting the calculated estimated fullness of the shipping container.

Abstract: Enhanced contrast between an object of interest and background surfaces visible in an image is provided using controlled lighting directed at the object. Exploiting the falloff of light intensity with distance, a light source (or multiple light sources), such as an infrared light source, can be positioned near one or more cameras to shine light onto the object while the camera(s) capture images. The captured images can be analyzed to distinguish object pixels from background pixels.

Abstract: Systems, methods, and computer media for implementing convolutional neural networks efficiently in hardware are disclosed herein. A memory is configured to store a sparse, frequency domain representation of a convolutional weighting kernel. A time-domain-to-frequency-domain converter is configured to generate a frequency domain representation of an input image. A feature extractor is configured to access the memory and, by a processor, extract features based on the sparse, frequency domain representation of the convolutional weighting kernel and the frequency domain representation of the input image. The feature extractor includes convolutional layers and fully connected layers. A classifier is configured to determine, based on extracted features, whether the input image contains an object of interest. Various types of memory can be used to store different information, allowing information-dense data to be stored in faster (e.g., faster access time) memory and sparse data to be stored in slower memory.

Abstract: An audio communication endpoint receives a bitstream containing spectral components representing spectral content of an audio signal, wherein the spectral components relate to a first range extending up to a first break frequency, above which any spectral components are unassigned. The endpoint adapts the received bitstream in accordance with a second range extending up to a second break frequency by removing spectral components or adding neutral-valued spectral components relating to a range between the first and second break frequencies. The endpoint then attenuates spectral content in a neighborhood of the least of the first and second break frequencies for thereby achieving a gradual spectral decay. After this, reconstructing the audio signal is reconstructed by an inverse transform operating on spectral components relating to said second range in the adapted and attenuated received bitstream. At small computational expense, the endpoint may to adapt to different sample rates in received bitstreams.

Abstract: According to the present invention, a pedestrian is detected from an imaged image and a partial image including the pedestrian is extracted, shape information of the pedestrian acquired from the extracted partial image is accumulated and the shape information of a predetermined time before and the current shape information are compared using the accumulated shape information to detect change in the movement of the pedestrian, discontinuous movement estimating information indicating a discontinuous movement of the pedestrian that occurs following the change in the movement of the pedestrian is acquired from a storage means at the time the change in the movement of the pedestrian is detected, and a behavior of the pedestrian is predicted using the acquired discontinuous movement estimating information.

Abstract: A method for fingerprint recognition utilizes an auto encode decode network to perform feature extraction on a first fingerprint image acquired by a fingerprint sensor and a second fingerprint image retrieved from a database. First and second fingerprint features corresponding to the first and second fingerprint images are thus obtained. The first and second fingerprint features may have equal dimensionality. Dimensionality reduction may be performed on the first and second fingerprint features to respectively obtain third and fourth fingerprint features. The third and fourth fingerprint features may have equal dimensionality. A cosine distance between the third and fourth finger print features may determine whether the first fingerprint image and the second fingerprint image belong to a same fingerprint.

Abstract: A target place is set in an area of a human body structure having a tree structure in a three-dimensional image. The tree structure of the human body structure is extracted. A path from a reference point set on a branch upstream side of the target place on the tree structure to the target place is determined. Priority is set for respective portions of the tree structure of the human body structure outside the path based on a positional relationship between the portions and the target place. An initial image representing only a portion of the path and images for confirmation of each step sequentially representing the respective portions of the human body structure outside the path according to the priority are generated from the three-dimensional image. The initial image is displayed, and then, the generated images for confirmation of each step are displayed.

Abstract: A voice recognition processing apparatus includes a voice acquirer, a first voice recognizer, a second voice recognizer, a sorter, a storage device, and a processor. The voice acquirer acquires a voice uttered by a user and outputs voice information. The first voice recognizer converts the voice information into first information. The second voice recognizer converts the voice information into second information. The sorter sorts third information and fourth information from the second information. The storage device stores the first information, the third information, and the fourth information. The processor performs processing based on the first information, the third information, and the fourth information. If there are one or two pieces of missing information in the first information, the third information, and the fourth information, the processor complements the missing information by using information stored in the storage device and performs processing.