Abstract: An image processing method in which a feature amount is analyzed for each of a plurality of images as layout target candidates. First and second image evaluations are performed for an image of the plurality of images, in accordance with first and second (different) evaluation criteria. A main image to be laid out on a main slot in a template is selected from the plurality of images based on the first image evaluation for each of the plurality of images. A sub image is selected to be laid out on a sub slot in the template, which is smaller than the main slot, based on the second image evaluation for each of the plurality of images. The main image is laid out on the main slot in the template, and the sub image is laid out on the sub slot in the template.
Abstract: Provided herein is a control method of an electronic apparatus. The control method of an electronic apparatus includes: generating signal type information using an image data of a signal region portion of a signal lamp in a driving-related image data of a vehicle; and performing a driving-related guide of the vehicle using the generated signal type information.
Abstract: A device includes an input to sequential data associated to a face; a predictor configured to predict facial parameters; and a corrector configured to correct the predicted facial parameters on the basis of input data, the input data containing geometric measurements and other information. A related method and a related computer program are also disclosed.
Type:
Grant
Filed:
April 13, 2017
Date of Patent:
April 30, 2019
Assignee:
Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V.
Inventors:
Dominik Seuss, Teena Chakkalayil Hassan, Johannes Wollenberg, Andreas Ernst, Jens-Uwe Garbas
Abstract: In an information processing method, the importance degree of each person who appears in a first image group and the importance degree of each person who appears in a second image group, containing the first image group, are determined, and, when selecting the image of the output target from the first image group, in a case in which the importance degree of a candidate image of the output target included in the first image group, which is determined from the appearance count in the first image group, exceeds a first threshold, and, in a case in which the importance degree of the candidate image of the output target, which is determined from the appearance count in the second image group, exceeds a second threshold, the candidate image is selected as the output target.
Abstract: Some implementations provide a computer-implemented method that include accessing image frames from a video sequence; detecting face of a subject in each image frame from the video sequence; detecting facial landmark features in the detected face; determining whether a sufficient number of facial landmark features and image frames have been obtained; in response to determining that a sufficient number of facial landmark features and image frames have been obtained, classifying detected facial landmark features from various detected image frames; quantifying variations of the classified facial landmark features across the detected image frames; correlating the quantified variations to a pre-determined threshold; and in response to determining that the quantified variations meet the pre-determined threshold, determining that the video sequence is from a live session.
Abstract: Provided herein is a control method of an electronic apparatus. The control method of an electronic apparatus includes: generating signal type information using an image data of a signal region portion of a signal lamp in a driving-related image data of a vehicle; and performing a driving-related guide of the vehicle using the generated signal type information.
Abstract: There is provided a method for analyzing an image of rod-shaped particles, the method comprising: transforming a spatial domain image of rod-shaped particles having random orientations to a frequency domain image thereof using DFT (discrete Fourier transform); extracting connected components from the frequency domain image using a frequency domain filter, wherein the connected components have a predetermined orientation; and back-transforming the frequency domain image having the extracted connected components to a spatial domain image thereof using IDFT (inverse discrete Fourier transform).
Type:
Grant
Filed:
November 11, 2016
Date of Patent:
April 23, 2019
Assignee:
Research & Business Foundation Sungkyunkwan University
Abstract: According to an aspect of an embodiment, a method may include obtaining a first digital image via a mapping application. The method may also include obtaining a second digital image via the mapping application. The method may additionally include determining a displacement factor between the first digital image and the second digital image. Further, the method may include generating a third digital image by cropping the second digital image based on the displacement factor, adjusting an aspect ratio of the third digital image, and resizing the third digital image. Moreover, the method may include generating a stereoscopic map image of the setting that includes a first-eye image and a second eye image. The first-eye image may be based on the first digital image and the second-eye image may be based on the third digital image.
Abstract: As to N images captured at different focus positions, which are arrayed in order of focus positions, N/2 images are set as feature point extraction images so that at least one of two adjacent images becomes a feature point extraction image; corresponding points corresponding to a feature point, extracted from the feature point extraction image, are searched for from the other images; a correction parameter, with which corresponding positions of the N images are matched, is calculated from a positional relation of the feature point and the corresponding points; and, with an image whose view angle is the smallest among the N images as a reference, the other images are corrected.
Abstract: Embodiments can provide a computer implemented method in a data processing system comprising a processor and a memory, the memory comprising instructions that are executed by the processor to cause the processor to implement a system for providing profile photo enhancement, the method comprising receiving, from an online platform, one or more specifications for image acceptance criteria; receiving, through an uploading user, a plurality of images; receiving, through a requesting user, a request to view an image; selecting a particular specification for image acceptance criteria; for each image in the plurality of images: examining, through an image processing toolbox, the image to determine if the image acceptance criteria are met; if all acceptance criteria are met, providing the image to the requesting user; if one or more acceptance criteria are not met, taking one or more actions to process the image, reexamining, through the image processing toolbox, the processed image to determine if the image acceptan
Type:
Grant
Filed:
August 23, 2016
Date of Patent:
April 9, 2019
Assignee:
International Business Machines Corporation
Abstract: Disclosed are a semiconductor fingerprint identification sensor and a method for manufacturing the same. The semiconductor fingerprint identification sensor includes: a sensing area, a control area and an interface area; the sensing area, the control area and the interface area are communicated with one another; a fingerprint information sensed in the sensing area is sent to the control area, and is output through the interface area after being processed in the control area; the sensing area includes an insulation layer, an wiring layer, a substrate layer and a protective layer which are stacked in a sequence, the wiring layer is embedded between the insulation layer and the substrate layer, a sensor array is disposed on a side of the substrate layer being in contact with the protective layer, a via hole corresponding to the sensor array is disposed on the substrate layer, the sensor array is electrically connected with a sensing lead circuit of the wiring layer through the via hole.
Abstract: A method and apparatus to generate a volume-panorama image are provided. A method of generating a volume-panorama image includes receiving conversion relationships between volume images, one of the received conversion relationships being between a first volume image of the volume images and a second volume image of the volume images, the second volume image including an area that is common to an area of the first volume image, generating an optimized conversion relationship from the one of the received conversion relationships based on the received conversion relationships, and generating the volume-panorama image based on the generated optimized conversion relationship.
Type:
Grant
Filed:
May 9, 2016
Date of Patent:
February 19, 2019
Assignee:
Samsung Electronics Co., Ltd.
Inventors:
Ouk Choi, Hwa-sup Lim, Jung-ho Kim, Do-kyoon Kim
Abstract: A system, device, and method for inspecting the cosmetic and operational features of electronic devices, including computing and telecommunications devices. The cosmetic inspection system includes an image capture unit for capturing the images of the electronic devices, and a user interface for processing the captured images and providing relevant information to the user of the system. Images of the external components such as external casing materials or touch screens of electronic devices are captured and the cosmetic inspection system uses baseline images to make determinations to identify defective components of the electronic devices. Based on these determinations, the system may conclude which, if any, replacement components of the devices are needed to restore the electronic device. In one embodiment, a user of the system may then be provided with information through a user interface about defective components and options for ordering replacement components.
Type:
Grant
Filed:
March 11, 2014
Date of Patent:
January 1, 2019
Assignee:
FedEx Supply Chain Logistics & Electronics, Inc.
Abstract: In some example embodiments, a system is provided for real-time analysis of audio signals. First digital audio signals are retrieved from memory. First computed streamed signal information corresponding to each of the first digital audio signals is generated by computing first metrics data for the first digital audio signals, the first computed streamed signal information including the first metrics data. The computed first streamed signal information is stored in the memory. The first computed streamed signal information is transmitted to one or more computing devices. Transmitting the first computed streamed signal information to the one or more computing devices causes the first computed streamed signal information to be displayed at the one or more computing devices.
Type:
Grant
Filed:
March 12, 2015
Date of Patent:
August 21, 2018
Assignee:
Cogito Corporation
Inventors:
Joshua Feast, Ali Azarbayejani, Skyler Place
Abstract: A method for performing natural language processing includes receiving a primary text file. The received primary text file is scanned to determine a set of statistics related to a frequency at which various words of the primary text file follow other words of the primary text file. A probabilistic word generator is created based on the determined set of statistics. The probabilistic word generator generates synthetic text exhibiting the determined set of statistics. Synthetic text exhibiting the determined set of statistics is generated using the created probabilistic word generator. Word vectorization is performed on the synthetic text. Results of the performed vectorization are used to perform machine learning tasks.
Type:
Grant
Filed:
July 24, 2015
Date of Patent:
July 17, 2018
Assignee:
INTERNATIONAL BUSINESS MACHINES CORPORATION
Abstract: Systems and methods for associating audio signals in an environment surrounding a voice-controlled system include receiving by a voice-controlled system through a microphone, an audio signal from a user of a plurality of users within an environment surrounding the microphone. The voice-controlled system determines a source location of the audio signal. The voice-controlled system determines a first user location of a first user and a second user location of a second user. The voice-controlled system then determines that the first user location correlates with the source location such that the source location and the first user location are within a predetermined distance of each other. In response, the voice-controlled system performs at least one security action associated with the first user providing the audio signal.
Abstract: A decoder that decodes DSD (Direct Stream Digital) data including: a memory storing the DSD data; a processor; a DMA (Direct Memory Access) controller configured to read the DSD data from the memory one word at a time according to a command from the processor; a parallel/serial converter configured to output a plurality of bits contained in a word read by the DMA controller in a bit stream format; and a silent pattern generator configured to selectively output a plurality of silent patterns in a time division manner during a silence period, wherein each of the plurality of silent patterns has a mark rate of 50% and is a string of bits having different values.
Abstract: A method includes acquiring a first corpus, including first text of a first sentence including a first word and described in a natural language, and second text of a second sentence including a second word different in meaning from the first word, a second word distribution of the second word being similar to a first word distribution of the first word, acquiring a second corpus including third text of a third sentence, including a third word identical to the first word and/or the second word, a third word distribution of the third word being not similar to the first word distribution, based on an arrangement of a word string in the first corpus and the second corpus, assigning to the first word a first vector representing a meaning of the first word and assigning to the second word a second vector representing a meaning of the second word.
Abstract: A method for analyzing a virtual discussion. The method may include identifying, with a processing device, a first concept relevant to a first subdiscussion associated with an online discussion. The method may also include identifying a second concept relevant to the first subdiscussion, and determining a relation between the first concept and the second concept.
Type:
Grant
Filed:
June 22, 2015
Date of Patent:
June 5, 2018
Assignee:
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventors:
Yi-Min Chee, Ashish Jagmohan, Krishna C. Ratakonda, Sara Rosenthal