专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明专利

GB2599441A System and method for recommending semantically relevant content 未知
公开(公告)号：GB2599441A
公开(公告)日：2022-04-06
申请号：GB202015695
申请日：2020-10-02
申请人： EMOTIONAL PERCEPTION AI LTD
发明人： ANGELOS PIKRAKIS , NADINE KROHER , JOE MICHAEL WILLIAM LYSKE
IPC分类号： G06F16/683 , G06F16/483 , G06F16/583 , G06F16/783
摘要： A property vector derived from extractable measurable properties of a data file is mapped to semantic properties for that data file. The property vector may be an output from a trained artificial neural network that, following pairwise training of the ANN using pairs of files that map pairwise similarity/dissimilarity in property space towards corresponding pairwise semantic similarity/dissimilarity in semantic space, both preserves and is representative of semantic properties of the data file. The system and method may assess, based on comparisons between generated property vectors, rank and then recommend and/or filter semantically close or semantically disparate candidate files in a database from a query from a user that includes the data file. Applications of the categorization and recommendation system and method apply to media or search tools and social media platforms, including media in the form of music, video, images data and/or text files.

42. 发明专利

AU2021211999A1 Automated analysis of image contents to determine the acquisition location of the image 未知
公开(公告)号：AU2021211999A1
公开(公告)日：2022-03-24
申请号：AU2021211999
申请日：2021-08-03
申请人： ZILLOW INC
发明人： MOULON PIERRE , KHOSRAVAN NAJI , LI YUGUANG , LI YUJIE , BOYADZHIEV IVAYLO
IPC分类号： G06T7/70 , G06F16/583 , G06K9/62 , G06N20/00 , G06T17/10 , G06T19/00
摘要： [0093] Techniques are described for using computing devices to perform automated operations for determining the acquisition location of an image using an analysis of the image's visual contents. In at least some situations, images to be analyzed include panorama images acquired at acquisition locations in an interior of a multi-room building, and the determined acquisition location information includes a location on a floor plan of the building and in some cases orientation direction information - in at least some such situations, the acquisition location determination is performed without having or using information from any distance-measuring devices about distances from an image's acquisition location to objects in the surrounding building. The acquisition location information may be used in various automated manners, including for controlling navigation of devices (e.g., autonomous vehicles), for display on one or more client devices in corresponding graphical user interfaces, etc. Co 0 > 00 U 0n c C T Lr) 00C CIt 'N't I C:t =n Ico VE "' V-C co L 0)Lo a) 0 U C)D U" a) E u) U) CNJ) a ) ' U)) >~ > L) LLu I - co 5 E', p )_ _ _ _

43. 发明专利

AU2020288622A1 Applying geotags to images for identifying exploration opportunities 未知
公开(公告)号：AU2020288622A1
公开(公告)日：2022-01-06
申请号：AU2020288622
申请日：2020-06-04
申请人： GEOQUEST SYSTEMS BV
发明人： FRUGIER-DORRINGTON TRACY , GARCIA JR CARLOS
IPC分类号： G06F16/587 , G01V99/00 , G06F16/583
摘要： A method includes obtaining first data representing a subterranean domain, and creating a geotag associated with a three-dimensional location of interest in the subterranean domain and a feature at the location of interest. The geotag is further associated with second data that describes the location of interest in the subterranean domain. The method also includes generating metadata describing a portion of the first data, the second data, or both, storing the geotag in a database including a plurality of geotags. The method may also include searching for an analog to the geotag.

44. 发明专利

GB2591695B Hash-based media search 未知
公开(公告)号：GB2591695B
公开(公告)日：2021-12-08
申请号：GB202105482
申请日：2014-06-24
申请人： GRASS VALLEY LTD
发明人： JONATHAN DIGGINS , GERARD PHILLIPS
IPC分类号： G06K9/00 , G06F16/583 , G06F16/783 , H04N21/235
摘要： A system for identifying video content, comprising: a query sequence processor configured to define a plurality of image sequences by a traveling window that encompasses a plurality of temporally separated video frames, the windowed frames being processed to form a spatial hash value 15, relating to differences between pixels within each image of the windowed sequence, and a temporal hash value 14, relating to differences between pixels of temporally separated frames of the windowed sequence; a database that stores the hash values in various ordered look-up tables 20, 30; and a search processor configured to search the ordered data 34, 24 for a sought hash value. The spatial and temporal hash values may comprise an entropy function and a frequency function. The relational database may comprise: an index ordered 12 first look-up table 10 of hash values and time codes 13; a second look-up table 20 ordered by one of the hash values; and a third look-up table that comprises single values for the ordering hash of the second table and a range of rows where that value of has is present in the second table.

45. 发明专利

ES2881598T3 Método mejorado para la comparación de huellas digitales y la identificación de cámara, dispositivo y sistema 未知
公开(公告)号：ES2881598T3
公开(公告)日：2021-11-30
申请号：ES15742110
申请日：2015-07-16
申请人： TORINO POLITECNICO
发明人： VALSESIA DIEGO , COLUCCIA GIULIO , BIANCHI TIZIANO , MAGLI ENRICO
IPC分类号： G06K9/00 , G06F16/583
摘要： Un método para la comparación de huellas digitales y la identificación de cámara, en donde se proporciona la lectura, a través de un dispositivo (3), de una huella digital de cámara extraída de un conjunto de imágenes, y el cálculo de una versión comprimida de dicha huella digital de cámara a través de una técnica de proyecciones aleatorias, en donde dicho método proporciona el almacenamiento en un medio de memoria (5), en particular una base de datos, versiones invariantes en escala de las huellas digitales comprimidas, siendo dichas versiones obtenidas ejecutando sucesivamente las operaciones de: - crear un patrón aleatorio correspondiente a tamaños máximos predeterminados; - redimensionar dicho patrón a las dimensiones de dicha huella digital para generar una matriz BCCB, bloque circulante con bloques circulantes, a partir de dicho patrón redimensionado, - calcular el producto de dicha matriz BCCB con dicha huella digital, - recortar un área contigua de dicho producto de tamaños predeterminados, y - almacenar en el medio de memoria (5) un conjunto de parámetros que consisten en una posición y un tamaño del área a ser recortada y un tamaño de la huella digital sin comprimir.

46. 发明专利

AU2020203091A1 Method and System for providing images of patrons at venues 未知
公开(公告)号：AU2020203091A1
公开(公告)日：2021-11-25
申请号：AU2020203091
申请日：2020-05-11
申请人： EXPERIENCEPIX PTY LTD
发明人： STEPHENS BOBBY , PRIESTLEY MICHAEL
IPC分类号： G06K9/78 , G06F16/532 , G06F16/583 , G06K9/00 , G06K9/62 , H04L9/32 , H04L29/08 , H04N1/00 , H04N5/91
摘要： Abstract A method of providing images of patrons at a venue, the method comprising: capturing images of the patrons at the venue; indexing the captured images of the patrons by an indexer based on faces of the patrons detected by a face recognition engine; receiving a query image of an individual patron; detecting a face of the individual patron in the query image by the face recognition engine; generating a unique identifier locked to the face of the individual patron; querying the indexed images by the face recognition engine based on the face of the individual patron to retrieve a personal gallery of images in which the face of the individual patron appears; providing the individual patron with access to the personal gallery of images using the unique identifier. Capture images of patrons at venue Index captured images of patrons by indexer based on faces of patrons detected by face recognition engine Receive query image of individual patron 130 Detect face of individual patron in query image by face recognition engine 140 Generate unique identifier locked to face of individual patron 150 Query indexed images by face recognition engine based on face of individual patron to retrieve personal gallery of images in which face of individual patron appears Provide individual patron with access to personal gallery of images using unique identifier 170 Figure 1

47. 发明专利

GB2553965B Managing feature data for environment mapping on an electronic device 未知
公开(公告)号：GB2553965B
公开(公告)日：2021-11-24
申请号：GB201716681
申请日：2016-08-10
申请人： GOOGLE LLC
发明人： ESHA NERURKAR , JOEL HESCH , SIMON LYNEN
IPC分类号： G06K9/00 , G06F16/583 , G06K9/46
摘要： An electronic device reduces localization data based on feature characteristics identified from the data. Based on the feature characteristics, a quality value can be assigned to each identified feature, indicating the likelihood that the data associated with the feature will be useful in mapping a local environment of the electronic device. The localization data is reduced by removing data associated with features have a low quality value, and the reduced localization data is used to map the local environment of the device by locating features identified from the reduced localization data in a frame of reference for the electronic device.

48. 发明专利

GB2556511B Displaying objects based on a plurality of models 未知
公开(公告)号：GB2556511B
公开(公告)日：2021-10-06
申请号：GB201800102
申请日：2016-10-04
申请人： GOOGLE LLC
发明人： MATIAS KONTKANEN
IPC分类号： G06T15/00 , G06F16/583 , G06K9/00 , G06T15/04 , G06T15/20 , G06T15/50 , G06T17/00
摘要： A system and method is provided for displaying surfaces of an object from a vantage point different from the vantage point from which imagery of the object was captured. In some aspects, imagery may be generated for display by combining visual characteristics from multiple source images and applying greater weight to the visual characteristics of some of the source images relative to the other source images. The weight may be based on the orientation of the surface relative to the location from which the image was captured and the location from which the object will be displayed.

49. 发明专利

GB2593637A Visual attribute determination for content selection 未知
公开(公告)号：GB2593637A
公开(公告)日：2021-09-29
申请号：GB202107890
申请日：2019-10-23
申请人： A9 COM INC
发明人： ABHIMANYU SALOKHE , MINGHUA GUO , EUSEBIUS LAI
IPC分类号： G06F16/532 , G06F16/583
摘要： Content can be located for items that are stylistically similar to an item of interest. The item of interest can be represented in a query image, which is analyzed to determine one or more regions having an item represented therein. The classification of the item is determined, enabling identification of a trained model to be used to process image data for the region(s) of the query image. The trained model outputs a set of attributes, relating to visual or stylistic attributes, and corresponding confidence or prominence values for the attributes. These attributes and values can be compared against a data repository to locate items determined to be similar based on corresponding attributes and values. A similarity determination algorithm can identify similar items and rank those items by similarity. Content for the most similar items is returned as a result for the query image.

50. 发明专利

AU2020202658B2 AUTOMATICALLY DETECTING USER-REQUESTED OBJECTS IN IMAGES 未知
公开(公告)号：AU2020202658B2
公开(公告)日：2021-09-09
申请号：AU2020202658
申请日：2020-04-21
申请人： ADOBE INC
发明人： LIN ZHE , COHEN SCOTT , LING MINGYANG
IPC分类号： G06K9/46 , G06F16/583 , G06K9/62 , G06T7/90
摘要： The present disclosure relates to an object selection system that accurately detects and optionally automatically selects user-requested objects (e.g., query objects) in digital images. For example, the object selection system builds and utilizes an object selection pipeline to determine which object detection neural network to utilize to detect a query object based on analyzing the object class of a query object. In particular, the object selection system can identify both known object classes as well as objects corresponding to unknown object classes. Identify A Query Object To Be Detected Within An Image 202 -1- "Sign" Determine If The Query Object Corresponds To A Known Object Class Object Classes "Sign"1 ? Detect The Query Object Utilizing A Known Detect The Query Object Utilizing An Object Class Neural Network 206 Unknown Object Class Neural Network 208 Region Proposal Object Classifier Region Proposal Concept Model Model Model Embedding Model Provide The Detected Query Object Within The Image 210 Mggard Fig. 2

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式