专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明专利

BR102019023679A2 método de projeção de crescimento humano para análise de compatibilidade de tamanho de vestimentas e afins 未知
公开(公告)号：BR102019023679A2
公开(公告)日：2021-05-25
申请号：BR102019023679
申请日：2019-11-11
申请人： ROGERIO BOCUZZI MACORIN
发明人： ROGERIO MACORIN
IPC分类号： G06K9/00 , G06F16/583 , G06F16/9535
摘要： método de projeção de crescimento humano para análise de compatibilidade de tamanho de vestimentas e afins. a presente invenção descreve um método de projeção do crescimento humano baseado em curvas de crescimento que visam auxiliar a compatibilizar tamanhos de vestimentas com o tamanho do corpo de cada pessoa durante a fase de crescimento. dada a velocidade com que bebês e crianças perdem suas roupas por conta do acelerado crescimento, o presente modelo visa criar bases de projeção das principais medidas do corpo humano que implicam no caimento e conforto de vestimentas. com tais projeções é possível determinar, com certo grau de precisão a depender do modelo estatístico empregado, qual tamanho de vestimenta servirá para a criança ou bebê, quando servirá e até mesmo por quanto tempo, auxiliando na previsão das compras ou até confecção, não apenas no que diz respeito a quando será necessário comprar (por conta das vestimentas atuais deixarem de servir), como também ajustar os tamanhos com as estações do ano, ou seja, saber qual tamanho de casaco servirá no próximo inverno, e por quantos invernos servirá, balizando assim a utilidade da peça, o que influencia na decisão de quanto vale pagar por ela. o presente modelo é aplicável também para outros segmentos do mercado que não o de vestuário, tais como, mas não se limitando, a equipamentos ortopédicos, dispositivos de internet das coisas (iot), entre outros que possam necessitar a verificação da compatibilidade com o tamanho do corpo humano.

32. 发明专利

IL259766A Relocalization systems and methods 未知
公开(公告)号：IL259766A
公开(公告)日：2021-03-25
申请号：IL25976618
申请日：2018-06-03
申请人： MAGIC LEAP INC
IPC分类号： G06F16/58 , G06F16/583 , G06K9/00 , G06K9/20 , G06K9/52 , G06K9/60 , G06K9/62 , G06K9/66 , G06K9/70 , G06N3/04 , G06N3/08 , G06T7/70 , G06T7/73 , G06T7/80
摘要： A method of determining a pose of an image capture device includes capturing an image using an image capture device. The method also includes generating a data structure corresponding to the captured image. The method further includes comparing the data structure with a plurality of known data structures to identify a most similar known data structure. Moreover, the method includes reading metadata corresponding to the most similar known data structure to determine a pose of the image capture device.

33. 发明专利

BR112019025409A2 identificação de vídeos com conteúdo inapropriado por processamento de registros de pesquisa 未知
公开(公告)号：BR112019025409A2
公开(公告)日：2020-06-16
申请号：BR112019025409
申请日：2018-09-14
申请人： GOOGLE LLC
发明人： SCOTT PETERSON
IPC分类号： G06F16/583
摘要： a presente invenção refere-se a um método para classificar o conteúdo da mídia. o método inclui identificação, por um dispositivo de processamento, uma pluralidade de resultados de pesquisa correspondentes a uma solicitação de pesquisa, a pluralidade de resultados de pesquisa correspondentes a uma pluralidade de itens de mídia; identificação, pelo dispositivo de processamento, de pelo menos um primeiro item de mídia e um segundo item de mídia da pluralidade de itens de mídia, o primeiro item de mídia sendo associado a um primeiro rótulo de conteúdo, o segundo item de mídia sendo associado a um segundo rótulo de conteúdo; determinar, com base, pelo menos em parte, na primeira interação do usuário com o primeiro item de mídia, se a solicitação de pesquisa representa uma demanda de conteúdo de mídia associado ao primeiro rótulo de conteúdo; e em resposta à determinação de que a solicitação de pesquisa representa a demanda de conteúdo de mídia associado ao primeiro rótulo de conteúdo, associando, pelo dispositivo de processamento, o segundo item de mídia ao primeiro rótulo de conteúdo.

34. 发明专利

GB2544853B Structured knowledge modeling and extraction from images 未知
公开(公告)号：GB2544853B
公开(公告)日：2020-01-01
申请号：GB201615371
申请日：2016-09-09
申请人： ADOBE INC
发明人： SCOTT D COHEN , WALTER WEI-TUH CHANG , BRIAN L PRICE , MOHAMMED HAMDY MAHMOUD ABDELBAKY ELHOSEINY
IPC分类号： G06K9/00 , G06F16/583
摘要： Techniques and systems are described to model and extract knowledge from images. A digital medium environment is configured to learn and use a model to compute a descriptive summarization of an input image automatically and without user intervention. Training data is obtained to train a model using machine learning in order to generate a structured image representation that serves as the descriptive summarization of an input image. The images and associated text are processed to extract structured semantic knowledge from the text, which is then associated with the images. The structured semantic knowledge is processed along with corresponding images to train a model using machine learning such that the model describes a relationship between text features within the structured semantic knowledge. Once the model is learned, the model is usable to process input images to generate a structured image representation of the image. An image search could also be carried out using the structured image representation. The structured knowledge may be in the form of tuples such as .

35. 发明专利

GB2573849A Utilizing a deep neural network-based model to identify visually similar digital images based on user-selected visual attributes 未知
公开(公告)号：GB2573849A
公开(公告)日：2019-11-20
申请号：GB201901759
申请日：2019-02-08
申请人： ADOBE INC
发明人： ZHE LIN , XIAOHUI SHEN , MINGYANG LING , JIANMING ZHANG , JASON KUEN , BRETT BUTTERFIELD
IPC分类号： G06F16/532 , G06F16/583
摘要： A computer readable medium for matching digital images based on visual similarity comprises instructions that cause a computer device to receive, from a user client device, a user selection of a query digital image and at least one of spatial selectivity, image composition, or object count to use to identify similar digital images, utilise a deep neural network-based model to generate a set of deep features for the query digital image, generate, based on the set of deep features of the query digital image and in accordance with the user selection, a deep neural network-based representation of the query digital image by utilising one or more of a spatial selectivity algorithm, an image composition algorithm, or an object count algorithm, and based on the deep neural network-based representation of the query digital image, identify, from a digital image database, a similar digital image for the query digital image, for example by determining similarity scores and ranking the images in the database. An image mask may be received by the user, which indicates a portion of the query image to emphasise in identifying similar images, by weighting the portion of the query image indicated by the mask.

36. 发明专利

AU2021211999B2 Automated analysis of image contents to determine the acquisition location of the image 未知
公开(公告)号：AU2021211999B2
公开(公告)日：2023-01-12
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 , 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 )_ _ _ _

37. 发明专利

CA3050456C FACIAL MODELLING AND MATCHING SYSTEMS AND METHODS 未知
公开(公告)号：CA3050456C
公开(公告)日：2023-01-03
申请号：CA3050456
申请日：2019-07-22
申请人： ALRASHEED SULTAN A
发明人： ALRASHEED SULTAN A , ATABANI YASIR OSAMA
IPC分类号： G06V40/16 , G06F16/583
摘要： A matching apparatus for characterising the human face in order to facilitate the search for people with similar faces. The apparatus uses 3D modelling of a variety of image sources including video to characterise a subject's face using a set of parameters. These parameters are then used to identify other people or image sources which have a set of parameters which are similar to the subject's. Feedback from the users is used to improve future matching.

38. 发明专利

AU2020215098B2 Method and device for detecting and adjusting decorative colour formulations in alignment with the visual perception of texture characteristics 未知
公开(公告)号：AU2020215098B2
公开(公告)日：2022-12-08
申请号：AU2020215098
申请日：2020-01-30
申请人： BASF COATINGS GMBH
发明人： BISCHOFF GUIDO
IPC分类号： G01J3/46 , G01J3/50 , G01N21/25 , G01N21/47 , G06F16/583 , G06T7/00 , G06T7/40
摘要： The invention relates to a computer-implemented method comprising at least the following steps: receiving (10) at least one image or a plurality of images, wherein, using an image-capturing unit, the at least one image is captured with a determined measurement geometry or each image of the plurality of images is captured with another measurement geometry on a surface of a target coating; carrying out (12) an image analysis for each of the obtained images, using at least one processor which is configured to execute at least one filtering technique; identifying (14) at least one sparkle point within a respective image; carrying out a characteristic analysis of the at least one identified sparkle point in the respective image in terms of at least one predefined size characteristic, using the at least one processor; determining (16) at least one value for the at least one predefined size characteristic for the at least one sparkle point; calculating (18) a size distribution for the respective image on the basis of the determined value for the at least one predefined size characteristic using the processor; providing (26) a formulation for a coating, which is the same as or at least similar to the target coating in appearance, taking into consideration the calculated size distribution and using the processor.

39. 发明专利

NL2027933B1 COMPREHENSIVE IDENTIFICATION AND TREATMENT METHOD FOR CROP DISEASES 未知
公开(公告)号：NL2027933B1
公开(公告)日：2022-10-20
申请号：NL2027933
申请日：2021-04-07
申请人： UNIV ZHENGZHOU LIGHT IND
发明人： YONGQUAN XIA , ZUHE LI , QIUWEN ZHANG , ERLIN TIAN , WEI HUANG
IPC分类号： G06F16/583 , G06F16/953 , G06T17/00
摘要： The invention discloses a comprehensive identiﬁcation and treatment method for crop diseases, which comprises the following steps: constructing an input sample set and a multi-source comparison library, integrating color texture description, 5 screening the input sample set, fusing model modelling, extracting color texture features, comprehensively analyzing and comparing color textures and determining specific diseases and insect pests and their locations, The method comprise that following step as follows: acquiring crop leaf image samples in the target range to form an input sample set, and numbering disease and insect pests color texture of 10 corresponding target crops by utilizing an external data source, Establishing a multi- source comparison library and establishing a visual model of an input sample set; The Path and Row numerical vectorization models corresponding to the images are constructed, the color texture features are extracted, and then compared with the multi-source comparison library. When the color textures coincide, the voice playing 15 module will play the speciﬁc description of diseases and insect pests for the color textures, thus accurately identifying crop diseases, which is more accurate than manual identification.

40. 发明专利

DK3311337T3 FREMGANGSMÅDER OG EN COMPUTERINDRETNING TIL BESTEMMELSE AF ÆGTHEDEN AF ET MÆRKE 未知
公开(公告)号：DK3311337T3
公开(公告)日：2022-05-30
申请号：DK16812194
申请日：2016-06-13
申请人： SYS TECH SOLUTIONS INC
发明人： VOIGT MATTHIAS , SOBORSKI MICHAEL L , AYOUB RAFIK
IPC分类号： G06F16/532 , G06F16/583

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