-
公开(公告)号：US20180204062A1
公开(公告)日：2018-07-19
申请号：US15879343
申请日：2018-01-24
申请人： HYPERVERGE INC.
发明人： Vignesh KRISHNAKUMAR , Hariprasad Prayagai SRIDHARASINGAN , Adarsh Amarendra TADIMARI , Saivenkatesh A.
CPC分类号： G06K9/4628 , G06K9/00624 , G06K9/00684 , G06K9/4609 , G06K9/4619 , G06K9/4671 , G06K9/6232 , G06K9/6277 , G06K9/66 , G06N3/0454 , G06N3/084
摘要： Efficient image processing systems and methods for image scene classification and similarity matching are disclosed. The image processing systems encompassed by this disclosure use a deep convolutional neural network to facilitate scene classification by recognizing the context of an image and thereby enabling searches for similar images. These methods and systems are scalable to a large set of images and achieve a higher performance compared to the current state of the art techniques.
-
公开(公告)号：US20240021016A1
公开(公告)日：2024-01-18
申请号：US18157047
申请日：2023-01-19
申请人： HYPERVERGE INC.
CPC分类号： G06V40/172 , G06V40/45 , G06V30/41 , G06V10/25
摘要： A system and method for authenticating an image is given. The method encompasses capturing a first image comprising at least one first human object and a second ID image; detecting at least one face of one first human object and processing the first human object based on face attribute checks, face quality checks, and face manipulation checks; performing a liveness check of the identification document to crop and align the region of interest; detecting a face of the at least one second human object; performing ID quality checks and ID tampering checks on the region of interest of the identification document; determining the image face feature vector and an ID card face feature vector; determining a match score between the image face feature vector and the ID card face feature vector and a status indicating one of authentication success, authentication failure, or a requirement for manual review of the image.
-
公开(公告)号：US20180113877A1
公开(公告)日：2018-04-26
申请号：US15791326
申请日：2017-10-23
申请人： HYPERVERGE INC.
发明人： Vignesh KRISHNAKUMAR , Awanish Raj , Sayeed Munawar Hussain , Nivedita Muthusubramanian , Sanchit Mehta , Hariprasad P S
CPC分类号： G06F16/176 , H04L12/44 , H04L2012/644 , H04W40/24 , H04W40/248
摘要： The present disclosure relates to methods and systems for sharing content, the method comprising receiving at a creator node, a selection of a first set comprising a plurality of joinee nodes, wherein each of said plurality of joinee nodes are associated with a corresponding unique identifier. The process further includes encoding the identifier associated with each of the plurality of joinee nodes in the selected first set and then transmitting the encoded identifiers to at least each of the plurality of joinee nodes in the first set. Next, the process includes receiving an acknowledgement from a subset of the first set, said subset comprising at least two joinee nodes, wherein said acknowledgement indicates a successful connection between the creator node and at least two joinee nodes in the subset. Subsequently, the method creates a network comprising the creator node and said subset and content is shared from the creator node to the subset via the created network.
-
4.发明公开公开(公告)号：US20240185635A1
公开(公告)日：2024-06-06
申请号：US18336504
申请日：2023-06-16
申请人： HYPERVERGE INC.
CPC分类号： G06V40/179 , G06V10/24 , G06V10/25 , G06V10/82 , G06V40/171 , G06V40/172
摘要： A system and method for detection of a fraudulent action using face database search and retrieval is given. The method identifies fraudulent action using a combination of images captured in real-time, feature vector extraction, and metadata matching. The method involves capturing, a query selfie image and a query ID card image. Thereafter, face feature vectors from the query images are extracted, and candidate face feature vectors are identified by searching a set of nearest neighbors of the extracted face feature vectors. The method then retrieves pre-stored application IDs associated with the candidate face feature vectors and a pre-stored metadata associated with the candidate face feature vectors. The method then matches the query metadata with the pre-stored metadata and generates either a fraudulent or non-fraudulent indication based on the matching. Thereafter it detects a fraudulent activity based on the fraudulent indication.
-
公开(公告)号：US10095950B2
公开(公告)日：2018-10-09
申请号：US15172139
申请日：2016-06-02
申请人： HYPERVERGE INC.
发明人： Vignesh Krishnakumar , Hariprasad Prayagai Sridharasingan , Adarsh Amarendra Tadimari , Saivenkatesh A
摘要： Efficient image processing systems and methods for image scene classification and similarity matching are disclosed. The image processing systems encompassed by this disclosure use a deep convolutional neural network to facilitate scene classification by recognizing the context of an image and thereby enabling searches for similar images. These methods and systems are scalable to a large set of images and achieve a higher performance compared to the current state of the art techniques.
-
公开(公告)号：US20160358024A1
公开(公告)日：2016-12-08
申请号：US15172139
申请日：2016-06-02
申请人： HYPERVERGE INC.
发明人： Vignesh KRISHNAKUMAR , Hariprasad Prayagai Sridharasingan , Adarsh Amarendra Tadimari , Saivenkatesh A
CPC分类号： G06K9/00684 , G06K9/00624 , G06K9/4609 , G06K9/4619 , G06K9/4628 , G06K9/4671 , G06K9/6232 , G06K9/6277 , G06K9/66 , G06N3/0454 , G06N3/084
摘要： Efficient image processing systems and methods for image scene classification and similarity matching are disclosed. The image processing systems encompassed by this disclosure use a deep convolutional neural network to facilitate scene classification by recognizing the context of an image and thereby enabling searches for similar images. These methods and systems are scalable to a large set of images and achieve a higher performance compared to the current state of the art techniques.
摘要翻译： 公开了用于图像场景分类和相似性匹配的高效图像处理系统和方法。 本公开所涵盖的图像处理系统使用深卷积神经网络来通过识别图像的上下文从而能够搜索类似的图像来促进场景分类。 这些方法和系统可扩展到大量图像，并且与现有技术的技术相比获得更高的性能。
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.01 秒)
