公开(公告)号：US12132987B2

公开(公告)日：2024-10-29

申请号：US17668881

申请日：2022-02-10

Applicant: CANON KABUSHIKI KAISHA

Inventor： Akihiko Kanda ,  Hideyuki Hamano

IPC: H04N23/67 ,  G06T7/50 ,  G06V10/772 ,  G06V10/778 ,  G06V40/10 ,  H04N23/60 ,  H04N23/667 ,  H04N23/80 ,  H04N23/959

CPC classification number: H04N23/675 ,  G06T7/50 ,  G06V10/772 ,  G06V10/7784 ,  G06V40/10 ,  H04N23/64 ,  H04N23/667 ,  H04N23/80 ,  H04N23/959 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196 ,  G06V2201/07

Abstract: An image pickup apparatus capable of setting a focus detection area to an area that a user wants to set for a detectable subject is provided. The image pickup apparatus comprising a first detecting unit configured to detect an area, which corresponds to at least a part of a subject area within an image and shows subject characteristics, as a first local area, a second detecting unit configured to detect an area, which corresponds to at least a part of the subject area and shows photographing scene characteristics, as a second local area, and a local area selecting unit configured to select one of the first local area and the second local area as an area to be focused according to information about a photographing scene of a subject in a case that both the first local area and the second local area are detected by the first detecting unit and the second detecting unit.

公开(公告)号：US12086719B2

公开(公告)日：2024-09-10

申请号：US17067194

申请日：2020-10-09

Applicant: ROYAL BANK OF CANADA

Inventor： Lei Chen ,  Jianhui Chen ,  Seyed Hossein Hajimirsadeghi ,  Gregory Mori

IPC: G06N3/084 ,  G06F18/214 ,  G06F18/22 ,  G06F18/2413 ,  G06V10/74 ,  G06V10/75 ,  G06V10/764 ,  G06V10/772 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06N3/084 ,  G06F18/214 ,  G06F18/22 ,  G06F18/24147 ,  G06V10/751 ,  G06V10/761 ,  G06V10/764 ,  G06V10/765 ,  G06V10/772 ,  G06V10/774 ,  G06V10/82

Abstract: Systems and methods of generating interpretive data associated with data sets. Embodiments of systems may be for adapting Grad-CAM methods for embedding networks. The system includes a processor and a memory. The memory stores processor-executable instructions that, when executed, configure the processor to: obtain a subject data set; generate a feature embedding based on the subject data set; determine an embedding gradient weight based on a prior-trained embedding network and the feature embedding associated with the subject data set, the prior-trained embedding network defined based on a plurality of embedding gradient weights respectively corresponding to a feature map generated based on a plurality of training samples, and wherein the embedding gradient weight is determined based on querying a feature space for the feature embedding associated with the subject data set; and generate signals for communicating interpretive data associated with the embedding gradient weight.

公开(公告)号：US20240248679A1

公开(公告)日：2024-07-25

申请号：US18461904

申请日：2023-09-06

Applicant: Private Identity LLC

Inventor： Scott Edward Streit

IPC: G06F7/02 ,  G06F18/21 ,  G06F18/213 ,  G06F21/32 ,  G06F21/55 ,  G06N3/08 ,  G06N7/01 ,  G06V10/772 ,  G06V10/774 ,  G06V10/98 ,  G06V40/12 ,  G06V40/16 ,  G06V40/40

CPC classification number: G06F7/02 ,  G06F18/213 ,  G06F18/217 ,  G06F21/32 ,  G06F21/554 ,  G06N3/08 ,  G06N7/01 ,  G06V10/772 ,  G06V10/774 ,  G06V10/993 ,  G06V40/12 ,  G06V40/16 ,  G06V40/40

Abstract: A set of measurable encrypted feature vectors can be derived from any biometric data and/or physical or logical user behavioral data, and then using an associated deep neural network (“DNN”) on the output (i.e., biometric feature vector and/or behavioral feature vectors, etc.) an authentication system can determine matches or execute searches on encrypted data. Behavioral or biometric encrypted feature vectors can be stored and/or used in conjunction with respective classifications, or in subsequent comparisons without fear of compromising the original data. In various embodiments, the original behavioral and/or biometric data is discarded responsive to generating the encrypted vectors. In other embodiment, helper networks can be used to filter identification inputs to improve the accuracy of the models that use encrypted inputs for classification.

公开(公告)号：US20240177455A1

公开(公告)日：2024-05-30

申请号：US18433265

申请日：2024-02-05

Applicant: Tesla, Inc.

Inventor： Matthew John Cooper ,  Paras Jagdish Jain ,  Harsimran Singh Sidhu

IPC: G06V10/772 ,  G06F18/213 ,  G06F18/214 ,  G06V10/774 ,  G06V20/00 ,  G06V20/56

CPC classification number: G06V10/772 ,  G06F18/213 ,  G06F18/214 ,  G06F18/2148 ,  G06V10/774 ,  G06V20/00 ,  G06V20/56

Abstract: Systems and methods for training machine models with augmented data. An example method includes identifying a set of images captured by a set of cameras while affixed to one or more image collection systems. For each image in the set of images, a training output for the image is identified. For one or more images in the set of images, an augmented image for a set of augmented images is generated. Generating an augmented image includes modifying the image with an image manipulation function that maintains camera properties of the image. The augmented training image is associated with the training output of the image. A set of parameters of the predictive computer model are trained to predict the training output based on an image training set including the images and the set of augmented images.

公开(公告)号：US20240169549A1

公开(公告)日：2024-05-23

申请号：US18424219

申请日：2024-01-26

Applicant: NVIDIA Corporation

Inventor： Dongwoo Lee ,  Junghyun Kwon ,  Sangmin Oh ,  Wenchao Zheng ,  Hae-Jong Seo ,  David Nister ,  Berta Rodriguez Hervas

IPC: G06T7/13 ,  G06T7/40 ,  G06T17/30 ,  G06V10/44 ,  G06V10/75 ,  G06V10/772 ,  G06V10/82 ,  G06V20/58

CPC classification number: G06T7/13 ,  G06T7/40 ,  G06T17/30 ,  G06V10/454 ,  G06V10/751 ,  G06V10/772 ,  G06V10/82 ,  G06V20/586 ,  G06T2207/10021 ,  G06T2207/20084 ,  G06T2207/30264

Abstract: A neural network may be used to determine corner points of a skewed polygon (e.g., as displacement values to anchor box corner points) that accurately delineate a region in an image that defines a parking space. Further, the neural network may output confidence values predicting likelihoods that corner points of an anchor box correspond to an entrance to the parking spot. The confidence values may be used to select a subset of the corner points of the anchor box and/or skewed polygon in order to define the entrance to the parking spot. A minimum aggregate distance between corner points of a skewed polygon predicted using the CNN(s) and ground truth corner points of a parking spot may be used simplify a determination as to whether an anchor box should be used as a positive sample for training.

公开(公告)号：US11972630B2

公开(公告)日：2024-04-30

申请号：US17616040

申请日：2020-06-03

Applicant: West Virginia University

Inventor： Nasser M. Nasrabadi ,  Jeremy M. Dawson ,  Ali Dabouei

IPC: G06V40/12 ,  G06V10/772 ,  G06V10/82

CPC classification number: G06V40/1347 ,  G06V10/772 ,  G06V10/82

Abstract: Various examples are provided for distortion rectification and fingerprint crossmatching. In one example, a method includes selecting an electronic, perspective distorted fingerprint sample; and generating an unwarped fingerprint sample by rectifying perspective distortions from the perspective distorted fingerprint sample by application of an unwarping transformation. Parameters of the unwarping transformation can be determined by a deep convolutional neural network (DCNN) trained on a database comprising contactless fingerprint samples suffering from perspective distortions. In another example, a system comprises processing circuitry that can: identify warp parameters associated with a contactless fingerprint sample, the warp parameters estimated from the contactless fingerprint sample by a DCNN trained on a database comprising contactless fingerprint samples suffering from perspective distortions; and generate an unwarped fingerprint sample from the contactless fingerprint sample, the unwarped fingerprint sample generated using an unwarping transformation based upon the identified warp parameters.

公开(公告)号：US11968406B2

公开(公告)日：2024-04-23

申请号：US17248795

申请日：2021-02-08

Applicant: Google LLC

Inventor： Krzysztof Potempa ,  Jyrki Alakuijala ,  Robert Obryk

IPC: H04N19/85 ,  G06F18/231 ,  G06V10/762 ,  G06V10/77 ,  G06V10/772 ,  H03M7/30 ,  H04N19/122 ,  H04N19/176 ,  H04N19/625

CPC classification number: H04N19/85 ,  G06F18/231 ,  G06V10/7625 ,  G06V10/7715 ,  G06V10/772 ,  H03M7/3088 ,  H04N19/122 ,  H04N19/176 ,  H04N19/625 ,  H03M7/3077

Abstract: An image encoder includes a processor and a memory. The memory includes instructions configured to cause the processor to perform operations. In one example implementation, the operations may include determining whether a dictionary item is available for replacing a block of an image being encoded, the determining based on a hierarchical lookup mechanism, and encoding the image along with reference information of the dictionary item in response to determining that the dictionary item is available. In one more example implementation, the operations may include performing principal component analysis (PCA) on a block to generate a corresponding projected block, the block being associated with a group of images, comparing the projected block with a corresponding threshold, descending the block recursively based on the threshold until a condition is satisfied, and identifying a left over block as a cluster upon satisfying of the condition.

公开(公告)号：US11967162B2

公开(公告)日：2024-04-23

申请号：US17935239

申请日：2022-09-26

Applicant: Fyusion, Inc.

Inventor： Chris Beall ,  Abhishek Kar ,  Stefan Johannes Josef Holzer ,  Radu Bogdan Rusu ,  Pavel Hanchar

IPC: G06V20/70 ,  G06T17/30 ,  G06T19/00 ,  G06V10/422 ,  G06V10/772 ,  G06V20/10 ,  G06V20/20 ,  G06V20/64

CPC classification number: G06V20/70 ,  G06T17/30 ,  G06T19/003 ,  G06V10/422 ,  G06V10/772 ,  G06V20/10 ,  G06V20/20 ,  G06V20/64

Abstract: A multi-view interactive digital media representation (MVIDMR) of an object can be generated from live images of an object captured from a camera. Selectable tags can be placed at locations on the object in the MVIDMR. When the selectable tags are selected, media content can be output which shows details of the object at location where the selectable tag is placed. A machine learning algorithm can be used to automatically recognize landmarks on the object in the frames of the MVIDMR and a structure from motion calculation can be used to determine 3-D positions associated with the landmarks. A 3-D skeleton associated with the object can be assembled from the 3-D positions and projected into the frames associated with the MVIDMR. The 3-D skeleton can be used to determine the selectable tag locations in the frames of the MVIDMR of the object.

公开(公告)号：US20240112447A1

公开(公告)日：2024-04-04

申请号：US17768597

申请日：2019-10-24

Applicant: NEC Corporation

Inventor： Azusa SAWADA ,  Soma SHIRAISHI ,  Takashi SHIBATA

IPC: G06V10/772 ,  G06V10/774

CPC classification number: G06V10/772 ,  G06V10/774 ,  G06V10/82

Abstract: The learning device includes a metric space learning unit and a case example storage unit. The metric space learning unit learns a metric space including feature vectors extracted from attributed image data, for each combination of different attributes, using the attributed image data to which attribute information is assigned. The case example storage unit computes the feature vector from the image data for case example to store the computed feature vector as a case example associated with the metric space, and stores additional information associated with the case example.

公开(公告)号：US20240037924A1

公开(公告)日：2024-02-01

申请号：US18039810

申请日：2021-12-01

Applicant: Merck Patent GmbH

Inventor： Helmut LINDE

IPC: G06V10/82 ,  G06V10/86 ,  G06V10/75 ,  G06V10/772

CPC classification number: G06V10/82 ,  G06V10/86 ,  G06V10/76 ,  G06V10/772 ,  G06V10/753

Abstract: A method for processing digital image recognition of invariant representations of hierarchically structured entities can be performed by a computer using an artificial neural network. The method involves learning a sparse coding dictionary on an input signal to obtain a representation of low-complexity components. Possible transformations are inferred from the statistics of the sparse representation by computing a correlation matrix. Eigenvectors of the Laplacian operator on the graph whose adjacency matrix is the correlation matrix from the previous step are computed. A coordinate transformation is performed to the base of eigenvectors of the Laplacian operator, and the first step is repeated with the next higher hierarchy level until all hierarchy levels of the invariant representations of the hierarchically structured entities are processed and the neural network is trained. The trained artificial neural network can then be used for digital image recognition of hierarchically structured entities.