REDES NEURONALES

VolverVolver

Resultados 203 resultados LastUpdate Última actualización 22/02/2020 [18:35:00] pdf PDF

Solicitudes publicadas en los últimos 60 días / Applications published in the last 60 days

Página1 de 9 nextPage   por página


DEEP LEARNING TECHNIQUES FOR SUPPRESSING ARTEFACTS IN MAGNETIC RESONANCE IMAGES

NºPublicación: WO2020037121A1 20/02/2020

Solicitante:

HYPERFINE RES INC [US]
4CATALYZER CORP [US]
LAZARUS CAROLE [US]
KUNDU PRANTIK [US]
TANG SUNLI [US]
MOSHEN SALEHI SEYED SADEGH [US]
SOFKA MICHAL [US]
SCHLEMPER JO [GB]
DYVORNE HADRIEN A [US]
OHALLORAN RAFAEL [US]
SACOLICK LAURA [US]
POOLE MICHAEL STEPHEN [US]
ROTHBERG JONATHAN M [US]

US_2020058106_A1

Resumen de: WO2020037121A1

Techniques for removing artefacts, such as RF interference and/or noise, from magnetic resonance data. The techniques include: obtaining (302) input magnetic resonance data using at least one radio-frequency coil (526) of a magnetic resonance imaging system (500); and generating (306) a magnetic resonance image from the input magnetic resonance data at least in part by using a neural network model (130) to suppress (304, 308) at least one artefact in the input magnetic resonance data.

traducir

IMAGE SEGMENTATION AND OBJECT DETECTION USING FULLY CONVOLUTIONAL NEURAL NETWORK

NºPublicación: WO2020036734A2 20/02/2020

Solicitante:

12 SIGMA TECH [US]

US_2020058126_A1

Resumen de: WO2020036734A2

This disclosure relates to digital image segmentation, region of interest identification, and object recognition. This disclosure describes a method, a system, for image segmentation based on fully convolutional neural network including an expansion neural network and contraction neural network. The various convolutional and deconvolution layers of the neural networks are architected to include a coarse-to-fine residual learning module and learning paths, as well as a dense convolution module to extract auto context features and to facilitate fast, efficient, and accurate training of the neural networks capable of producing prediction masks of regions of interest. While the disclosed method and system are applicable for general image segmentation and object detection/identification, they are particularly suitable for organ, tissue, and lesion segmentation and detection in medical images.

traducir

DEEP LEARNING TECHNIQUES FOR SUPPRESSING ARTEFACTS IN MAGNETIC RESONANCE IMAGES

NºPublicación: US2020058106A1 20/02/2020

Solicitante:

LAZARUS CAROLE [US]
KUNDU PRANTIK [US]
TANG SUNLI [US]
MOSHEN SALEHI SEYED SADEGH [US]
SOFKA MICHAL [US]
SCHLEMPER JO [GB]
DYVORNE HADRIEN A [US]
OHALLORAN RAFAEL [US]
SACOLICK LAURA [US]
POOLE MICHAEL STEPHEN [US]
ROTHBERG JONATHAN M [US]

Resumen de: US2020058106A1

Techniques for removing artefacts, such as RF interference and/or noise, from magnetic resonance data. The techniques include: obtaining input magnetic resonance (MR) data using at least one radio-frequency (RF) coil of a magnetic resonance imaging (MRI) system; and generating an MR image from input MR data at least in part by using a neural network model to suppress at least one artefact in the input MR data.

traducir

SEMI-SUPERVISED TRAINING OF NEURAL NETWORKS

NºPublicación: US2020057936A1 20/02/2020

Solicitante:

GOOGLE LLC [US]

CN_109952583_A

Resumen de: US2020057936A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes obtaining a batch of labeled training items and a batch of unlabeled training items; processing the labeled training items and the unlabeled training items using the neural network and in accordance with current values of the network parameters to generate respective embeddings; determining a plurality of similarity values, each similarity value measuring a similarity between the embedding for a respective labeled training item and the embedding for a respective unlabeled training item; determining a respective roundtrip path probability for each of a plurality of roundtrip paths; and performing an iteration of a neural network training procedure to determine a first value update to the current values of the network parameters that decreases roundtrip path probabilities for incorrect roundtrip paths.

traducir

DENSE THREE-DIMENSIONAL CORRESPONDENCE ESTIMATION WITH MULTI-LEVEL METRIC LEARNING AND HIERARCHICAL MATCHING

NºPublicación: US2020058156A1 20/02/2020

Solicitante:

NEC LAB AMERICA INC [US]

Resumen de: US2020058156A1

A method for estimating dense 3D geometric correspondences between two input point clouds by employing a 3D convolutional neural network (CNN) architecture is presented. The method includes, during a training phase, transforming the two input point clouds into truncated distance function voxel grid representations, feeding the truncated distance function voxel grid representations into individual feature extraction layers with tied weights, extracting low-level features from a first feature extraction layer, extracting high-level features from a second feature extraction layer, normalizing the extracted low-level features and high-level features, and applying deep supervision of multiple contrastive losses and multiple hard negative mining modules at the first and second feature extraction layers. The method further includes, during a testing phase, employing the high-level features capturing high-level semantic information to obtain coarse matching locations, and refining the coarse matching locations with the low-level features to capture low-level geometric information for estimating precise matching locations.

traducir

Neural Network Processor

NºPublicación: US2020057942A1 20/02/2020

Solicitante:

GOOGLE LLC [US]

US_2019354862_A1

Resumen de: US2020057942A1

A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.

traducir

SYSTEM AND METHOD FOR NEURAL NETWORK ORCHESTRATION

NºPublicación: US2020058307A1 20/02/2020

Solicitante:

VERITONE INC [US]

Resumen de: US2020058307A1

Methods and systems for classifying a multimedia file using interclass data is disclosed. One of the methods includes receiving, from a first transcription engine, one or more transcription results of one or more audio segments of the multimedia file; identifying a first transcription result for a first audio segment having a low confidence of accuracy; identifying a first image data of the multimedia file corresponding to the first segment; receiving, from an image classification engine trained to classify image data, an image classification result of one or more portions of the first image data in response to requesting the image classification engine to classify the first image data; and selecting, based at least on the image classification result of the one or more portions of the first image data, a second transcription engine to re-classify the first audio segment.

traducir

Video action detection method based on convolutional neural network

NºPublicación: US2020057935A1 20/02/2020

Solicitante:

UNIV PEKING SHENZHEN GRADUATE SCHOOL [CN]

WO_2018171109_PA

Resumen de: US2020057935A1

A video action detection method based on a convolutional neural network (CNN) is disclosed in the field of computer vision recognition technologies. A temporal-spatial pyramid pooling layer is added to a network structure, which eliminates limitations on input by a network, speeds up training and detection, and improves performance of video action classification and time location. The disclosed convolutional neural network includes a convolutional layer, a common pooling layer, a temporal-spatial pyramid pooling layer and a full connection layer. The outputs of the convolutional neural network include a category classification output layer and a time localization calculation result output layer. The disclosed method does not require down-sampling to obtain video clips of different durations, but instead utilizes direct input of the whole video at once, improving efficiency. Moreover, the network is trained by using video clips of the same frequency without increasing differences within a category, thus reducing the learning burden of the network, achieving faster model convergence and better detection.

traducir

MATERIAL SELECTION AND OPTIMIZATION PROCESS FOR COMPONENT MANUFACTURING

NºPublicación: US2020055614A1 20/02/2020

Solicitante:

UNITED TECHNOLOGIES CORP [US]

EP_3611672_A1

Resumen de: US2020055614A1

A method for designing a material for an aircraft component includes training a neural network to correlate microstructural features of an alloy with material properties of the alloy by at least providing a set of images of the alloy to the neural network. Each of the images in the set of images has varied constituent compositions. The method further includes providing the neural network with a set of determined material properties corresponding to each image, associating the microstructural features of each image with the set of empirically determined data corresponding to the image, and determining non-linear relationships between the microstructural features and corresponding empirically determined material properties via a machine learning algorithm, receiving a set of desired material properties of the alloy for aircraft component, and determining a set of microstructural features capable of achieving the desired material properties of the alloy based on the determined non-linear relationships.

traducir

SPATIAL ATTENTION MODEL FOR IMAGE CAPTIONING

NºPublicación: US2020057805A1 20/02/2020

Solicitante:

SALESFORCE COM INC [US]

JP_2019537147_A

Resumen de: US2020057805A1

The technology disclosed presents a novel spatial attention model that uses current hidden state information of a decoder long short-term memory (LSTM) to guide attention and to extract spatial image features for use in image captioning. The technology disclosed also presents a novel adaptive attention model for image captioning that mixes visual information from a convolutional neural network (CNN) and linguistic information from an LSTM. At each timestep, the adaptive attention model automatically decides how heavily to rely on the image, as opposed to the linguistic model, to emit the next caption word. The technology disclosed further adds a new auxiliary sentinel gate to an LSTM architecture and produces a sentinel LSTM (Sn-LSTM). The sentinel gate produces a visual sentinel at each timestep, which is an additional representation, derived from the LSTM's memory, of long and short term visual and linguistic information.

traducir

METHOD AND APPARATUS FOR ACCELERATING DATA PROCESSING IN NEURAL NETWORK

NºPublicación: US2020057934A1 20/02/2020

Solicitante:

SEOUL NAT UNIV R&DB FOUNDATION [KR]

WO_2018199721_PA

Resumen de: US2020057934A1

Proposed are a method and apparatus for accelerating data processing in a neural network. The apparatus for accelerating data processing in a neural network may include: a control unit configured to quantize data by at least one method according to a characteristic of data calculated at a node forming at least one layer constituting the neural network, and to separately perform calculation at the node according to the quantized data; and memory configured to store the quantized data.

traducir

IMAGE SEGMENTATION AND OBJECT DETECTION USING FULLY CONVOLUTIONAL NEURAL NETWORK

NºPublicación: US2020058126A1 20/02/2020

Solicitante:

12 SIGMA TECH [US]

US_10304193_PA

Resumen de: US2020058126A1

This disclosure relates to digital image segmentation, region of interest identification, and object recognition. This disclosure describes a method, a system, for image segmentation based on fully convolutional neural network including an expansion neural network and contraction neural network. The various convolutional and deconvolution layers of the neural networks are architected to include a coarse-to-fine residual learning module and learning paths, as well as a dense convolution module to extract auto context features and to facilitate fast, efficient, and accurate training of the neural networks capable of producing prediction masks of regions of interest. While the disclosed method and system are applicable for general image segmentation and object detection/identification, they are particularly suitable for organ, tissue, and lesion segmentation and detection in medical images.

traducir

AUTOMATED ULTRASOUND VIDEO INTERPRETATION OF A BODY PART, SUCH AS A LUNG, WITH ONE OR MORE CONVOLUTIONAL NEURAL NETWORKS SUCH AS A SINGLE-SHOT-DETECTOR CONVOLUTIONAL NEURAL NETWORK

NºPublicación: US2020054306A1 20/02/2020

Solicitante:

INVENTIVE GOVERNMENT SOLUTIONS LLC [US]

Resumen de: US2020054306A1

In an embodiment, an intelligent system includes an electronic circuit configured to execute a neural network, to detect at least one feature in an image of a body portion while executing the neural network, and to determine a respective position and a respective class of each of the detected at least one feature while executing the neural network. For example, such a system can execute a neural network to detect at least one feature in an image of a lung, to determine a respective position within the image of each detected feature, and to classify each of the detected features as one of the following: A-line, B-line, pleural line, consolidation, and pleural effusion.

traducir

BIOPSY OR PAP SMEAR IMAGE PROCESSING METHOD, COMPUTER APPARATUS, AND SYSTEM

NºPublicación: WO2020034192A1 20/02/2020

Solicitante:

SUN YUNG NIEN [CN]

Resumen de: WO2020034192A1

A method, which is used for biopsy or pap smear images and which comprises: using a detection convolutional neural network to process biopsy or pap smear images so as to obtain at least one candidate organism image from among the biopsy or pap smear images; and using an identification convolutional neural network to identify the candidate organism image so as to obtain an organism identification result.

traducir

IMAGE CLASSIFICATION USING BATCH NORMALIZATION LAYERS

NºPublicación: US2020057924A1 20/02/2020

Solicitante:

GOOGLE LLC [US]

US_2020012942_A1

Resumen de: US2020057924A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images or features of images using an image classification system that includes a batch normalization layer. One of the systems includes a convolutional neural network configured to receive an input comprising an image or image features of the image and to generate a network output that includes respective scores for each object category in a set of object categories, the score for each object category representing a likelihood that that the image contains an image of an object belonging to the category, and the convolutional neural network comprising: a plurality of neural network layers, the plurality of neural network layers comprising a first convolutional neural network layer and a second neural network layer; and a batch normalization layer between the first convolutional neural network layer and the second neural network layer.

traducir

Object Location Method, Device and Storage Medium Based on Image Segmentation

NºPublicación: US2020057917A1 20/02/2020

Solicitante:

SHENZHEN DORABOT INC [CN]

CN_109102543_A

Resumen de: US2020057917A1

The invention discloses an object location method, device and storage medium based on image segmentation, the object location method comprises: collecting and labeling training images to obtain a trained database; designing a fully convolutional neural network (FCNN); training the FCNN to obtain a target neural network, by inputting the trained database into the FCNN; labeling and locating object images, based on the target neural network. The method is using the training samples collected in the application scenario to train the FCNN, so it can obtain an optimized FCNN and achieve higher robustness and segmentation accuracy. Particularly, the object segmentation method in the embodiment can perform high-precision segmentation on a plurality of overlapping envelope regions when processing envelopes in a logistics system, and an envelope on the top layer is accurate singulation, allowing the robot to grab only one envelope each time, greatly improving the accuracy and experience of logistics sorting.

traducir

APPARATUS FOR PROCESSING A NEURAL NETWORK

NºPublicación: US2020057919A1 20/02/2020

Solicitante:

FOTONATION LTD [IE]

Resumen de: US2020057919A1

An apparatus for processing a neural network comprises an image memory into which an input image is written tile-by-tile, each tile overlapping a previous tile to a limited extent; a weights memory for storing weight information for a plurality of convolutional layers of a neural network, including at least two pooling layers; and a layer processing engine configured to combine information from the image and weights memories to generate an output map and to write the output map to image memory. The apparatus is configured to store a limited number of values from adjacent a boundary of an output map for a given layer. The layer processing engine is configured to combine the output map values from a previously processed image tile with the information from the image memory and the weights when generating an output map for a layer of the neural network following the given layer.

traducir

IMAGE IDENTIFICATION APPARATUS, IMAGE IDENTIFICATION METHOD, TRAINING APPARATUS, AND NEURAL NETWORK

NºPublicación: US2020057916A1 20/02/2020

Solicitante:

CANON KK [JP]

Resumen de: US2020057916A1

There is provided with an image identification apparatus. An extraction unit extracts a feature value of an image from image data using a Neural Network (NN). A processing unit identifies the image based on the feature value extracted by the extraction unit. The NN comprises a plurality of calculation layers connected hierarchically. The NN includes a plurality of sub-neural networks for performing processing of calculation layers after a specific calculation layer. Mutually different data from an output of the specific calculation layer are respectively inputted to the plurality of sub-neural networks.

traducir

METHOD AND APPARATUS FOR DETECTING OBJECTS OF INTEREST IN IMAGES

NºPublicación: US2020057904A1 20/02/2020

Solicitante:

SIEMENS AG [DE]

CN_110235146_A

Resumen de: US2020057904A1

A method and apparatus for detecting objects of interest in images, the method comprising the steps of supplying (S1) at least one input image to a trained deep neural network, DNN, which comprises a stack of layers; and using at least one deconvolved output of at least one learned filter or combining (S2) deconvolved outputs of learned filters of at least one layer of the trained deep neural network, DNN, to detect the objects of interest in the supplied images.

traducir

NEURAL NETWORK MODEL TRAINING METHOD AND APPARATUS, FACE RECOGNITION METHOD AND APPARATUS, DEVICE, AND MEDIUM

NºPublicación: WO2020034542A1 20/02/2020

Solicitante:

PING AN TECH SHENZHEN CO LTD [CN]

CN_110197109_A

Resumen de: WO2020034542A1

A neural network model training method and apparatus, a face recognition method and apparatus, a device, and a medium, capable of effectively recognizing a face to be recognized. The neural network model training method comprises: obtaining point cloud data corresponding a face and depth image data corresponding to the face (S10); obtaining first projection data of the point cloud data in a first preset direction, and obtaining second projection data of the point cloud data in a second preset direction, the first preset direction and the second preset direction being different projection directions (S20); using the depth image data, the first projection data, and the second projection data as training data of a VGG neural network model (S30); and training the VGG neural network model by means of a training set constituted by the training data corresponding to N faces, wherein N is greater than or equal to 2 (S40), to obtain a converged VGG neural network model.

traducir

METHODS AND APPARATUS FOR HILN CHARACTERIZATION USING CONVOLUTIONAL NEURAL NETWORK

NºPublicación: EP3610240A1 19/02/2020

Solicitante:

SIEMENS HEALTHCARE DIAGNOSTICS INC [US]

CN_110573859_A

Resumen de: WO2018191287A1

A method of characterizing a serum and plasma portion of a specimen in regions occluded by one or more labels. The characterization may be used for determining Hemolysis (H), Icterus (I), and/or Lipemia (L), or Normal (N) of a serum or plasma portion of a specimen. The method includes capturing one or more images of a labeled specimen container including a serum or plasma portion, processing the one or more images with a convolutional neural network to provide a determination of Hemolysis (H), Icterus (I), and/or Lipemia (L), or Normal (N). In further embodiments, the convolutional neural network can provide N'-Class segmentation information. Quality check modules and testing apparatus adapted to carry out the method are described, as are other aspects.

traducir

Method and apparatus for recognizing a license plate of a vehicle

NºPublicación: AU2019204641A1 13/02/2020

Solicitante:

JENOPTIK TRAFFIC SOLUTIONS UK LTD [GB]

US_2020034647_A1

Resumen de: AU2019204641A1

METHOD AND APPARATUS FOR RECOGNIZING A LICENSE PLATE OF A VEHICLE The present disclosure provides an apparatus (100) for recognizing a license plate (105) of a vehicle (110), the apparatus (100) comprising an interface (140) for reading-in an image (135) of a surrounding of an optical sensor (130), the image (135) originating from the optical sensor (130) picturing at least said vehicle (110) having a detectable license plate (105). The apparatus (100) further comprises a unit (145) for analyzing the image (135) using a convolutional neural network (150), the convolutional neural network (150) having at least two separated symbol identification branches (220a, 220b), each of the separated symbol identification branches (220a, 200b) being configured for identifying one of several symbols (155) of the license plate (105) and/or the convolutional neural network (150) having a country identification branch (225) being separated from the symbol identification branches (220a, 220b), the country identification branch (225) being configured for identifying the country (160) having issued the license plate (105). Finally the apparatus (100) comprises a unit (165) for outputting (330) the at least two identified symbols (155) and/or the identified country (160) in order to recognize the license plate (105) of the vehicle (110). (Figure 1)

traducir

RECYCLING SYSTEM AND METHOD BASED ON DEEP-LEARNING AND COMPUTER VISION TECHNOLOGY

NºPublicación: US2020050922A1 13/02/2020

Solicitante:

UNIV NATIONAL CHIAO TUNG [TW]

Resumen de: US2020050922A1

A recycling system and a method based on deep-learning and computer vision technology are disclosed. The system includes a trash sorting device and a trash sorting algorithm. The trash sorting device includes a trash arraying mechanism, trash sensors, a trash transfer mechanism and a controller. The trash arraying mechanism is configured to process trash in a batch manner. The controller drives the trash arraying mechanism according to the signals of trash sensors and controls the sorting gates of the trash sorting mechanism to rotate. The trash sorting algorithm makes use of the images of trash, wherein the images are taken by cameras in different directions. The trash sorting algorithm includes a dynamic object detection algorithm, an image pre-processing algorithm, an identification module and a voting and selecting algorithm. The identification module is based on the convolutional neural networks (CNNs) and may at least identify four kinds of trash.

traducir

SYSTEMS, APPARATUS, AND METHODS FOR EMBEDDED ENCODINGS OF CONTEXTUAL INFORMATION USING A NEURAL NETWORK WITH VECTOR SPACE MODELING

NºPublicación: US2020050207A1 13/02/2020

Solicitante:

GM GLOBAL TECH OPERATIONS LLC [US]

DE_102019114577_A1

Resumen de: US2020050207A1

Systems, Apparatuses and Methods for implementing a neural network system for controlling an autonomous vehicle (AV) are provided, which includes: a neural network having a plurality of nodes with context to vector (context2vec) contextual embeddings to enable operations of the of the AV; a plurality of encoded context2vec AV words in a sequence of timing to embed data of context and behavior; a set of inputs which comprise: at least one of a current, a prior, and a subsequent encoded context2vec AV word; a neural network solution applied by the at least one computer to determine a target context2vec AV word of each set of the inputs based on the current context2vec AV word; an output vector computed by the neural network that represents the embedded distributional one-hot scheme of the input encoded context2vec AV word; and a set of behavior control operations for controlling a behavior of the AV.

traducir

Anatomical Segmentation Identifying Modes and Viewpoints with Deep Learning Across Modalities

Nº publicación: US2020051238A1 13/02/2020

Solicitante:

IBM [US]

Resumen de: US2020051238A1

A mechanism is provided in a data processing system comprising a processor and a memory, the memory comprising instructions that are executed by the processor to specifically configure the processor to implement a multi-modal classification and segmentation engine for anatomical segmentation identifying modes and viewpoints in biomedical images. The mechanism trains a neural network perform simultaneous classification and segmentation using a set of training images. The neural network provides a classification output that identifies a class label and a second output that identifies a segmentation label. The multi-modal classification and segmentation engine provides a biomedical image as the input image to the neural network. The neural network outputs a plurality of class label probabilities for a plurality of class labels and a plurality of segmentation label probabilities for each of a plurality of segmentation labels. A post-processing component executing within the multi-modal classification and segmentation engine classifies the biomedical image as an identified modality and an identified viewpoint based on the plurality of class label probabilities. The multi-modal classification and segmentation engine segments the biomedical image based on the plurality of segmentation label probabilities. The multi-modal classification and segmentation engine outputs the classified and segmented biomedical image.

traducir

Página1 de 9 nextPage por página

punteroimgVolver