Patents by Inventor Liviu-Cristian DUTU
Liviu-Cristian DUTU has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20230419727Abstract: A method to determine activity in a sequence of successively acquired images of a scene, comprises: acquiring the sequence of images; for each image in the sequence of images, forming a feature block of features extracted from the image and determining image specific information including a weighting for the image; normalizing the determined weightings to form a normalized weighting for each image in the sequence of images; for each image in the sequence of images, combining the associated normalized weighting and associated feature block to form a weighted feature block; passing a combination of the weighted feature blocks through a predictive module to determine an activity in the sequence of images; and outputting a result comprising the determined activity in the sequence of images.Type: ApplicationFiled: August 17, 2023Publication date: December 28, 2023Inventors: Alexandru Malaescu, Dan Filip, Mihai Ciuc, Liviu-Cristian Dutu, Madalin Dumitru-Guzu
-
Patent number: 11776319Abstract: A method to determine activity in a sequence of successively acquired images of a scene, comprises: acquiring the sequence of images; for each image in the sequence of images, forming a feature block of features extracted from the image and determining image specific information including a weighting for the image; normalizing the determined weightings to form a normalized weighting for each image in the sequence of images; for each image in the sequence of images, combining the associated normalized weighting and associated feature block to form a weighted feature block; passing a combination of the weighted feature blocks through a predictive module to determine an activity in the sequence of images; and outputting a result comprising the determined activity in the sequence of images.Type: GrantFiled: July 14, 2020Date of Patent: October 3, 2023Inventors: Alexandru Malaescu, Dan Filip, Mihai Ciuc, Liviu-Cristian Dutu, Madalin Dumitru-Guzu
-
Patent number: 11727273Abstract: The technology relates to tuning a data translation block (DTB) including a generator model and a discriminator model. One or more processors may be configured to receive training data including an image in a second domain. The image in the second domain may be transformed into a first domain with a generator model. The transformed image may be processed to determine one or more outputs with one or more deep neural networks (DNNs) trained to process data in the first domain. An original objective function for the DTB may be updated based on the one or more outputs. The generator and discriminator models may be trained to satisfy the updated objective function.Type: GrantFiled: December 3, 2021Date of Patent: August 15, 2023Inventors: Alexandru Malaescu, Adrian Dorin Capata, Mihai Ciuc, Alina Sultana, Dan Filip, Liviu-Cristian Dutu
-
Patent number: 11699293Abstract: A neural network image processing apparatus arranged to acquire images from an image sensor and to: identify a ROI containing a face region in an image; determine at plurality of facial landmarks in the face region; use the facial landmarks to transform the face region within the ROI into a face region having a given pose; and use transformed landmarks within the transformed face region to identify a pair of eye regions within the transformed face region. Each identified eye region is fed to a respective first and second convolutional neural network, each network configured to produce a respective feature vector. Each feature vector is fed to respective eyelid opening level neural networks to obtain respective measures of eyelid opening for each eye region. The feature vectors are combined and to a gaze angle neural network to generate gaze yaw and pitch values substantially simultaneously with the eyelid opening values.Type: GrantFiled: February 22, 2022Date of Patent: July 11, 2023Inventors: Joseph Lemley, Liviu-Cristian Dutu, Stefan Mathe, Madalin Dumitru-Guzu, Dan Filip
-
Publication number: 20220171458Abstract: A neural network image processing apparatus arranged to acquire images from an image sensor and to: identify a ROI containing a face region in an image; determine at plurality of facial landmarks in the face region; use the facial landmarks to transform the face region within the ROI into a face region having a given pose; and use transformed landmarks within the transformed face region to identify a pair of eye regions within the transformed face region. Each identified eye region is fed to a respective first and second convolutional neural network, each network configured to produce a respective feature vector. Each feature vector is fed to respective eyelid opening level neural networks to obtain respective measures of eyelid opening for each eye region. The feature vectors are combined and to a gaze angle neural network to generate gaze yaw and pitch values substantially simultaneously with the eyelid opening values.Type: ApplicationFiled: February 22, 2022Publication date: June 2, 2022Inventors: Joseph Lemley, Liviu-Cristian Dutu, Stefan Mathe, Madalin Dumitru-Guzu, Dan Filip
-
Patent number: 11314324Abstract: A neural network image processing apparatus arranged to acquire images from an image sensor and to: identify a ROI containing a face region in an image; determine at plurality of facial landmarks in the face region; use the facial landmarks to transform the face region within the ROI into a face region having a given pose; and use transformed landmarks within the transformed face region to identify a pair of eye regions within the transformed face region. Each identified eye region is fed to a respective first and second convolutional neural network, each network configured to produce a respective feature vector. Each feature vector is fed to respective eyelid opening level neural networks to obtain respective measures of eyelid opening for each eye region. The feature vectors are combined and to a gaze angle neural network to generate gaze yaw and pitch values substantially simultaneously with the eyelid opening values.Type: GrantFiled: February 3, 2020Date of Patent: April 26, 2022Assignee: FotoNation LimitedInventors: Joseph Lemley, Liviu-Cristian Dutu, Stefan Mathe, Madalin Dumitru-Guzu, Dan Filip
-
Publication number: 20220092361Abstract: The technology relates to tuning a data translation block (DTB) including a generator model and a discriminator model. One or more processors may be configured to receive training data including an image in a second domain. The image in the second domain may be transformed into a first domain with a generator model. The transformed image may be processed to determine one or more outputs with one or more deep neural networks (DNNs) trained to process data in the first domain. An original objective function for the DTB may be updated based on the one or more outputs. The generator and discriminator models may be trained to satisfy the updated objective function.Type: ApplicationFiled: December 3, 2021Publication date: March 24, 2022Applicant: FotoNation LimitedInventors: Alexandru Malaescu, Adrian Dorin Capata, Mihai Ciuc, Alina Sultana, Dan Filip, Liviu-Cristian Dutu
-
Publication number: 20220019776Abstract: A method to determine activity in a sequence of successively acquired images of a scene, comprises: acquiring the sequence of images; for each image in the sequence of images, forming a feature block of features extracted from the image and determining image specific information including a weighting for the image; normalizing the determined weightings to form a normalized weighting for each image in the sequence of images; for each image in the sequence of images, combining the associated normalized weighting and associated feature block to form a weighted feature block; passing a combination of the weighted feature blocks through a predictive module to determine an activity in the sequence of images; and outputting a result comprising the determined activity in the sequence of images.Type: ApplicationFiled: July 14, 2020Publication date: January 20, 2022Applicant: FotoNation LimitedInventors: Alexandru MALAESCU, Dan FILIP, Mihai CIUC, Liviu-Cristian DUTU, Madalin DUMITRU-GUZU
-
Patent number: 11195056Abstract: The technology relates to tuning a data translation block (DTB) including a generator model and a discriminator model. One or more processors may be configured to receive training data including an image in a second domain. The image in the second domain may be transformed into a first domain with a generator model. The transformed image may be processed to determine one or more outputs with one or more deep neural networks (DNNs) trained to process data in the first domain. An original objective function for the DTB may be updated based on the one or more outputs. The generator and discriminator models may be trained to satisfy the updated objective function.Type: GrantFiled: March 12, 2020Date of Patent: December 7, 2021Inventors: Alexandru Malaescu, Adrian Dorin Capata, Mihai Ciuc, Alina Sultana, Dan Filip, Liviu-Cristian Dutu
-
Publication number: 20210089831Abstract: The technology relates to tuning a data translation block (DTB) including a generator model and a discriminator model. One or more processors may be configured to receive training data including an image in a second domain. The image in the second domain may be transformed into a first domain with a generator model. The transformed image may be processed to determine one or more outputs with one or more deep neural networks (DNNs) trained to process data in the first domain. An original objective function for the DTB may be updated based on the one or more outputs. The generator and discriminator models may be trained to satisfy the updated objective function.Type: ApplicationFiled: March 12, 2020Publication date: March 25, 2021Applicant: FotoNation LimitedInventors: Alexandru MALAESCU, Adrian Dorin CAPATA, Mihai CIUC, Alina SULTANA, Dan FILIP, Liviu-Cristian DUTU
-
Publication number: 20200342212Abstract: A neural network image processing apparatus arranged to acquire images from an image sensor and to: identify a ROI containing a face region in an image; determine at plurality of facial landmarks in the face region; use the facial landmarks to transform the face region within the ROI into a face region having a given pose; and use transformed landmarks within the transformed face region to identify a pair of eye regions within the transformed face region. Each identified eye region is fed to a respective first and second convolutional neural network, each network configured to produce a respective feature vector. Each feature vector is fed to respective eyelid opening level neural networks to obtain respective measures of eyelid opening for each eye region. The feature vectors are combined and to a gaze angle neural network to generate gaze yaw and pitch values substantially simultaneously with the eyelid opening values.Type: ApplicationFiled: February 3, 2020Publication date: October 29, 2020Applicant: FotoNation LimitedInventors: Joseph LEMLEY, Liviu-Cristian DUTU, Stefan MATHE, Madalin DUMITRU-GUZU, Dan FILIP
-
Patent number: 10684681Abstract: A neural network image processing apparatus arranged to acquire images from an image sensor and to: identify a ROI containing a face region in an image; determine at plurality of facial landmarks in the face region; use the facial landmarks to transform the face region within the ROI into a face region having a given pose; and use transformed landmarks within the transformed face region to identify a pair of eye regions within the transformed face region. Each identified eye region is fed to a respective first and second convolutional neural network, each network configured to produce a respective feature vector. Each feature vector is fed to respective eyelid opening level neural networks to obtain respective measures of eyelid opening for each eye region. The feature vectors are combined and to a gaze angle neural network to generate gaze yaw and pitch values substantially simultaneously with the eyelid opening values.Type: GrantFiled: June 11, 2018Date of Patent: June 16, 2020Assignee: FotoNation LimitedInventors: Joseph Lemley, Liviu-Cristian Dutu, Stefan Mathe, Madalin Dumitru-Guzu
-
Publication number: 20190377409Abstract: A neural network image processing apparatus arranged to acquire images from an image sensor and to: identify a ROI containing a face region in an image; determine at plurality of facial landmarks in the face region; use the facial landmarks to transform the face region within the ROI into a face region having a given pose; and use transformed landmarks within the transformed face region to identify a pair of eye regions within the transformed face region. Each identified eye region is fed to a respective first and second convolutional neural network, each network configured to produce a respective feature vector. Each feature vector is fed to respective eyelid opening level neural networks to obtain respective measures of eyelid opening for each eye region. The feature vectors are combined and to a gaze angle neural network to generate gaze yaw and pitch values substantially simultaneously with the eyelid opening values.Type: ApplicationFiled: June 11, 2018Publication date: December 12, 2019Applicant: FotoNation LimitedInventors: Joseph LEMLEY, Liviu-Cristian DUTU, Stefan MATHE, Madalin DUMITRU-GUZU