Patents by Inventor Nikos Fragoulis
Nikos Fragoulis 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).
-
Patent number: 11526753Abstract: An exemplary aspect relates to the field of pattern recognition, and in one exemplary embodiment to the field of image recognition. More specifically, an embodiment relates to the use of deep neural networks for image recognition and how these kinds of pattern classification structures may be augmented in order to become aware of the available computation time, and the available computational resources so as to appropriately adjust the computational complexity of their associated algorithms and consequently their need for computing resources. The methods and systems described herein at least enable more economical and flexible implementations for porting to embedded computing frameworks by respecting their computational resources.Type: GrantFiled: February 6, 2020Date of Patent: December 13, 2022Assignee: IRIDA LABS S.A.Inventors: Nikos Fragoulis, Ilias Theodorakopoulos
-
Publication number: 20220253711Abstract: The disclosed system incorporates a new learning module, the Learning Kernel Activation Module (LKAM), at least serving the purpose of enforcing the utilization of less convolutional kernels by learning kernel activation rules and by actually controlling the engagement of various computing elements: The exemplary module activates/deactivates a sub-set of filtering kernels, groups of kernels, or groups of full connected neurons, during the inference phase, on-the-fly for every input image depending on the input image content and the learned activation rules.Type: ApplicationFiled: April 29, 2022Publication date: August 11, 2022Inventors: Ilias THEODORAKOPOULOS, Vassileios POTHOS, Dimitris KASTANIOTIS, Nikos FRAGOULIS
-
Patent number: 11321613Abstract: The disclosed system incorporates a new learning module, the Learning Kernel Activation Module (LKAM), at least serving the purpose of enforcing the utilization of less convolutional kernels by learning kernel activation rules and by actually controlling the engagement of various computing elements: The exemplary module activates/deactivates a sub-set of filtering kernels, groups of kernels, or groups of full connected neurons, during the inference phase, on-the-fly for every input image depending on the input image content and the learned activation rules.Type: GrantFiled: November 16, 2017Date of Patent: May 3, 2022Assignee: IRIDA LABS S.A.Inventors: Ilias Theodorakopoulos, Vassileios Pothos, Dimitris Kastaniotis, Nikos Fragoulis
-
Publication number: 20220027603Abstract: An exemplary embodiment relates to the field of Automatic Face Recognition (AFR) systems. More specifically one exemplary embodiment relates at least to a method and a system capable of recognizing the face of a person using a device equipped with a camera of any kind and an associated computer, such as an embedded computer. The system is alternatively suitable to be implemented as an embedded system with minimal processing hardware capabilities, consuming very low power.Type: ApplicationFiled: October 4, 2021Publication date: January 27, 2022Inventors: Dimitris Kastaniotis, Ilias Theodorakopoulos, Nikos Fragoulis
-
Patent number: 11138413Abstract: An exemplary embodiment relates to the field of Automatic Face Recognition (AFR) systems. More specifically one exemplary embodiment relates at least to a method and a system capable of recognizing the face of a person using a device equipped with a camera of any kind and an associated computer, such as an embedded computer. The system is alternatively suitable to be implemented as an embedded system with minimal processing hardware capabilities, consuming very low power.Type: GrantFiled: December 16, 2019Date of Patent: October 5, 2021Assignee: IRIDA LABS S.A.Inventors: Dimitris Kastaniotis, Ilias Theodorakopoulos, Nikos Fragoulis
-
Publication number: 20200257977Abstract: An exemplary aspect relates to the field of pattern recognition, and in one exemplary embodiment to the field of image recognition. More specifically, an embodiment relates to the use of deep neural networks for image recognition and how these kinds of pattern classification structures may be augmented in order to become aware of the available computation time, and the available computational resources so as to appropriately adjust the computational complexity of their associated algorithms and consequently their need for computing resources. The methods and systems described herein at least enable more economical and flexible implementations for porting to embedded computing frameworks by respecting their computational resources.Type: ApplicationFiled: February 6, 2020Publication date: August 13, 2020Inventors: Nikos FRAGOULIS, Ilias THEODORAKOPOULOS
-
Publication number: 20200117886Abstract: An exemplary embodiment relates to the field of Automatic Face Recognition (AFR) systems. More specifically one exemplary embodiment relates at least to a method and a system capable of recognizing the face of a person using a device equipped with a camera of any kind and an associated computer, such as an embedded computer. The system is alternatively suitable to be implemented as an embedded system with minimal processing hardware capabilities, consuming very low power.Type: ApplicationFiled: December 16, 2019Publication date: April 16, 2020Inventors: Dimitris Kastaniotis, Ilias Theodorakopoulos, Nikos Fragoulis
-
Patent number: 10509952Abstract: An exemplary embodiment relates to the field of Automatic Face Recognition (AFR) systems. More specifically one exemplary embodiment relates at least to a method and a system capable of recognizing the face of a person using a device equipped with a camera of any kind and an associated computer, such as an embedded computer. The system is alternatively suitable to be implemented as an embedded system with minimal processing hardware capabilities, consuming very low power.Type: GrantFiled: August 25, 2017Date of Patent: December 17, 2019Assignee: IRIDA LABS S.A.Inventors: Dimitris Kastaniotis, Ilias Theodorakopoulos, Nikos Fragoulis
-
Patent number: 10185897Abstract: In the event that a moving body (e.g. a person, a car, etc.) is outfitted with a video camera or with a camera-equipped device (e.g. a tablet or a mobile phone), the system described in one aspect is able to understand the motion of the moving by analyzing the video frame sequence captured by the camera. This means that the system can categorize the motion of the body-carrying camera to one of several types (e.g., is this a person walking? is this a person running? etc.), understand the nature of the moving body holding the camera-equipped device (e.g. Is this a car?, Is this a person? etc.) and even to identify the moving body (which car?, which person? etc.).Type: GrantFiled: November 29, 2016Date of Patent: January 22, 2019Assignee: IRIDA LABS S.A.Inventors: Ilias Theodorakopoulos, Nikos Fragoulis
-
Publication number: 20180137417Abstract: The disclosed system incorporates a new learning module, the Learning Kernel Activation Module (LKAM), at least serving the purpose of enforcing the utilization of less convolutional kernels by learning kernel activation rules and by actually controlling the engagement of various computing elements: The exemplary module activates/deactivates a sub-set of filtering kernels, groups of kernels, or groups of full connected neurons, during the inference phase, on-the-fly for every input image depending on the input image content and the learned activation rules.Type: ApplicationFiled: November 16, 2017Publication date: May 17, 2018Inventors: Ilias THEODORAKOPOULOS, Vassileios POTHOS, Dimitris KASTANIOTIS, Nikos FRAGOULIS
-
Publication number: 20180060649Abstract: An exemplary embodiment relates to the field of Automatic Face Recognition (AFR) systems. More specifically one exemplary embodiment relates at least to a method and a system capable of recognizing the face of a person using a device equipped with a camera of any kind and an associated computer, such as an embedded computer. The system is alternatively suitable to be implemented as an embedded system with minimal processing hardware capabilities, consuming very low power.Type: ApplicationFiled: August 25, 2017Publication date: March 1, 2018Inventors: Dimitris Kastaniotis, Ilias Theodorakopoulos, Nikos Fragoulis
-
Publication number: 20170124418Abstract: A stand-alone computer-camera system capable of extracting car-plate information. This is achieved by using an on-board computer in order to analyze the video stream recorded by the camera sensor, and can be used with any type of camera sensor. The system features specific characteristics making it extremely fast and able to catch plates of cars moving at high-speed. The special algorithms incorporated in this system, are specially implemented, in order to be able to be ported on an embedded computer system, which has usually lower capabilities in terms of processing power and memory than a general-purpose computer.Type: ApplicationFiled: January 17, 2017Publication date: May 4, 2017Inventors: Dimitrios Besiris, Nikos Fragoulis
-
Publication number: 20170076466Abstract: In the event that a moving body (e.g. a person, a car, etc.) is outfitted with a video camera or with a camera-equipped device (e.g. a tablet or a mobile phone), the system described in one aspect is able to understand the motion of the moving by analyzing the video frame sequence captured by the camera. This means that the system can categorize the motion of the body-carrying camera to one of several types (e.g., is this a person walking? is this a person running? etc.), understand the nature of the moving body holding the camera-equipped device (e.g. Is this a car?, Is this a person? etc.) and even to identify the moving body (which car?, which person? etc.).Type: ApplicationFiled: November 29, 2016Publication date: March 16, 2017Inventors: Ilias Theodorakopoulos, Nikos Fragoulis
-
Patent number: 9547800Abstract: A stand-alone computer-camera system capable of extracting car-plate information. This is achieved by using an on-board computer in order to analyze the video stream recorded by the camera sensor, and can be used with any type of camera sensor. The system features specific characteristics making it extremely fast and able to catch plates of cars moving at high-speed. The special algorithms incorporated in this system, are specially implemented, in order to be able to be ported on an embedded computer system, which has usually lower capabilities in terms of processing power and memory than a general-purpose computer.Type: GrantFiled: July 5, 2016Date of Patent: January 17, 2017Assignee: IRIDA LABS S.A.Inventors: Dimitrios Besiris, Nikos Fragoulis
-
Patent number: 9508026Abstract: In the event that a moving body (e.g. a person, a car, etc.) is outfitted with a video camera or with a camera-equipped device (e.g. a tablet or a mobile phone), the system described in one aspect is able to understand the motion of the moving by analyzing the video frame sequence captured by the camera. This means that the system can categorize the motion of the body-carrying camera to one of several types (e.g., is this a person walking? is this a person running? etc.), understand the nature of the moving body holding the camera-equipped device (e.g. Is this a car?, Is this a person? etc.) and even to identify the moving body (which car?, which person? etc.).Type: GrantFiled: July 1, 2014Date of Patent: November 29, 2016Assignee: IRIDA LABS S.A.Inventors: Ilias Theodorakopoulos, Nikos Fragoulis
-
Publication number: 20160314368Abstract: A stand-alone computer-camera system capable of extracting car-plate information. This is achieved by using an on-board computer in order to analyze the video stream recorded by the camera sensor, and can be used with any type of camera sensor. The system features specific characteristics making it extremely fast and able to catch plates of cars moving at high-speed. The special algorithms incorporated in this system, are specially implemented, in order to be able to be ported on an embedded computer system, which has usually lower capabilities in terms of processing power and memory than a general-purpose computer.Type: ApplicationFiled: July 5, 2016Publication date: October 27, 2016Inventors: Dimitrios Besiris, Nikos Fragoulis
-
Publication number: 20160005184Abstract: In the event that a moving body (e.g. a person, a car, etc.) is outfitted with a video camera or with a camera-equipped device (e.g. a tablet or a mobile phone), the system described in one aspect is able to understand the motion of the moving by analyzing the video frame sequence captured by the camera. This means that the system can categorize the motion of the body-carrying camera to one of several types (e.g., is this a person walking? is this a person running? etc.), understand the nature of the moving body holding the camera-equipped device (e.g. Is this a car?, Is this a person? etc.) and even to identify the moving body (which car?, which person? etc.).Type: ApplicationFiled: July 1, 2014Publication date: January 7, 2016Inventors: Ilias Theodorakopoulos, Nikos Fragoulis
-
Publication number: 20150154463Abstract: A stand-alone computer-camera system capable of extracting car-plate information. This is achieved by using an on-board computer in order to analyze the video stream recorded by the camera sensor, and can be used with any type of camera sensor. The system features specific characteristics making it extremely fast and able to catch plates of cars moving at high-speed. The special algorithms incorporated in this system, are specially implemented, in order to be able to be ported on an embedded computer system, which has usually lower capabilities in terms of processing power and memory than a general-purpose computer.Type: ApplicationFiled: December 4, 2013Publication date: June 4, 2015Applicant: IRIDA LABS S.A.Inventors: Dimitrios Besiris, Nikos Fragoulis
-
Publication number: 20150030208Abstract: By collecting, analyzing and processing a series of images captured by a camera one can estimate the motion that a device containing the camera has experienced. Exemplary techniques disclosed herein at least enable device motion estimation based on any selection of images from a camera related to the device.Type: ApplicationFiled: July 29, 2013Publication date: January 29, 2015Applicant: IRIDA LABS S.A.Inventor: Nikos Fragoulis