Patents by Inventor Constantin Vertan
Constantin Vertan 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: 10346677Abstract: Techniques for identifying a person in a target image are described. According to one of the techniques, identifying a person in a target image involves displaying, within a graphical user interface, an image that depicts one or more faces. One or more faces are automatically detected within the image. A user provides input that selects a face of the one or more faces to be a currently-selected face. A set of images are selected from a collection of images, where the set of images includes images that closely match the currently-selected face. Concurrently with display of the currently-selected face, each image in the set of images is displayed. Within the graphical user interface, a control is provided. The control enables a user to select a target image from the set of images. In response to detecting that the user has selected a target image using the control, the currently-selected face is associated with a person to which the target image corresponds.Type: GrantFiled: September 29, 2017Date of Patent: July 9, 2019Assignee: FotoNation LimitedInventors: Eran Steinberg, Peter Corcoran, Yury Prilutsky, Petronel Bigioi, Mihai Ciuc, Stefanita Ciurel, Constantin Vertan
-
Publication number: 20180025218Abstract: Techniques for identifying a person in a target image are described. According to one of the techniques, identifying a person in a target image involves displaying, within a graphical user interface, an image that depicts one or more faces. One or more faces are automatically detected within the image. A user provides input that selects a face of the one or more faces to be a currently-selected face. A set of images are selected from a collection of images, where the set of images includes images that closely match the currently-selected face. Concurrently with display of the currently-selected face, each image in the set of images is displayed. Within the graphical user interface, a control is provided. The control enables a user to select a target image from the set of images. In response to detecting that the user has selected a target image using the control, the currently-selected face is associated with a person to which the target image corresponds.Type: ApplicationFiled: September 29, 2017Publication date: January 25, 2018Inventors: Eran STEINBERG, Peter CORCORAN, Yury PRILUTSKY, Petronel BIGIOI, Mihai CIUC, Stefanita CIUREL, Constantin VERTAN
-
Patent number: 8897504Abstract: A processor-based system operating according to digitally-embedded programming instructions performs a method including identifying a group of pixels corresponding to a face region within digital image data acquired by an image acquisition device. A set of face analysis parameter values is extracted from said face region, including a faceprint associated with the face region. First and second reference faceprints are determined for a person using reference images captured respectively in predetermined face-portrait conditions and using ambient conditions. The faceprints are analyzed to determine a baseline faceprint and a range of variability from the baseline associated with the person. Results of the analyzing are stored and used in subsequent recognition of the person in a subsequent image acquired under ambient conditions.Type: GrantFiled: July 31, 2012Date of Patent: November 25, 2014Assignee: DigitalOptics Corporation Europe LimitedInventors: Eran Steinberg, Peter Corcoran, Yury Prilutsky, Petronel Bigioi, Mihai Ciuc, Stefanita Ciurel, Constantin Vertan
-
Patent number: 8682097Abstract: A digital image processing technique is for detecting and correcting visual imperfections using a reference image. A main image and one or more reference images having a temporal and/or spatial overlap and/or proximity with the original image are captured. Device information, image data and/or meta data are analyzed of the one or more reference images relating to a defect in the main image. The device corrects the defect based on the information, image data and/or meta-data to create an enhanced version of the main image.Type: GrantFiled: June 16, 2008Date of Patent: March 25, 2014Assignee: DigitalOptics Corporation Europe LimitedInventors: Eran Steinberg, Petronel Bigioi, Adrian Zamfir, Alexandru Drimbarean, Peter Corcoran, Stefan Petrescu, Emilian David, Constantin Vertan
-
Patent number: 8553949Abstract: A processor-based system operating according to digitally-embedded programming instructions performs a method including identifying a group of pixels corresponding to a face region within digital image data acquired by an image acquisition device. A set of face analysis parameter values is extracted from said face region, including a faceprint associated with the face region. First and second reference faceprints are determined for a person using reference images captured respectively in predetermined face-portrait conditions and using ambient conditions. The faceprints are analyzed to determine a baseline faceprint and a range of variability from the baseline associated with the person. Results of the analyzing are stored and used in subsequent recognition of the person in a subsequent image acquired under ambient conditions.Type: GrantFiled: September 4, 2009Date of Patent: October 8, 2013Assignee: DigitalOptics Corporation Europe LimitedInventors: Eran Steinberg, Peter Corcoran, Yury Prilutsky, Petronel Bigioi, Mihai Ciuc, Stefanita Ciurel, Constantin Vertan
-
Patent number: 8391645Abstract: A method of automatically establishing the correct orientation of an image using facial information. This method is based on the exploitation of the inherent property of image recognition algorithms in general and face detection in particular, where the recognition is based on criteria that is highly orientation sensitive. By applying a detection algorithm to images in various orientations, or alternatively by rotating the classifiers, and comparing the number of successful faces that are detected in each orientation, one may conclude as to the most likely correct orientation. Such method can be implemented as an automated method or a semi automatic method to guide users in viewing, capturing or printing of images.Type: GrantFiled: December 19, 2011Date of Patent: March 5, 2013Assignee: DigitalOptics Corporation Europe LimitedInventors: Eran Steinberg, Yury Prilutsky, Peter Corcoran, Petronel Bigioi, Leo Blonk, Mihnea Gângea, Constantin Vertan
-
Publication number: 20130050460Abstract: A processor-based system operating according to digitally-embedded programming instructions performs a method including identifying a group of pixels corresponding to a face region within digital image data acquired by an image acquisition device. A set of face analysis parameter values is extracted from said face region, including a faceprint associated with the face region. First and second reference faceprints are determined for a person using reference images captured respectively in predetermined face-portrait conditions and using ambient conditions. The faceprints are analyzed to determine a baseline faceprint and a range of variability from the baseline associated with the person. Results of the analyzing are stored and used in subsequent recognition of the person in a subsequent image acquired under ambient conditions.Type: ApplicationFiled: July 31, 2012Publication date: February 28, 2013Inventors: Eran Steinberg, Peter Corcoran, Yury Prilutsky, Petronel Bigioi, Mihai Ciuc, Stefanita Ciurel, Constantin Vertan
-
Publication number: 20120155709Abstract: A method of automatically establishing the correct orientation of an image using facial information. This method is based on the exploitation of the inherent property of image recognition algorithms in general and face detection in particular, where the recognition is based on criteria that is highly orientation sensitive. By applying a detection algorithm to images in various orientations, or alternatively by rotating the classifiers, and comparing the number of successful faces that are detected in each orientation, one may conclude as to the most likely correct orientation. Such method can be implemented as an automated method or a semi automatic method to guide users in viewing, capturing or printing of images.Type: ApplicationFiled: December 19, 2011Publication date: June 21, 2012Applicant: DIGITALOPTICS CORPORATION EUROPE LIMITEDInventors: Eran Steinberg, Yury Prilutsky, Peter Corcoran, Petronel Bigioi, Leo Blonk, Mihnea Gângea, Constantin Vertan
-
Patent number: 8184900Abstract: A technique for detecting large and small non-red eye flash defects in an image is disclosed. The method comprises selecting pixels of the image which have a luminance above a threshold value and labeling neighboring selected pixels as luminous regions. A number of geometrical filters are applied to the luminous regions to remove false candidate luminous regions.Type: GrantFiled: August 20, 2007Date of Patent: May 22, 2012Assignee: DigitalOptics Corporation Europe LimitedInventors: Mihai Ciuc, Florin Nanu, Stefan Petrescu, Adrian Capata, Constantin Vertan, Peter Corcoran, Petronel Bigioi, Eran Steinberg
-
Patent number: 8081844Abstract: A method of automatically establishing the correct orientation of an image using facial information. This method is based on the exploitation of the inherent property of image recognition algorithms in general and face detection in particular, where the recognition is based on criteria that is highly orientation sensitive. By applying a detection algorithm to images in various orientations, or alternatively by rotating the classifiers, and comparing the number of successful faces that are detected in each orientation, one may conclude as to the most likely correct orientation. Such method can be implemented as an automated method or a semi automatic method to guide users in viewing, capturing or printing of images.Type: GrantFiled: November 18, 2010Date of Patent: December 20, 2011Assignee: DigitalOptics Corporation Europe LimitedInventors: Eran Steinberg, Yury Prilutsky, Peter Corcoran, Petronel Bigioi, Leo Blonk, Mihnea Gângea, Constantin Vertan
-
Patent number: 8073286Abstract: Flash image orb artifacts arising from specular reflections from airborne particles are corrected. A specific location is detected within a digital image of a flash image airborne particle artifact (orb). A defined curved plane shape is electronically identified within the image. Luminances are analyzed of pixels within the identified shape to assess whether the shape in fact corresponds to an orb. The digital image is corrected by removing the orb. One or more pixel values are adjusted inside the orb, and one or more edge pixel values of the orb are also adjusted.Type: GrantFiled: August 9, 2007Date of Patent: December 6, 2011Assignee: DigitalOptics Corporation Europe LimitedInventors: Emilian David, Constantin Vertan, Adrian Zamfir, Alexandru Drimbarean, Peter Corcoran, Eran Steinberg
-
Publication number: 20110064329Abstract: A method of automatically establishing the correct orientation of an image using facial information. This method is based on the exploitation of the inherent property of image recognition algorithms in general and face detection in particular, where the recognition is based on criteria that is highly orientation sensitive. By applying a detection algorithm to images in various orientations, or alternatively by rotating the classifiers, and comparing the number of successful faces that are detected in each orientation, one may conclude as to the most likely correct orientation. Such method can be implemented as an automated method or a semi automatic method to guide users in viewing, capturing or printing of images.Type: ApplicationFiled: November 18, 2010Publication date: March 17, 2011Applicant: TESSERA TECHNOLOGIES IRELAND LIMITEDInventors: Eran Steinberg, Yury Prilutsky, Peter Corcoran, Petronel Bigioi, Leo Blonk, Mihnea Gângea, Constantin Vertan
-
Patent number: 7844135Abstract: A method of automatically establishing the correct orientation of an image using facial information. This method is based on the exploitation of the inherent property of image recognition algorithms in general and face detection in particular, where the recognition is based on criteria that is highly orientation sensitive. By applying a detection algorithm to images in various orientations, or alternatively by rotating the classifiers, and comparing the number of successful faces that are detected in each orientation, one may conclude as to the most likely correct orientation. Such method can be implemented as an automated method or a semi automatic method to guide users in viewing, capturing or printing of images.Type: GrantFiled: June 10, 2009Date of Patent: November 30, 2010Assignee: Tessera Technologies Ireland LimitedInventors: Eran Steinberg, Yury Prilutsky, Peter Corcoran, Petronel Bigioi, Leo Blonk, Mihnea Gangea, Constantin Vertan
-
Publication number: 20090245693Abstract: A method of automatically establishing the correct orientation of an image using facial information. This method is based on the exploitation of the inherent property of image recognition algorithms in general and face detection in particular, where the recognition is based on criteria that is highly orientation sensitive. By applying a detection algorithm to images in various orientations, or alternatively by rotating the classifiers, and comparing the number of successful faces that are detected in each orientation, one may conclude as to the most likely correct orientation. Such method can be implemented as an automated method or a semi automatic method to guide users in viewing, capturing or printing of images.Type: ApplicationFiled: June 10, 2009Publication date: October 1, 2009Applicant: FotoNation Ireland LimitedInventors: Eran Steinberg, Yury Prilutsky, Peter Corcoran, Petronel Bigioi, Leo Blonk, Mihnea Gangea, Constantin Vertan
-
Patent number: 7565030Abstract: A method of automatically establishing the correct orientation of an image using facial information. This method is based on the exploitation of the inherent property of image recognition algorithms in general and face detection in particular, where the recognition is based on criteria that is highly orientation sensitive. By applying a detection algorithm to images in various orientations, or alternatively by rotating the classifiers, and comparing the number of successful faces that are detected in each orientation, one may conclude as to the most likely correct orientation. Such method can be implemented as an automated method or a semi automatic method to guide users in viewing, capturing or printing of images.Type: GrantFiled: December 27, 2004Date of Patent: July 21, 2009Assignee: FotoNation Vision LimitedInventors: Eran Steinberg, Yury Prilutsky, Peter Corcoran, Petronel Bigioi, Leo Blonk, Mihnea Gangea, Constantin Vertan
-
Patent number: 7551800Abstract: Flash image orb artifacts arising from specular reflections from airborne particles are corrected. An image of a scene using flash illumination and a reference image of substantially the same scene are acquired. The reference and flash images are subtracted to generate a difference image. Edge and interior region features of an orb artifact within the difference image are determined. The edge feature is matched with the interior region, and the orb artifact is corrected from the flash image based on the matching.Type: GrantFiled: August 9, 2007Date of Patent: June 23, 2009Assignee: FotoNation Vision LimitedInventors: Peter Corcoran, Eran Steinberg, Alexandru Drimbarean, Constantin Vertan, Adrian Zamfir
-
Publication number: 20080317378Abstract: A digital image processing technique is for detecting and correcting visual imperfections using a reference image. A main image and one or more reference images having a temporal and/or spatial overlap and/or proximity with the original image are captured. Device information, image data and/or meta data are analyzed of the one or more reference images relating to a defect in the main image. The device corrects the defect based on the information, image data and/or meta-data to create an enhanced version of the main image.Type: ApplicationFiled: June 16, 2008Publication date: December 25, 2008Applicant: FotoNation Ireland LimitedInventors: Eran Steinberg, Petronel Bigioi, Adrian Zamfir, Alexandru Drimbarean, Peter Corcoran, Stefan Petrescu, Emilian David, Constantin Vertan
-
Publication number: 20080075385Abstract: Flash image orb artifacts arising from specular reflections from airborne particles are corrected. A specific location is detected within a digital image of a flash image airborne particle artifact (orb). A defined curved plane shape is electronically identified within the image. Luminances are analyzed of pixels within the identified shape to assess whether the shape in fact corresponds to an orb. The digital image is corrected by removing the orb. One or more pixel values are adjusted inside the orb, and one or more edge pixel values of the orb are also adjusted.Type: ApplicationFiled: August 9, 2007Publication date: March 27, 2008Inventors: Emilian David, Constantin Vertan, Adrian Zamfir, Alexandru Drimbarean, Peter Corcoran, Eran Steinberg
-
Publication number: 20080069433Abstract: Flash image orb artifacts arising from specular reflections from airborne particles are corrected. An image of a scene using flash illumination and a reference image of substantially the same scene are acquired. The reference and flash images are subtracted to generate a difference image. Edge and interior region features of an orb artifact within the difference image are determined. The edge feature is matched with the interior region, and the orb artifact is corrected from the flash image based on the matching.Type: ApplicationFiled: August 9, 2007Publication date: March 20, 2008Inventors: Peter Corcoran, Eran Steinberg, Alexandru Drimbarean, Constantin Vertan, Adrian Zamfir
-
Publication number: 20080049970Abstract: A technique for detecting large and small non-red eye flash defects in an image is disclosed. The method comprises selecting pixels of the image which have a luminance above a threshold value and labeling neighboring selected pixels as luminous regions. A number of geometrical filters are applied to the luminous regions to remove false candidate luminous regions.Type: ApplicationFiled: August 20, 2007Publication date: February 28, 2008Applicant: FOTONATION VISION LIMITEDInventors: Mihai Ciuc, Florin Nanu, Stefan Peterscu, Adrian Capata, Constantin Vertan, Peter Corcoran, Petronel Bigioi, Eran Steinberg