公开(公告)号：AU2012253292B2

公开(公告)日：2015-10-29

申请号：AU2012253292

申请日：2012-05-11

Applicant: APPLE INC

Inventor： VALKO EDWARD ALLEN ,  WALDON MATTHEW C ,  VAN DER MERWE RUDOLPH ,  VIETA WILLIAM MATTHEW ,  HAGGERTY MYRA M ,  NELSON ALEX T ,  JENKINS KAREN LOUISE ,  SMITH SCOTT THOMAS ,  SOLEM JAN ERIK

IPC: G06F1/32

Abstract: One embodiment may take the form of a method of operating a computing device to provide presence based functionality. The method may include operating the computing device in a reduced power state and collecting a first set of data from at least one sensor. Based on the first set of data, the computing device determines a probability that an object is within a threshold distance of the computing device and, if the object is within the threshold distance, the device activates at least one secondary sensor to collect a second set of data. Based on the second set of data, the device determines if the object is a person. If the object is a person, the device determines a position of the person relative to the computing device and executes a change of state in the computing device based on the position of the person relative to the computing device. If the object is not a person, the computing device remains in a reduced power state.

公开(公告)号：CA2789887C

公开(公告)日：2015-11-17

申请号：CA2789887

申请日：2012-09-17

Applicant: APPLE INC

Inventor： SOLEM JAN ERIK ,  ROUSSON MICHAEL

IPC: G06K9/46

Abstract: Systems, methods, and computer readable media for determining and applying face recognition parameter sets are described. In general, techniques are disclosed for identifying and constructing a unique combination of facial recognition discriminators into a "face feature vector" that has been found to be more robust (e.g., stable to image noise, a person's pose, and scene illumination) and accurate (e.g., provide high recognition rates) than prior art techniques. More particularly, a face feature vector may be generated by the combination of shape descriptors (e.g., as generated by two-dimensional and three-dimensional shape models) and texture descriptors (e.g., as generated by global and local texture models).

公开(公告)号：AU2012227166B2

公开(公告)日：2014-05-22

申请号：AU2012227166

申请日：2012-09-18

Applicant: APPLE INC

Inventor： SOLEM JAN ERIK ,  ROUSSON MICHAEL

IPC: G06K9/46 ,  G06T7/00

Abstract: FACE FEATURE VECTOR CONSTRUCTION Abstract Systems, methods, and computer readable media for determining and applying face recognition parameter sets are described. In general, techniques are disclosed for identifying and constructing a unique combination of facial recognition discriminators into a "face feature vector" that has been found to be more robust (e.g., stable to image noise, a person's pose, and scene illumination) and accurate (e.g., provide high recognition rates) than prior art techniques. More particularly, a face feature vector may be generated by the combination of shape descriptors (e.g., as generated by two-dimensional and three-dimensional shape models) and texture descriptors (e.g., as generated by global and local texture models). 2D SHAPE DESC. 210 3D SHAPE DESC. 215 GLOBAL | GLOBAL TEXTURE DESC. 230 TEXTURE MODEL LOCAL LOCAL TEXTURE DESC. TEXTURE MODEL ' 235 FACE FEATURE

公开(公告)号：AU2012227166A1

公开(公告)日：2013-07-04

申请号：AU2012227166

申请日：2012-09-18

Applicant: APPLE INC

Inventor： SOLEM JAN ERIK ,  ROUSSON MICHAEL

IPC: G06K9/46 ,  G06T7/00

Abstract: FACE FEATURE VECTOR CONSTRUCTION Abstract Systems, methods, and computer readable media for determining and applying face recognition parameter sets are described. In general, techniques are disclosed for identifying and constructing a unique combination of facial recognition discriminators into a "face feature vector" that has been found to be more robust (e.g., stable to image noise, a person's pose, and scene illumination) and accurate (e.g., provide high recognition rates) than prior art techniques. More particularly, a face feature vector may be generated by the combination of shape descriptors (e.g., as generated by two-dimensional and three-dimensional shape models) and texture descriptors (e.g., as generated by global and local texture models). 2D SHAPE DESC. 210 3D SHAPE DESC. 215 GLOBAL | GLOBAL TEXTURE DESC. 230 TEXTURE MODEL LOCAL LOCAL TEXTURE DESC. TEXTURE MODEL ' 235 FACE FEATURE

公开(公告)号：AT551664T

公开(公告)日：2012-04-15

申请号：AT05771849

申请日：2005-08-11

Applicant: APPLE INC

Inventor： SOLEM JAN ERIK ,  KAHL FREDRIK

IPC: G06K9/00 ,  G06K9/64 ,  G06T20060101 ,  G06T15/00

Abstract: The method involves obtaining a two dimensional (2D) representation of an object, and detecting image features in the obtained 2D representation. A highly probable three dimensional (3D) shape of a certain object class consistent with 2D images is recovered using the obtained image. The recovered 3D shape is compared with a reference representation of the object of the object class. Independent claims are also included for the following: (A) a computer program stored in a computer readable storage medium and executed in a computational unit for object recognition of a three dimensional (3D) object (B) a system for object recognition of a three dimensional (3D) object.

公开(公告)号：AU2012253292A1

公开(公告)日：2013-10-31

申请号：AU2012253292

申请日：2012-05-11

Applicant: APPLE INC

Inventor： VALKO EDWARD ALLEN ,  WALDON MATTHEW C ,  VAN DER MERWE RUDOLPH ,  VIETA WILLIAM MATTHEW ,  HAGGERTY MYRA M ,  NELSON ALEX T ,  JENKINS KAREN LOUISE ,  SMITH SCOTT THOMAS ,  SOLEM JAN ERIK

IPC: G06F1/32

Abstract: One embodiment may take the form of a method of operating a computing device to provide presence based functionality. The method may include operating the computing device in a reduced power state and collecting a first set of data from at least one sensor. Based on the first set of data, the computing device determines a probability that an object is within a threshold distance of the computing device and, if the object is within the threshold distance, the device activates at least one secondary sensor to collect a second set of data. Based on the second set of data, the device determines if the object is a person. If the object is a person, the device determines a position of the person relative to the computing device and executes a change of state in the computing device based on the position of the person relative to the computing device. If the object is not a person, the computing device remains in a reduced power state.

公开(公告)号：CA2789887A1

公开(公告)日：2013-06-20

申请号：CA2789887

申请日：2012-09-17

Applicant: APPLE INC

Inventor： SOLEM JAN ERIK ,  ROUSSON MICHAEL

IPC: G06K9/46

Abstract: Systems, methods, and computer readable media for determining and applying face recognition parameter sets are described. In general, techniques are disclosed for identifying and constructing a unique combination of facial recognition discriminators into a "face feature vector" that has been found to be more robust (e.g., stable to image noise, a person's pose, and scene illumination) and accurate (e.g., provide high recognition rates) than prior art techniques. More particularly, a face feature vector may be generated by the combination of shape descriptors (e.g., as generated by two-dimensional and three-dimensional shape models) and texture descriptors (e.g., as generated by global and local texture models).

公开(公告)号：ES2385041T3

公开(公告)日：2012-07-17

申请号：ES05771849

申请日：2005-08-11

Applicant: POLAR ROSE AB ,  APPLE INC

Inventor： SOLEM JAN ERIK ,  KAHL FREDRIK

IPC: G06K9/00 ,  G06K9/64 ,  G06T20060101 ,  G06T15/00

Abstract: Un procedimiento para reconocimiento de objetos de un objeto tridimensional (307), 3D, que comprende lasetapas de:- obtener al menos una representación bidimensional (606), 2D, de dicho objeto;- detectar características de imagen en dicha representación 2D (606) obtenida;- inferir una forma 3D dispersa correspondiente a las características de imagen utilizando unarepresentración vectorial latente de dicha forma 3D dispersa y utilizando un modelo de formaestadístico multi-perspectiva.caracterizado por comprender además las etapas de- extender la forma 3D dispersa a una forma 3D densa encajando la superficie a dicha forma 3Ddispersa utilizando un modelo de forma estadístico aprendido que consiste en una superficie mediacompleta del objeto para regularizar dicha forma de superficie de forma específica para una clasede objetos;- comparar la forma 3D densa con formas 3D de referencia (605) obtenidas previamente; y por lotanto- identificar un objeto individual de la clase de objetos.

公开(公告)号：WO2014004536A3

公开(公告)日：2014-08-21

申请号：PCT/US2013047659

申请日：2013-06-25

Applicant: APPLE INC

Inventor： SOLEM JAN ERIK ,  STALENHOEF THIJS WILLEM

IPC: G06F17/30

CPC classification number: G10L15/265 ,  G06F17/30268

Abstract: The electronic device with one or more processors and memory provides a digital photograph of a real-world scene. The electronic device provides a natural language text string corresponding to a speech input associated with the digital photograph. The electronic device performs natural language processing on the text string to identify one or more terms associated with an entity, an activity, or a location. The electronic device tags the digital photograph with the one or more terms and their associated entity, activity, or location.

Abstract translation: 具有一个或多个处理器和存储器的电子设备提供真实世界场景的数字照片。 电子设备提供对应于与数字照片相关联的语音输入的自然语言文本串。 电子设备对文本串执行自然语言处理以识别与实体，活动或位置相关联的一个或多个词语。 电子设备用数字照片标记一个或多个词语及其相关的实体，活动或位置。