Abstract: A watching assistance system that assists watching over a subject on a bed, the watching assistance system includes: a detector configured to detect a position of a predetermined region of the subject from the image captured by an imaging device; a determination unit configured to determine whether the subject raises oneself up based on the position at which the predetermined region of the subject is detected; and an output unit configured to provide notification when the determination unit determines that the subject raises oneself up. Based on a bed region in the image, a lying region is set to an existing range of a predetermined region at a lying time, and a raising-up region is set to an existing range of the predetermined region at a raising-up time. The lying region and the raising-up region are disposed at an interval.

Abstract: A gesture recognition apparatus detecting a gesture from an image and generating for an object device an instruction corresponding to the gesture, the gesture recognition apparatus comprises an image acquiring unit configured to acquire an image; an object part extracting unit configured to extract an object part performing a gesture; an object part shape identifying unit configured to identify a shape of the extracted object part; a representative point determining unit configured to set a representative point that is a point representing a position of the object part; a gesture recognizing unit configured to recognize a gesture, based on a motion of the representative point; and a command generating unit configured to generate an instruction corresponding to the recognized gesture, wherein the representative point determining unit determines a position of a representative point corresponding to the object part, using the identified shape of the object part.

Abstract: A method for controlling a target-image detecting device configured to detect a target image as a part of photographed images and as an image of a target object from the photographed images, includes sequentially obtaining a plurality of the photographed images that form a moving image, detecting a target image included in the obtained photographed image, generating a detection result and accumulating the generated detection result in memory as detection history, referring to the detection history of the memory and deciding whether the detection result of the target image of the same target object is included in a latest predetermined number of detection results, outputting the detection result when the detection result is included, and not outputting the detection result when the detection result is not included.

Abstract: A monitoring system for monitoring a target is described. The monitoring system extracts features of a person's face from an image obtained from the face of the person and determines whether the person's face matches a person included in a list containing facial features of multiple individuals.

Abstract: An image recognition device for recognizing respective types of display objects appearing in an image is provided, the image recognition device comprising: a change object selecting unit configured to select a change object, a target whose recognition result is to be modified, from the display objects and to determine that a type of each determined object is a type of one of recognition candidates which has the highest degree of reliability, the determined objects being not the change object; a pair object selecting unit configured to select a pair object from the determined objects, the pair object making a pair with the change object; and a recognition processing unit configured to modify the recognition result of the change object and to identify the change object, on the basis of a pair information list that indicates an object type associated with a type of the pair object.

Abstract: One aspect of the present invention provides a classifier update device that enhances accuracy of the determination made by a classifier with respect to a specific determination target. A feature quantity update unit updates a reference value of a predetermined criterion in the classifier based on target image data including a specific type of target acquired by an image acquisition unit.

Abstract: A photographing device comprises a detector configured to detect a plurality of subjects from an image photographed by a photographing part; a priority setting part configured to set a priority on each of the plurality of subjects detected by the detector using one or a plurality of pieces of photographing history information, the photographing history information including focused subject information that shows one or a plurality of focused subjects in a history image, the focused subject information being related to the history image, the history image being photographed by the photographing part in the past; a focused subject selector configured to select the subject on which a lens is focused from the plurality of subjects, in order of the priority set by the priority setting part; and a presenting part configured to present the subject selected by the focused subject selector.

Abstract: An image processing device configured to detect a detection target, which is all or a part of a predetermined main body on an image has a detection target detection unit that detects an estimated detection target that the image processing device assumes to be the detection target from the image, a heterogeneous target determination unit that determines whether the estimated detection target detected by the detection target detection unit is an estimated heterogeneous target that the image processing device assumes to be a heterogeneous target, which is all or a part of a main body different in class from the main body, and a detection target determination unit that determines whether the estimated detection target detected by the detection target detection unit is the detection target based on a determination result of the heterogeneous target determination unit.

Abstract: An attribute of image data can accurately be discriminated. An image attribute discrimination apparatus includes a heterogeneous region extracting unit that specifies a heterogeneous region from image data. The heterogeneous region includes a heterogeneous matter whose attribute is different from that of a content originally produced by the image data. An image attribute discrimination apparatus further includes a scene discrimination unit that discriminates the attribute of the image data based on a feature quantity extracted from a pixel group except each pixel in the heterogeneous region in each pixel of the image data.

Abstract: Menu-set operation controller provides an instruction for displaying a menu set, when the received manipulation instruction matches with a first manipulation. The controller provides an instruction for changing a selection state of a first-level option in the menu set, when the manipulation instruction matches with a second manipulation. The controller provides, when the manipulation instruction matches with a third manipulation, an instruction for changing a selection state of a second-level option, which is of a narrower concept than a first-level option currently selected. The controller provides an instruction for determining the second-level option, when the manipulation instruction matches with a fourth manipulation. The menu set is on the display such that a name of the first-level option indicating a function of the multimedia apparatus is displayed in a center, and a name of the second-level option, which is of the narrower concept than the first-level option is displayed.

Abstract: A gesture recognition apparatus detecting a gesture from an image and generating for an object device an instruction corresponding to the gesture, the gesture recognition apparatus comprises an image acquiring unit configured to acquire an image; an object part extracting unit configured to extract an object part performing a gesture; an object part shape identifying unit configured to identify a shape of the extracted object part; a representative point determining unit configured to set a representative point that is a point representing a position of the object part; a gesture recognizing unit configured to recognize a gesture, based on a motion of the representative point; and a command generating unit configured to generate an instruction corresponding to the recognized gesture, wherein the representative point determining unit determines a position of a representative point corresponding to the object part, using the identified shape of the object part.

Abstract: A gesture recognition apparatus detecting a gesture from an acquired image and transmitting an instruction to move a pointer in correspondence with the gesture to an object device, the gesture recognition apparatus includes an image acquiring unit configured to acquire an image; a gesture acquiring unit configured to acquire a shape of an object part performing a gesture and a motion of the object part from the acquired image; and a pointer control unit configured to generate an instruction to move a pointer in correspondence with a motion of the object part, and to output the instruction to the object device, wherein the pointer control unit determines a movement amount of the pointer based on the shape of the object part and the motion of the object part.

Abstract: An image processor has an image input section that receives image data output from an imaging unit for imaging a subject, the image data including the subject, a position information acquisition section that acquires position information indicating a current position, an object recognition section that recognizes the subject in the image data input from the image input section, and an attention object list management section that manages, for each position upon photographing, a first attention object list including first attention object data indicating an attention object candidate selected from among the subjects recognized in the image data that is previously photographed at the position upon photographing.

Abstract: A registration image including a desired target can easily be registered. A domain near an assigned position assigned by a user on a photographed image is extracted from the photographed image to generate a search image, a classifier performs the processing to the generated search image, and a processing domain having the largest number of hierarchies to which a weak classifier can perform the processing is extracted from the photographed image to generate the registration image.

Abstract: An image processor is provided, the image processor including a general-purpose classifier that detects a predetermined large classification target; and a dedicated classifier that detects a small classification target which is a subdivision of the large classification target; an image acquisition part that acquires an image photographed by a camera; an image extracting part that extracts a registered image including a user-assigned domain from the photographed image; a dedicated classifier performing part that causes the dedicated classifier to perform detection processing to the registered image extracted; a dedicated classifier selector that selects the dedicated classifier having a highest index indicating superiority or inferiority of a detection result; and a classifier generator that generates a registered image classifier to detect a target included in the registered image by replacing some weak classifiers included in the selected dedicated classifier with weak classifiers included in the general-pur

Abstract: A monitoring system configured to monitor a monitoring target, the monitoring system includes: a face feature quantity extraction unit configured to extract a person's face feature quantity from input images captured by first and second imaging devices; a matching unit configured to determine whether a person in the input image is a person of a face feature quantity list by comparing the face feature quantities, wherein a second face feature quantity list is a subset or an empty set of a first face feature quantity list, the matching unit matches the face feature quantity of the person in the input image captured by the first imaging device against each face feature quantity of the first face feature quantity list, and matches the face feature quantity of the person in the input image captured by the second imaging device against each face feature quantity of the second face feature quantity list.

Abstract: An image recognition device for recognizing respective types of display objects appearing in an image is provided, the image recognition device comprising: a change object selecting unit configured to select a change object, a target whose recognition result is to be modified, from the display objects and to determine that a type of each determined object is a type of one of recognition candidates which has the highest degree of reliability, the determined objects being not the change object; a pair object selecting unit configured to select a pair object from the determined objects, the pair object making a pair with the change object; and a recognition processing unit configured to modify the recognition result of the change object and to identify the change object, on the basis of a pair information list that indicates an object type associated with a type of the pair object.

Abstract: An image processor has an image input section that receives image data output from an imaging unit for imaging a subject, the image data including the subject, a position information acquisition section that acquires position information indicating a current position, an object recognition section that recognizes the subject in the image data input from the image input section, and an attention object list management section that manages, for each position upon photographing, a first attention object list including first attention object data indicating an attention object candidate selected from among the subjects recognized in the image data that is previously photographed at the position upon photographing.

Abstract: One aspect of the present invention provides a classifier update device that enhances accuracy of the determination made by a classifier with respect to a specific determination target. A feature quantity update unit updates a reference value of a predetermined criterion in the classifier based on target image data including a specific type of target acquired by an image acquisition unit.

Abstract: A method for controlling a target-image detecting device configured to detect a target image as a part of photographed images and as an image of a target object from the photographed images, includes sequentially obtaining a plurality of the photographed images that form a moving image, detecting a target image included in the obtained photographed image, generating a detection result and accumulating the generated detection result in memory as detection hysteresis, referring to the detection hysteresis of the memory and deciding whether the detection result of the target image of the same target object is included in a latest predetermined number of detection results, outputting the detection result when the detection result is included, and not outputting the detection result when the detection result is not included.