摘要:
An image sensing device collects the speech and image of a person to be sensed and carries out recognition of the collected speech. When the image sensing device determines as the recognition result that the speech represents a predetermined sentence, the image sensing device performs recognition on an acquired image. When the image sensing device determines as a recognition result that the image is a human face showing a predetermined facial expression, the image sensing device records the image and audio information.
摘要:
A situation monitoring device which enables monitoring of a variety of situations and reporting in response to the situation using a single device is provided. The situation monitoring device is easy to install and to use and a system therefore can be implemented inexpensively. The situation monitoring device recognizes a place or installation where the device is installed (step S102), holds relational information correlating the place of installation and the situation to be recognized and determines a predetermined situation to be recognized according to place of installation recognition results and the relational information (step S104), recognizes a determined predetermined situation (step S106), and reports the result of the predetermined situation to a user (step S108).
摘要:
An image sensing device is provided that collects the speech and image of a person to be sensed and carries out recognition of collected speech. When the image sensing device determines as the recognition result that the speech represents a predetermined sentence, the image sensing device performs recognition on an acquired image. When the image sensing device determines as a recognition result that the image is a human face showing a predetermined facial expression, the image sensing device records the image and audio information.
摘要:
An image including a face is input (S201), a plurality of local features are detected from the input image, a region of a face in the image is specified using the plurality of detected local features (S202), and an expression of the face is determined on the basis of differences between the detection results of the local features in the region of the face and detection results which are calculated in advance as references for respective local features in the region of the face (S204).
摘要:
An eye region is detected, in the detected eye region, the region of an iris outline is extended inward, and a hollow region surrounded by the extended region is detected as a poor hue quality region. An outline of the poor hue quality region is shaped by approximating the outline to one of a circle and an ellipse. The hue of the shaped poor hue quality region is corrected on the basis of color information obtained from a neighboring region inside an iris outline.
摘要:
At least one exemplary embodiment is directed to an imaging processing method where a plurality of images are picked up while an imaging direction of a camera is being changed. The images are combined into a composite image. A target region is specified within the composite image. An imaging direction and an imaging magnification for imaging an object included in the target region in a predetermined size are calculated based on a position and a size of the target region in the composite image and an imaging parameter set for the camera when the plurality of images are picked up. Accordingly, the imaging direction and the imaging magnification for imaging the object to be imaged can be set easily.
摘要:
An eye region is extracted from an input image. A poor pupil hue quality region is extracted from the eye region. A high brightness region is extracted from the poor pupil hue quality region. A region obtained by excluding the high brightness region from the poor pupil hue quality region is extracted as a red-eye region. The high brightness region is corrected by using a method different from that for the red-eye region.
摘要:
An eye region is detected, in the detected eye region, the region of an iris outline is extended inward, and a hollow region surrounded by the extended region is detected as a poor hue quality region. An outline of the poor hue quality region is shaped by approximating the outline to one of a circle and an ellipse. The hue of the shaped poor hue quality region is corrected on the basis of color information obtained from a neighboring region inside an iris outline.
摘要:
A plurality of kinds of feature amounts are collected from image information and voice information on a person existing in a space, valid values of the collected feature amounts are calculated, feature amounts to be used for personal recognition are determined in the collected feature amounts on the basis of the calculated valid values, and personal recognition is performed by using the determined feature amounts.
摘要:
A person area is detected from an inputted image, a category to which a person shown in the person area belongs is recognized, a correction area is extracted from the person area, and the correction area is corrected based on the recognized category. Thus, the inputted image is easily corrected in an appropriate manner according to the category of the person, that is, an object.