Abstract: An image processing device configured to detect a salient region from an image has a pixel small-region image generating unit that generates a pixel small-region image using, as a unit, a pixel small region made of pixels adjacent to one another and whose luminance values or chromaticity are similar, from the image, a prior probability calculator that calculates prior probability of likelihood of the salient region for each of the pixels of the image, a region generating unit that generates a salient-region-containing region having high possibility of containing a salient region on the basis of a corner point extracted from the image, and a likelihood calculator.

Abstract: An image processing device for identifying a characteristic of an eye from a face image comprising: a first differentiation unit configured to differentiate an eye region in at least a vertical direction of the eye to obtain a first luminance gradient; a first edge extraction unit configured to extract a first edge point according to the first luminance gradient; and a curve identification unit configured to identify a curve, which is a B-spline curve or a Bezier curve expressed by a control point and both end points and fits to the first edge point, as a curve expressing an upper-eyelid or lower-eyelid outline, the end points being an inner corner point of eye and a tail point of eye, by voting for the control point that is a voting target with respect to the first edge point using the Hough transform.

Abstract: An image processing device for identifying a characteristic of an eye from a face image comprising: a first differentiation unit configured to differentiate an eye region in a crosswise direction of the eye to obtain a first luminance gradient; a first edge extraction unit configured to extract a first and a second edge points; a voting unit configured to vote for an ellipse; a pupil outline identification unit configured to identify an ellipse expressing a pupil outline; a second differentiation unit configured to obtain a second luminance gradient by differentiating in a vertical direction; a second edge extraction unit configured to extract a third edge point; a curve identification unit configured to identify a curve that fits to the third edge point as a curve expressing an eyelid outline; and a pupil region identification unit configured to identify a pupil region based on the identified ellipse and the identified curve.

Abstract: An image processing device has a query image specification unit that specifies a query image in accordance with designation by a user, an object detection unit that detects an object in the query image, a synthetic query image generation unit that synthesizes a plurality of objects in the objects detected by the object detection unit to generate a synthetic query image including the plurality of objects, and an image retrieval unit that retrieves an image similar to the synthetic query image based on the synthetic query image.

Abstract: An image processing device for identifying a characteristic of an eye from a face image comprising: a first differentiation unit configured to differentiate an eye region in a crosswise direction of the eye to obtain a first luminance gradient; a first edge extraction unit configured to extract a first and a second edge points; a voting unit configured to vote for an ellipse; a pupil outline identification unit configured to identify an ellipse expressing a pupil outline; a second differentiation unit configured to obtain a second luminance gradient by differentiating in a vertical direction; a second edge extraction unit configured to extract a third edge point; a curve identification unit configured to identify a curve that fits to the third edge point as a curve expressing an eyelid outline; and a pupil region identification unit configured to identify a pupil region based on the identified ellipse and the identified curve.

Abstract: An image processing device for identifying a characteristic of an eye from a face image comprising: a first differentiation unit configured to differentiate an eye region in at least a vertical direction of the eye to obtain a first luminance gradient; a first edge extraction unit configured to extract a first edge point according to the first luminance gradient; and a curve identification unit configured to identify a curve, which is a B-spline curve or a Bezier curve expressed by a control point and both end points and fits to the first edge point, as a curve expressing an upper-eyelid or lower-eyelid outline, the end points being an inner corner point of eye and a tail point of eye, by voting for the control point that is a voting target with respect to the first edge point using the Hough transform.

Abstract: A gesture recognition apparatus is caused to correctly recognize start and end of a gesture without use of special unit by a natural manipulation of a user and low-load processing for the gesture recognition apparatus. The gesture recognition apparatus that recognizes the gesture from action of a recognition object taken in a moving image includes: a gravity center tracking unit that detects a specific subject having a specific feature from the moving image; a moving speed determining unit that computes a moving speed per unit time of the specific subject; a moving pattern extracting unit that extracts a moving pattern of the specific subject; and a start/end judgment unit that discriminates movement of the specific subject as an instruction (such as an instruction to start or end gesture recognition processing) input to the gesture recognition apparatus when the moving speed and the moving pattern satisfy predetermined conditions.

Abstract: An image processing method includes a segmentation step that segments an input image into a plurality of regions by using an automatic segmentation algorithm, and a computation step that calculates a saliency value of one region of the plurality of segmented regions by using a weighted sum of color differences between the one region and all other regions. Accordingly, it is possible to automatically analyze visual saliency regions in an image, and a result of analysis can be used in application areas including significant object segmentation, object recognition, adaptive image compression, content-aware image resizing, and image retrieval.

Abstract: A gesture recognition apparatus is caused to correctly recognize start and end of a gesture without use of special unit by a natural manipulation of a user and low-load processing for the gesture recognition apparatus. The gesture recognition apparatus that recognizes the gesture from action of a recognition object taken in a moving image includes: a gravity center tracking unit that detects a specific subject having a specific feature from the moving image; a moving speed determining unit that computes a moving speed per unit time of the specific subject; a moving pattern extracting unit that extracts a moving pattern of the specific subject; and a start/end judgment unit that discriminates movement of the specific subject as an instruction (such as an instruction to start or end gesture recognition processing) input to the gesture recognition apparatus when the moving speed and the moving pattern satisfy predetermined conditions.

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.