Fujitsu Frontech Limited

Fujitsu Corporation

Tomoharu Suzuki

Shinichi Eguchi

Maki Yabuki

Takehiro Sekikawa

The image processing apparatus is configured by including a palm luminance estimation unit and a surface reflected component enhancement unit that separate low-frequency components from a signal indicating luminance values of pixels of an input image, a denoising processing unit that executes a denoising process for the signal from which the low-frequency components have been separated, and a merging unit that generates an image by merging the signal after the denoising process and the low-frequency components.

Image processing apparatus, image processing method, and computer-readable recording medium

A biometrics authentication device is configured so as to include: a filter that extracts a plurality of directional features from an input image; a per-direction directional feature normalization processing unit that normalizes the plurality of directional features extracted by the filter; a non-directional feature generating unit that generates a non-directional feature on the basis of the plurality of directional features output from the per-direction directional feature normalization processing unit; a matching processing unit that determines a degree of similarity between the non-directional feature and a registered non-directional feature stored in a storing unit; and a determining unit that determines identity by using the degree of similarity.

Biometrics authentication device and biometrics authentication method

A biometrics authentication device is configured to include a non-directional feature generation process unit configured to generate a non-directional feature on the basis of a directional features; a directional feature generation process unit configured to select, from among the directional features, a reference directional feature corresponding to a reference direction; a non-directional feature matching process unit configured to obtain a first degree of similarity between the non-directional feature and a registered non-directional feature; a directional feature matching process unit configured to obtain a second degree of similarity between the reference directional feature and a registered reference directional feature; and a determination unit configured to make a weight of the second degree of similarity smaller than a weight of the first degree of similarity and to determine whether or not a subject is a person to be authenticated, by using the first degree of similarity and the second degree of similarity.

A biometrics authentication device is configured to include: a filter that extracts from an input image directional features that respectively correspond to directions different from each other; an perpendicular filter that, from among the directional features extracted from the filter, decreases a luminance value of the entirety of a directional feature that corresponds to a prescribed direction, increases a luminance value of the entirety of a directional feature that corresponds to a direction perpendicular to the directional feature that corresponds to the prescribed direction, and outputs other directional features with no change; a non-directional feature generation processing unit that generates a non-directional feature on the basis of the directional features output from the perpendicular filter; a matching processing unit that obtains a similarity between the non-directional feature and a registered non-directional feature stored in a storing unit; and a determining unit that determines identity by using the similarity.

A biometrics authentication device is configured so as to include: a PLDI (Principal-Line Dependent Index) generating unit that extracts directional features that respectively correspond to directions different from each other from an image, and generates a PLDI (Principal-Line Dependent Index) indicating dependency of a principal line on the basis of the directional features; a PLDI (Principal-Line Dependent Index) matching processing unit that determines a second degree of similarity between the PLDI and a registered PLDI; and a determining unit that determines identity by using a first degree of similarity.

An authentication apparatus performs identity authentication by comparing and matching image information of a palm captured by a sensor unit with a preliminarily registered template. A surface information correcting unit corrects concavity/convexity of a palm surface for surface information that allows the concavity/convexity thereof to be evaluated. The surface information is extracted by a surface information extraction unit from the image information obtained by capturing the palm. When the surface information is not corrected by the surface information correcting unit or not used for authentication by an authentication unit even after correction, the authentication apparatus newly obtains image information of the palm. Correction by the surface information correcting unit reduces opportunities for the authentication apparatus to perform notification to guide the palm to a proper posture.

Authentication apparatus, authentication program, and authentication method

An image processing method extracts line segment elements from grayscale captured images, so that line segments are extracted at high-speed without being influenced by contrast ratio, even if morphology processing is used. A selection processing select an area where continuous line segments possibly exist from the captured image and a morphology processing detect line segment elements in the selected area by scanning an operator. Line segments can be extracted in a plurality of directions at high-speed. Also by an extraction target area selection processing, an area of which contrast ratio is low, continuing from an area of which contrast ratio is high in the line segment growth direction is also extracted as one line segment.

Image processing method and image processor

A pattern alignment method performs alignment of the comparison source pattern or the comparison target pattern that has been subjected to the angle-scale conversion with the comparison source pattern. Angular deviations and scale factors between the comparison source pattern and the comparison target pattern are computed separately, after angle and scale conversion, the measured template matching is performed. Therefore, parallel-displacement alignment can be made faster and precise alignment is possible. Template matching processing can be minimized, and aligning can be performed precisely and rapidly.

Growing community of inventors

Inagi, Japan

Tomoharu Suzuki