GSDT Fintech Group Inc. (GSDT)

[investor911]

SUMMARY OF EVRM INVENTION:

One aspect of the present invention is to provides a method of detecting an outer boundary of an iris from an image of an eye. The method comprises: providing data representing an image of an eye comprising an image of the iris of the eye, the iris image being substantially annular and defined between inner and outer boundaries, the eye image comprising a plurality of pixels, the eye image data comprising location information and image information for each pixel of the eye image; providing location information of the inner boundary of the iris image; comparing the image information of a pixel on the inner boundary with the image information of pixels of the eye image; and determining a pixel is on the outer boundary of the iris image when a difference between the image information of that pixel and the image information of the pixel on the inner boundary becomes a maximum among differences of the image information. In the above-described method, the location information of the inner boundary is obtained with use of a Canny edge detection method.

Another aspect of the present invention provides a method of obtaining an iris pattern. The method comprises: providing an image of an iris of an eye, the iris image being substantially annular and defined between inner and outer boundaries; obtaining data of a substantial portion, but not all, of the iris image; and processing the data of the substantial portion to obtain an iris pattern. In the above-described method, the data comprises positional information and image information of a point within the portion. The substantial portion of the iris image is from about 25% to about 95% of an area of the iris image. The substantial portion of the iris image is from about 40% to about 85% of an area of the iris image. The substantial portion of the iris image is from about 50% to about 75% of an area of the iris image. The substantial portion of the iris image is from about 55% to about 65% of an area of the iris image. The substantial portion of the iris image is substantially annular. The substantial portion is annular and defined from the inner boundary to an imaginary closed line between the inner and outer boundaries. The imaginary closed line is substantially parallel to the inner boundary.

Still in the above-described method, a tangent at a point on the inner boundary is substantially parallel to a tangent at a point on the imaginary line that is on a line perpendicular to the tangent at the point on the inner boundary. The substantial portion is annular and defined from an imaginary closed line between the inner and outer boundaries to the outer boundary. The imaginary closed line is substantially parallel to the outer boundary. The substantial portion is annular and defined between a first imaginary closed line and a second imaginary closed line, wherein the first imaginary line is drawn between the inner and outer boundaries, and wherein the second imaginary line is drawn between the first imaginary line and the outer boundary. The first and second lines are substantially parallel to each other. The substantial portion of the iris image is not annular. The data of the substantial portion is transformed into a polar coordinate form.

A further aspect of the present invention provides a device for use with a iris pattern recognition system. The method comprises: means for providing an image of an iris of an eye, the iris image being substantially annular and defined between inner and outer boundaries; means for obtaining data of a substantial portion, but not all, of the iris image; and means for processing the data of the substantial portion to obtain an iris pattern. In the above-described device, an iris image processing device comprises: an input device configured to receive an image of an eye comprising an image of an iris of an eye, the iris image being substantially annular and defined between inner and outer boundaries; a first circuit configured to identify data of the iris image from the image of the eye; and a second circuit configured to process the iris image data so as to obtain data of a substantial portion, but not all, of the iris image for further processing. The first and second circuits are integrated in a circuit board or a chip.

The other aspect of the present invention is a security system using iris pattern recognition. The system comprises: an input device configured to receive an image of an eye comprising an image of an iris of an eye, the iris image being substantially annular and defined between inner and outer boundaries; a first circuit configured to identify data of the iris image from the image of the eye; a second circuit configured to process the iris image data so as to obtain data of a substantial portion, but not all, of the iris image for further processing; and a third circuit configured to process the data of the substantial portion of the iris image so as to determine whether the data of the iris image matches a pre-registered data.

A further aspect of the present invention is a method of processing a iris image. The method comprises: providing data of an original image of an iris; and producing at least one modified iris image data with use of the data of the original iris image, the modified iris image data representing an iris image that is rotated by an angle about a point on the original image. In the above-described method the point of rotation is located at a substantially central position of the original image of the iris. The original iris image data to determine whether the original iris image data matches a pre-registered iris image data. The modified iris image data to determine whether the modified iris image data matches a pre-registered iris image data. The modified iris image data represents an iris image that is rotated in a clockwise direction. The modified iris image data represents an iris image that is rotated in a counter-clockwise direction. A plurality of modified iris image data are produced. The modified iris image data is processed in accordance with a wavelet transform method. The original iris image data is processed in accordance with a wavelet transform method.

Still another aspect of the present invention provides an iris image processing device, which comprises: means for providing data of an original image of an iris; and means for producing at least one modified iris image data based on the data of the original iris image, the modified iris image data representing an iris image that is rotated by an angle about a point on the original image. The above-described device further comprises: means for determining whether the modified iris image data matches a pre-registered data.

Still another aspect of the present invention provides an iris image processing device, which comprises: an input device configured to receive an image of an eye comprising an image of an iris of an eye; a first circuit configured to identify data of the iris image from the image of the eye; and a second circuit configured to process the iris image data so as to produce at least one modified iris image data based on the data of the original iris image, the modified iris image data representing an iris image that is rotated by an angle about a point on the original image.

Still further aspect of the present invention provides a security system using iris pattern recognition, which comprises: the above-described iris image processing device; and a third circuit configured to process the modified iris image data to determine whether the modified iris image data matches a pre-registered data.

The present invention is conceived to solve the above problems. An object of the present invention is to provide a non-contact type human iris recognition method for performing a pre-processing by detecting an iris image from an eye image of a user acquired by image acquisition equipment and converting the iris image into an iris image in polar coordinates, wherein inner and outer boundaries of an iris of the user are detected by analyzing differences in pixels of a Canny edge detector and the image.

Another object of the present invention is to provide a human iris recognition method, wherein if an iris in an acquired eye image has been rotated at an arbitrary angle with respect to a centerline of the iris, i.e. in case of a rotated iris image, the rotated iris image is corrected into a normal iris image, and wherein if a lower portion of a converted iris image in the polar coordinates is curved with an irregular shape, i.e. in case of a slanted iris image, the iris image is normalized in predetermined dimensions, so that the iris image with a variety of deformation is processed into data on a correct iris image so as to markedly reduce a false acceptance rate and a false rejection rate.

In order to achieve the objects of the present invention, the present invention provides a non-contact type human iris recognition method by correction of a rotated iris image for performing a pre-processing by acquiring an eye image of a user by means of image acquisition equipment using an infrared illuminator, by extracting an iris image from the acquired user's eye image, and by converting the extracted iris image into an iris image in polar coordinates. The pre-processing comprises the steps of detecting an inner boundary of an iris from the acquired user's eye image by means of a Canny edge detector; comparing a pixel value of image information at a beginning coordinates (x, y) of the detected inner boundary of the iris with the other pixel values of image information while proceeding upward and downward and leftward and rightward from the inner boundary, finding out the maximum value among values of difference in the compared pixels, and detecting an outer boundary of the iris; and extracting an iris region existing between the inner and outer boundaries, and converting the extracted iris region into the iris image in the polar coordinates.

If the iris in the acquired eye image has been slanted, the method may further comprise a step of normalizing the converted iris image in the polar coordinates so as to have predetermined dimensions.

If the iris in the acquired eye image has been rotated at an arbitrary angle with respect to a centerline of the iris, the method may further comprise the steps of temporarily generating a plurality of arrays of the iris image by means of shifts by an arbitrary angle with respect to an array of the converted iris image in the polar coordinates; performing wavelet transform in order to generate characteristic vectors of the iris corresponding to the plurality of arrays of the iris image that have been temporarily generated; comparing the respective characteristic vectors generated by the wavelet transform with previously registered characteristic vectors to obtain similarities; and accepting a characteristic vector corresponding to the maximum similarity among the obtained similarities as the characteristic vector of the user.