Abstract: This invention provides an image processing method and image processing device capable of detecting a falsification with high accuracy. A watermarked image inputting part 200 includes: a watermark information extracting part 220 for detecting a superposing position of a superposed pattern from a pattern-superposed image having an identifiable pattern superposed on an original image; and an input image deforming part 230 for creating a corrected image of a pattern-superposed image 260 based on information on the detected superposing position. Since an image having a printed sheet scanned is corrected based on the position information on the signal embedded at the time of printing, an image before printing can be restored without distortion and stretching from the image scanned from a printed matter. Accordingly, the correlation of the position between the images can be determined with high accuracy and further a high-performance detection of falsification can be performed.

Abstract: A tampering judgement system is provided which is capable of easily checking whether or not a printed document has been tampered. An image feature information extracting section extracts image feature information from a document image. An image feature information embedding section gives image feature information integrally as original image feature information to a document and a document image output section outputs the information as a printed document. When the printed document is given to the tampering judgement system, the image data is read by a document image reading section. An image feature information extracting section extracts image feature information contained in a document being an object for judgement on tampering. An embedding information extracting section extracts original image feature information from image data.

Abstract: There is provided a watermark information detecting method capable of detecting confidential information accurately from a document including confidential information. In this method, a filtering process is performed on the whole surface of an input image (S310), and a position of signal is obtained by using a signal position searching template in order for the sum of filter output value to be maximum (S320). Then a signal border is determined (S340). Even when the image is expanded or contracted due to displacement of paper, etc., the signal position can be correctly detected and confidential information can be correctly detected from a document including confidential information.

Abstract: To provide an electronic watermark embedding device for improving accuracy when classified information is being detected. The watermark image forming section 1006 creates a watermark image based on classified information 1004 with reference to the document image. For the document image, embedding regions for embedding a dot pattern which is identifiable as a prescribed symbol by a prescribed filter are detected, and a determination is made as to whether or not the proportion of the text region to the embedding region is less than or equal to a prescribed threshold value, and if the proportion of the text region is less than or equal to the prescribed threshold value, a prescribed number of dot patterns in which a symbol formed of at least a portion of the classified information is identifiable (symbol unit) is embedded in a region where the embedding region and the text region do not overlap.

Abstract: There is provided a watermark information detecting method capable of detecting confidential information accurately from a document including confidential information. In this method, a filtering process is performed on the whole surface of an input image (S310), and a position of signal is obtained by using a signal position searching template in order for the sum of filter output value to be maximum (S320). Then a signal border is determined (S340). Even when the image is expanded or contracted due to displacement of paper, etc., the signal position can be correctly detected and confidential information can be correctly detected from a document including confidential information.

Abstract: There are provided a watermark information embedding device and a watermark information detection device which can correctly extract classified information. In the watermark information embedding device, a plurality of dot patterns the wave directions and/or wavelengths of which are changed depending on dot arrangements are prepared, one symbol is given to one of the dot patterns, and the dot patterns are combined and arranged, so that the classified information is given. The watermark information detection device includes two-dimensional wavelet filters the number of which is equal to the number of dot patterns and which have the same wave directions and the same wavelengths as those of the dot patterns. Convolutions between an arbitrary region in a watermarked image and the plurality of two-dimensional wavelet filters are calculated, and it is determined that the dot pattern corresponding to the two-dimensional wavelet filter having the maximum convolution is embedded in the region.

Abstract: There are disclosed a watermark information embedment device capable of accurately embedding secret information, and a watermark information detection device. In the watermark information embedment device, there are prepared a plurality of different sorts of dot patterns in which the wave propagation direction and the wave length are changed depending on the dot arrangement. Each dot pattern of the same sort is given the same symbol, and the secret information is represented by combining these dot patterns. In the watermark information detection device, there are provided 2-dimensional wavelet filters having the same wave propagation direction and the wave length as the different sorts of dot patterns.

Abstract: To provide an electronic watermark embedding device for improving accuracy when classified information is being detected. The watermark image forming section 1006 creates a watermark image based on classified information 1004 with reference to the document image. For the document image, embedding regions for embedding a dot pattern which is identifiable as a prescribed symbol by a prescribed filter are detected, and a determination is made as to whether or not the proportion of the text region to the embedding region is less than or equal to a prescribed threshold value, and if the proportion of the text region is less than or equal to the prescribed threshold value, a prescribed number of dot patterns in which a symbol formed of at least a portion of the classified information is identifiable (symbol unit) is embedded in a region where the embedding region and the text region do not overlap.

Abstract: There are provided a watermark information embedding device and a watermark information detection device which can correctly extract classified information. In the watermark information embedding device, a plurality of dot patterns the wave directions and/or wavelengths of which are changed depending on dot arrangements are prepared, one symbol is given to one of the dot patterns, and the dot patterns are combined and arranged, so that the classified information is given. The watermark information detection device includes two-dimensional wavelet filters the number of which is equal to the number of dot patterns and which have the same wave directions and the same wavelengths as those of the dot patterns. Convolutions between an arbitrary region in a watermarked image and the plurality of two-dimensional wavelet filters are calculated, and it is determined that the dot pattern corresponding to the two-dimensional wavelet filter having the maximum convolution is embedded in the region.

Abstract: A tampering judgement system is provided which is capable of easily checking whether or not a printed document has been tampered. An image feature information extracting section extracts image feature information from a document image. An image feature information embedding section gives image feature information integrally as original image feature information to a document and a document image output section outputs the information as a printed document. When the printed document is given to the tampering judgement system, the image data is read by a document image reading section. An image feature information extracting section extracts image feature information contained in a document being an object for judgement on tampering. An embedding information extracting section extracts original image feature information from image data.

Abstract: An individual identification device and a method for extracting an iris region which can extract the iris region with high accuracy even if the shape of a pupil is not circular as in the case of a horse, cattle or the like. Contour lines of the pupil and an granula iridia are extracted from an image inputted. Part of a circle is applied to a contour line of the pupil and a radius of the contour line outside the iris region is estimated by an angle formed by two lines, one to connect both ends of the pupil and the other to pass the center of the circle. An iris circle is estimated by applying part of the circle to the contour line inside and outside the iris region.

Abstract: There are disclosed a water information embedment device capable of accurately fetching secret information, and a watermark information detection device. In the watermark information embedment device, there are prepared plural sorts of dot patterns of which the wave propagation direction and the wave length are changed depending on the dot arrangement. Each of the same sorts of dot patterns is given the same symbol by one each, and the secret information is attained by combining these dot patterns. In the watermark information detection device, there are provided 2-dimensional wavelet filters having the same wave propagation direction and the wave length as the dot pattern by the number equal to the number of the dot patterns.

Abstract: An animal identification system is provided which is designed to determine outlines of a pupil and irial granule in an input image of an eye of an animal to be identified, apply an arc to a lower portion of the outline of the pupil, turns back the arc from a principal axis to define a reference axis, and maps an image of the irial granule into a polar coordinate system whose origin is the center of the reference axis. The shape of the irial granule corrected in the above manner is compared with a reference shape stored in a memory to determine whether the input image arises from the same animal or not.

Abstract: An input image that includes an eye is divided into a plurality of blocks, and a mosaic image in which each of the blocks has a density value is produced. Among all the blocks, one having a small distance from a center point of the mosaic image and having a small density value is determined to be a block including the center of the pupil of the eye. Then, based on the determined block, a center position of the pupil in the input image is derived. Based on the density value of the block including the center of the pupil, a density threshold value is set. Then, based on the density threshold value, a two-valued image is produced from the input image. Among regions in the two-valued image which are darker than the density threshold value, one including the center position of the pupil is extracted as a pupil region.

Abstract: An animal identification system is provided which is designed to determine outlines of a pupil and irial granule in an input image of an eye of an animal to be identified, apply an arc to a lower portion of the outline of the pupil, turns back the arc from a principal axis to define a reference axis, and maps an image of the irial granule into a polar coordinate system whose origin is the center of the reference axis. The shape of the irial granule corrected in the above manner is compared with a reference shape stored in a memory to determine whether the input image arises from the same animal or not.

Abstract: An animal identification system is provided which is designed to determine outlines of a pupil and irial granule in an input image of an eye of an animal to be identified, apply an arc to a lower portion of the outline of the pupil, turn back the arc from a principal axis to define a reference axis, and map an image of the irial granule into a polar coordinate system whose origin is the center of the reference axis. The shape of the irial granule corrected in the above manner is compared with a reference shape stored in a memory to determine whether the input image arises from the same animal or not.

Abstract: An input image that includes an eye is divided into a plurality of blocks, and a mosaic image in which each of the blocks has a density value is produced. Among all the blocks, one having a small distance from a center point of the mosaic image and having a small density value is determined to be a block including the center of the pupil of the eye. Then, based on the determined block, a center position of the pupil in the input image is derived. Based on the density value of the block including the center of the pupil, a density threshold value is set. Then, based on the density threshold value, a two-valued image is produced from the input image. Among regions in the two-valued image which are darker than the density threshold value, one including the center position of the pupil is extracted as a pupil region.