Abstract: To lighten influences of external light when picking up images of biological patterns. The biological pattern imaging device includes a casing having an opening part on one of surfaces. The opening part is in a size that is about to be covered in a closed state when a biological part is placed thereon. The casing contains a light source for irradiating the biological part placed on the opening part, and an imaging part for picking up an image of the irradiated biological part.

Abstract: A face feature is extracted by a face feature extracting unit, a confidence index is extracted by a confidence index extracting unit, and then, they are outputted as a face meta-data. At a time of matching, by using the confidence index of the face meta-data, a distribution estimating unit estimates the data of a parameter and the like with regard to a posterior distribution when the confidence index is obtained. A distance calculating unit calculates a similarity between feature values. Consequently, the precision of face verification can be improved, thereby carrying out a practical face matching.

Abstract: An input pattern feature amount is decomposed into element vectors. For each of the feature vectors, a discriminant matrix obtained by discriminant analysis is prepared in advance. Each of the feature vectors is projected into a discriminant space defined by the discriminant matrix and the dimensions are compressed. According to the feature vector obtained, projection is performed again by the discriminant matrix to calculate the feature vector, thereby suppressing reduction of the feature amount effective for the discrimination and performing effective feature extraction.

Abstract: A method and apparatus for extracting feature vectors for face recognition and retrieval are provided. An entire Fourier feature vector is generated for an entire face area of a normalized face image using first and second normalized vectors, and a central Fourier feature vector is generated for a central face area of the normalized face image using third and fourth normalized vectors. An entire intensity feature vector is generated for the entire face area, and a local intensity feature vector is generated for a predetermined number of face component-wise areas. An entire composite feature vector is generated by coupling the first and second normalized vectors and the entire intensity feature, and a central composite feature vector is generated by coupling the third and fourth normalized vectors and the local intensity feature vectors.

Abstract: An input pattern feature amount is decomposed into element vectors. For each of the feature vectors, a discriminant matrix obtained by discriminant analysis is prepared in advance. Each of the feature vectors is projected into a discriminant space defined by the discriminant matrix and the dimensions are compressed. According to the feature vector obtained, projection is performed again by the discriminant matrix to calculate the feature vector, thereby suppressing reduction of the feature amount effective for the discrimination and performing effective feature extraction.

Abstract: A face meta-data creating technique in which the description length is short and which is used to extract the face feature for face recognition immune to the local error. An area cut-out section (121) cuts out a local area of a face image. Frequency feature extracting means (122) extracts the frequency spectrum of the local area. Vector projection means (123) projects the obtained frequency feature onto a partial space to extract the face feature of the local area. Aface meta-data unit (12) extracts the face features from local areas cut out in different positions, thus creating face features as face meta-data.

Abstract: A moving object is detected by subtraction between successive frames produced by a video camera and a position and a size of the moving object are determined. Preceding and succeeding frames produced by the video camera are stored into respective memories and the panning, tilting and zooming functions of the video camera are controlled according to the determined position and size of the moving object. A motion compensation is performed on the preceding frame to compensate for a motion of background image caused by a tracking movement of the camera so that coordinates of the motion-compensated frame are transformed to coordinates of the succeeding frame. An image difference between the motion-compensated frame and the succeeding frame is extracted as a moving object and a position and a size of the extracted image are determined, with which the video camera is adaptively controlled.

Abstract: A face feature is extracted by a face feature extracting unit, a confidence index is extracted by a confidence index extracting unit, and then, they are outputted as a face meta-data. At a time of matching, by using the confidence index of the face meta-data, a distribution estimating unit estimates the data of a parameter and the like with regard to a posterior distribution when the confidence index is obtained. A distance calculating unit calculates a similarity between feature values. Consequently, the precision of face verification can be improved, thereby carrying out a practical face matching.

Abstract: A method and apparatus for extracting feature vectors for face recognition and retrieval are provided. An entire Fourier feature vector is generated for an entire face area of a normalized face image using first and second normalized vectors, and a central Fourier feature vector is generated for a central face area of the normalized face image using third and fourth normalized vectors. An entire intensity feature vector is generated for the entire face area, and a local intensity feature vector is generated for a predetermined number of face component-wise areas. An entire composite feature vector is generated by coupling the first and second normalized vectors and the entire intensity feature, and a central composite feature vector is generated by coupling the third and fourth normalized vectors and the local intensity feature vectors.

Abstract: A moving object is detected by subtraction between successive frames produced by a video camera and a position and a size of the moving object are determined. Preceding and succeeding frames produced by the video camera are stored into respective memories and the panning, tilting and zooming functions of the video camera are controlled according to the determined position and size of the moving object. A motion compensation is performed on the preceding frame to compensate for a motion of background image caused by a tracking movement of the camera so that coordinates of the motion-compensated frame are transformed to coordinates of the succeeding frame. An image difference between the motion-compensated frame and the succeeding frame is extracted as a moving object and a position and a size of the extracted image are determined, with which the video camera is adaptively controlled.

Abstract: For providing an efficient image pattern matching system, an image feature extractor (11) of the invention comprises a feature vector extraction means (101) for extracting a feature vector from the pattern image, a quality index extraction means (106) for extracting quality index information of the pattern image, an error distribution information storing means (105) wherein error distribution information representing correlation between error distribution of the feature vector and the quality index information is prepared, and a confidence attribution means (107) for obtaining confidence estimation information referring to the error distribution information retrieved with the quality index information. The image feature analyzer (51) prepares the errors distribution information. An image feature matching system collates feature information of an image pattern extracted by the image feature extractor (11) by comparing it to registered feature information.

Abstract: For providing an efficient image pattern matching system, an image feature extractor (11) of the invention comprises a feature vector extraction means (101) for extracting a feature vector from the pattern image, a quality index extraction means (106) for extracting quality index information of the pattern image, an error distribution information storing means (105) wherein error distribution information representing correlation between error distribution of the feature vector and the quality index information is prepared, and a confidence attribution means (107) for obtaining confidence estimation information referring to the error distribution information retrieved with the quality index information. The image feature analyzer (51) prepares the error distribution information. An image feature matching system collates feature information of an image pattern extracted by the image feature extractor (11) by comparing it to registered feature information.

Abstract: A skin pattern image is filtered by convolution calculation on a real plane or product calculation on a Fourier transformed plane with each of two-dimensional filters prepared according to kinds of features to be extracted of the skin pattern image. Image intensity of each subregion of each filtered data is calculated. Feature of each subregion is represented by a feature parameter corresponding to a filter that gives a highest value of the image intensity of the subregion. An initial pattern of features thus obtained is smoothed to minimize an evaluation function. A filtered skin pattern image having pixel values of each subregion smoothed by a set of filters prepared for extracting a kind of features is further filtered by another set of filters for extracting another kind of features.

Abstract: In order to classify fingerprint images with a high precision by integrating classification results and their merits of different classification means making use of their probability data, a fingerprint image classification system of the invention includes: a plurality of classification units (12 and 15), each of the plurality of classification units (12 and 15) generating an individual probability data set (17 or 18) indicating each probability of a fingerprint image (16) to be classified into each of categories; a probability estimation unit (13) for estimating an integrated probability data set (19) from every of the individual probability data set (17 and 18); and a category decision unit (14) for outputting a classification result of the fingerprint image (16) according to the integrated probability data set (19).

Abstract: A skin pattern classification system extracts ridge line data and valley line data from image data of a skin pattern. Minutiae are extracted from the ridge line data and the valley line data. Subsequently, minutia correspondence information is obtained by detecting mutual correspondence among the minutiae from the ridge line data, valley line data and the minutiae. Skin patterns are obtained by finding and tracing characteristic lines referring to the minutia correspondence information, the ridge line data and the valley line data, and the characteristic lines and the minutia correspondence information serve to provide pattern classification.

Abstract: From an image memory of a fingerprint picture, gradient vectors of the picture are calculated. And from distribution of gradient vectors in a subregion, ridge direction of the subregion are determined, and confidence of the determined direction is also defined.

Abstract: An energy function is defined as a linear sum of a discrepancy evaluation function and a dispersion evaluation function. Direction variables of all the subregions of a ridge direction pattern are variables of both evaluation functions. Direction variables are successively renovated along a line on which the energy function becomes minimum for a change of a concerned variable keeping all other variables unchanged. Reliabilities of initial directions in all the subregions are included as coefficients in the discrepancy evaluation function, and a higher reliability of an initial direction constrains the directional difference between the initial direction and the corresponding direction variable in a smaller amount. A set of variables which makes the energy function minimum is taken as a set of smoothed ridge direction pattern.

Abstract: Substituted heterocyclic derivatives represented by the formula (I) ##STR1## wherein R, R.sup.1, R.sup.2, R.sup.3, R.sup.4, Q.sup.1, Q.sup.2, Q.sup.3, Q.sup.4, X and Y are as defined, including, specifically, the compound (E)-3-[3-[3-(2-methoxymethyl-8,8-dimethyl-4-nonen-6-ynyl)phenoxymethyl]phe nyl]thiophene, exhibit squalene epoxidase inhibiting activity and are useful in the treatment or prophylaxis of hypercholesterolemia, hyperlipidemia and arteriosclerosis.

Abstract: Substituted amine derivatives represented by the general formula ##STR1## wherein Q is --C--D--E--F--G--M-- or --N--H--I--J--K--L-- [C, D, E, F, G, H, I, J, K and L are each O, S, a carbonyl group, --CHR.sup.a --, --R.sup.b .dbd. or --NR.sup.c -- (R.sup.a, R.sup.b and R.sup.c are each H or a lower alkyl group), M and N are each an aromatic ring of 5-6 members optionally having a halogen, OH, LN, a lower alkyl group or a lower alkoxy group, provided that L is not O, S, or --NR.sup.c --]; R is a heterocyclic ring of 5-6 members; R.sup.1 is H, a lower alkyl group, a lower haloalkyl group, a lower alkenyl group, a lower alkynyl group or a cycloalkyl group; R.sup.2, R.sup.3, R.sup.4, R.sup.5, R.sup.6 and R.sup.7 are each H, a halogen or a lower alkyl group or two of them denote a single bond; R.sup.8 and R.sup.9 are each F, CF.sub.3 or a lower alkyl group or are a cycloalkane in combination thereof; and R.sup.10 is H, F, CF.sub.3 an acetoxy group, a lower alkyl group or a lower alkoxy group.

Abstract: Substituted amine derivatives represented by the general formula ##STR1## wherein Q is -C-D-E- F-G-M- or -N-H-I-J-K-L- [C, D, E, F, G, H, I, J, K and L are each O, S, a carbonyl group, -CHR.sup.2 -, -R.sup.b = or -NR.sup.c - (R.sup.a, R.sup.b and R.sup.c are each H or a lower alkyl group), M and N are each an aromatic ring of 5-6 members optionally having a halogen, OH, LN, a lower alkyl group or a lower alkoxy group, provided that L is not O, S, or -NR.sup.c -]; R is a heterocyclic ring of 5-6 members; R.sup.1 is H, a lower alkyl group, a lower haloalkyl group, a lower alkenyl group, a lower alkynyl group or a cycloalkyl group; R.sup.2, R.sup.3, R.sup.4, R.sup.5 R.sup.6 and R.sup.7 are each H, a halogen or a lower alkyl group or two of them denote a single bond; R.sup.8 and R.sup.9 are each F, CF.sub.3 or a lower alkyl group or are a cycloalkane in combination thereof; and R.sup.10 is H, F, CF.sub. 3 an acetoxy group, a lower alkyl group or a lower alkoxy group.