A two-dimensional image sensor 12 having openings 28 through which light can pass is formed on a transparent substrate 21 and combined with a planar light source 11 and an optical element 13 which defines optical paths. The optical element 13 is formed by combining one of a diffraction grating, a microlens and a specular surface of V-shaped grooves with a collected fiber member formed from bundled optical fibers having light shielding side faces so as to allow the transfer of an image. The profiles of these components are determined so that light may be focused upon a finger contacting area on the center line between the openings 28 and photo-sensitive elements 24 of the sensor 12.

The fingerprint image input apparatus includes two-dimensional image sensor 14 formed on transparent substrate 21 and including diffraction grating 41, photo-sensitive elements 24, switch elements 22, switching lines 25, signal reading lines 26, bias applying lines 27, and light interception plates 23 disposed below photo-sensitive elements 24, planar light source 11 and transparent protective film 42. Diffraction grating 41 is formed on two-dimensional image sensor 14 together with photo-sensitive elements 24 commonly using one or more opaque materials of photo-sensitive elements 24.

Four fingers of a hand of an individual person, i.e. the index finger, the middle finger, the medical finger and the little finger are placed on a transparent measuring table in juxtaposition. A guide member is also placed on the table to restrict the position of the hand and light is irradiated onto the table. The intensity of the light passed through the transparent measuring table is scanned by a television camera and so on at every light receiving point to convert it an electrical signal. Thus obtained electric signals are processed to calculate the differential data of the finger lengths thereby detecting an individual person.

The image processing system has a unit for photographing an object in two dimensions, a feature extraction unit for extracting features from the two-dimensional image data from the photographing means, and a three-dimensional shape reproduction unit. The feature extraction unit refers to feature points given to the object to extract the features. The three-dimensional shape reproduction unit expresses the object by a dynamic equation, applies force from the feature extraction coordinates to the dynamic model to cause the dynamic model to change shape and supplement depth data, and to thereby reproduce the three-dimensional shape of the object. To increase the speed of the processing, it is desirable to divide the image data of the object into portions with little changes in shape and perform the processing for reproducing the three-dimensional shape for each mode.

A method for analyzing stored image details for identification purposes is disclosed in which slopes are abstracted from an image to provide three-dimensional recognition information as abstractions. Data representing light levels of an image are stored in a picture memory device, which is analyzed in a predetermined manner to select absolute illumination magnitudes between fixed locations of the image. This information is directly related to the slope between the locations. Steeper slopes and their corresponding locations are stored as recognition data in a learn mode. These abstractions are compared and several are permanently stored. In an access mode, the previously-obtained information is utilized to verify with current data, and depending upon the degree of correlation therebetween, an indication of recognition is either verified or rejected. If current data is better than any of the permanently-stored data, the permanently-stored data is replaced by the current data to update the permanently-stored data.