Person identification apparatus and method using concentric templates and feature point candidates

Claim 2

A person identification apparatus, comprising: image input means for inputting an image of a person to be identified; face area extraction means for extracting a face area from the inputted image of the person; feature point extraction means for extracting a plurality of candidate of feature points from the extracted face area by superimposing a separation filter on the face area, the separation filter being a mask of concentric shapes including an outer ring and an inner ring to calculate a separability of feature value between the outer ring and the inner ring; feature point set selection means for selecting n-sets of candidate feature points from all sets of candidate feature points according to face structure information; feature point decision means for extracting a neighbor pattern including a position of each candidate feature point from the face area, a size of the neighbor pattern being based on a size of the separation filter, for calculating a similarity value between the neighbor pattern for each candidate feature point and a previously-registered template pattern, the template pattern being a standard image of the feature point, and for selecting one set of candidate feature points whose sum of the similarity values is highest among n-sets of the candidate feature points; normalization means for generating a normalized face image of the face area according to the one set of candidate feature points; and recognition means for comparing the normalized face image with previously-registered image to identify the person.

Claim 3

The person identification apparatus according to claim 1, wherein said image input means inputs an image including a nostril of the face of the person.

Claim 4

The person identification apparatus according to claim 1, wherein a plurality of the separation filters having different sizes are superimposed on the face area to handle various sizes of the feature points.

Claim 5

The person identification apparatus according to claim 3, wherein said feature point extraction means includes means for respectively calculating the separability of a feature value between pixels included in the outer ring and pixels included in the inner ring according to a decision equation while the mask is superimposed on the face area.

Claim 6

The person identification apparatus according to claim 4, wherein said feature point extraction means includes means for extracting pixels area corresponding to a position of the mask from the face area as the candidate feature point when the separability corresponding to the position of the mask exceeds a threshold.

Claim 7

The person identification apparatus according to claim 1, wherein said face structure information includes a first distance between a pair of eyes, a second distance between a pair of nostrils, a third distance between a pair of edges of a mouth, a fourth distance between a center point of the first distance and a center point of the second distance, a first angle between a vector of the first distance and a vector of the second distance, and a second angle between a vector of the first distance and a vector of the fourth distance.

Claim 8

The person identification apparatus according to claim 6, wherein said feature point set selection means includes means for calculating an evaluation value for all sets of candidate feature points according to the face structure information, and means for selecting n-sets of the candidate feature points whose evaluation values have a high rank among all sets of candidate feature points.

Claim 9

The person identification apparatus according to claim 1, wherein said feature point decision means includes means for extracting a rectangular area corresponding to the position of the candidate feature point from the face area as the neighbor pattern.

Claim 10

The person identification apparatus according to claim 1, wherein said normalization means includes means for normalizing position and size of the one set of candidate feature points to generate the normalized face image.

Claim 13

A computer readable memory containing computer-readable instructions to identify a person, comprising: instruction means for causing a computer to input a face image of the person to be identified; instruction means for causing a computer to extract a face area from the face image of the person instruction means for causing a computer to extract a plurality of candidate feature points from the face area by superimposing a separation filter on the face area, the separation filter being a mask of concentric shapes including an outer ring and an inner ring to calculate a separability of feature value between the outer ring and the inner ring; instruction means for causing a computer to select n-sets of candidate feature points from all sets of candidate feature points according to face structure information; instruction means for causing a computer to extract a neighbor pattern including a position of each candidate feature point from the face area, a size of the neighbor pattern being based on a size of the separation filter; instruction means for causing a computer to calculate a similarity value between the neighbor pattern of each candidate feature point and a previously-registered template pattern, the template pattern being a standard image of the feature point; instruction means for causing a computer to select one set of the candidate feature points whose sum of the similarity values is highest among n-sets of the candidate feature points; instruction means for causing a computer to generate a normalized face image of the face area according to the one set of candidate feature points; and instruction means for causing a computer to compare the normalized face image with a previously-registered image to identify the person.

Claim 14

A computer readable memory containing computer-readable instructions to identify a person, comprising: instruction means for causing a computer to input a face image of the person to be identified; instruction means for causing a computer to extract a face area from the face image of the person instruction means for causing a computer to extract a plurality of candidate feature points from the face area by superimposing a separation filter on the face area, the separation filter being a mask of concentric shapes including an outer ring and an inner ring to calculate a separability of feature value between the outer ring and the inner ring; instruction means for causing a computer to select n-sets of candidate feature points from all sets of candidate feature points according to face structure information; instruction means for causing a computer to extract a neighbor pattern including a position of each candidate feature point from the face area, a size of the neighbor pattern being based on a size of the separation filter; instruction means for causing a computer to calculate a similarity value between the neighbor pattern of each candidate feature point and a previously-registered template pattern, the template pattern being a standard image of the feature point; instruction means for causing a computer to select one set of the candidate feature points whose sum of the similarity values is highest among n-sets of the candidate feature points; instruction means for causing a computer to generate a normalized face image of the face area according to the one set of candidate feature points; and instruction means for causing a computer to compare the normalized face image with a previously-registered image to identify the person.