Image processing apparatus and method

• US 6,690,814 B1
• Filed: 03/10/2000
• Issued: 02/10/2004
• Est. Priority Date: 03/11/1999
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Yuasa, Mayumi, Suzuki, Kaoru, Wakasugi, Tomokazu, Yamaguchi, Osamu, Fukui, Kazuhiro
• Primary Examiner(s): Patel, Jayanti K.
• Application Number:
  US09/522,597
• Time in Patent Office: 1,432 Days
• Field of Search: 382/103, 382/115, 382/118, 382/117, 382/157, 382/168, 382/171, 382/172, 382/170, 382/190, 382/199, 382/209, 382/218, 434/155, 902/3-6, 902/25-29, 351/206, 348/14.01, 348/159, 348/169
• US Class Current: 382/118
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

An image processing apparatus. A camera inputs an image of a face of a person to be recognized. A recognition area detection section generates a difference image between the input image and a predetermined pattern, and detects a recognition area whose value is above a threshold from the input image. An input data generation section converts the recognition area to a predetermined input data. A similarity calculation section calculates a similarity by comparing the predetermined input data with a predetermined dictionary data. A view position of the camera is located lower than a position of the face of the person. A direction of the optical axis of the camera represents an angle of elevation from a horizontal direction.

Claims

1. An image processing apparatus, comprising;

a camera for inputting an image of a face of a person to be recognized;

recognition area detection means for generating a difference image between the input image and a predetermined pattern and for detecting a recognition area whose value is above a threshold from the difference image;

input data generation means for converting the recognition area to predetermined input data; and

similarity calculation means for calculating a similarity by comparing the predetermined input data with predetermined dictionary data,

wherein a view position of the camera is located lower than a position of the face of the person, a direction of an optical axis of the camera represents an angle of elevation from a horizontal direction, and the angle of elevation is 20°

˜

60°

so that the camera inputs the image including both pupils and both nostrils of the face of the person.

2. The image processing apparatus according to claim 1,

wherein the camera is set at one of two pillars of a gate apparatus for admitting a person in order to input the image of the face of the person passing through the two pillars of the gate apparatus.

3. The image processing apparatus according to claim 2,

wherein the camera inputs the image of the face of one person from slanting lower position against a passing direction of the one person.

4. The image processing apparatus according to claim 3,

wherein the predetermined pattern is a background image of the ceiling in a room in which the gate apparatus is located.

5. The image processing apparatus according to claim 4,

further comprising a variation correction means for eliminating low frequency element affected by illumination from the input image as a variation correction image, the variation correction image being supplied to said recognition area detection means.

6. An image processing apparatus, comprising:

a camera for inputting an image of a face of a person to be recognized;

face detection means for detecting a face area from the input image;

facial part detection means for detecting a plurality of facial parts from the face area; and

gaze direction detection means for detecting a gaze direction of the person from the plurality of facial parts;

wherein a view position of the camera is located lower than a position of the face of the person, a direction of an optical axis of the camera represents an angle of elevation from a horizontal direction, and the angle of elevation is 20°

˜

60°

so that the camera inputs the image including both pupils and both nostrils of the face of the person.

7. The image processing apparatus according to claim 6,

wherein the posture of the person defines the vertical axis to which the horizontal axis is perpendicular.

8. The image processing apparatus according to claim 7,

wherein said facial part detection means detects two pupils from the face area as the plurality of facial parts, and

wherein said gaze direction detection means calculates a similarity between each pattern of the two pupils and a dictionary pattern of pupil of each gaze direction, and selects one gaze direction of the dictionary pattern of the largest similarity as the person'"'"'s gaze direction.

9. An image processing apparatus, comprising:

a camera for inputting an image of a face of a person to be recognized;

face detection means for detecting a face area from the input image;

facial part detection means for detecting a plurality of facial parts from the face area;

person identification means for identifying the person using a facial pattern having the plurality of facial parts; and

target means for leading at least one of a gaze direction and a facial position of the person to one of a predetermined direction and a position,

wherein a view position of the camera is located lower than a position of the face of the person, a direction of an optical axis of the camera represents an angle of elevation from a horizontal direction, and the angle of elevation is 20°

˜

60°

so that the camera inputs the image including both pupils and both nostrils of the face of the person.

10. The image processing apparatus according to claim 9,

wherein said target means includes one of a CRT display viewable by the person, a liquid crystal display of narrow view angle, a mark to lead the person'"'"'s gaze direction, a mirror, and another camera to input a frontal face image of the person.

11. A method for processing an image, comprising:

inputting an image of a face of a person to be recognized using a camera;

generating a difference image between the input image and a predetermined pattern;

detecting a recognition area whose value is above a threshold from the difference image;

converting the recognition area to predetermined input data; and

calculating a similarity by comparing the predetermined input data with predetermined dictionary data;

wherein a view position of the camera is located lower than a position of the face of the person, a direction of an optical axis of the camera represents an angle of elevation from a horizontal direction, and the angle of elevation is 20°

˜

60°

so that the camera inputs the image including both pupils and both nostrils of the face of the person.

12. A method for processing an image, comprising:

inputting an image of a face of a person to be recognized using a camera;

detecting a face area from the input image;

detecting a plurality of facial parts from the face area; and

detecting a gaze direction of the person from the plurality of facial parts,

wherein a view position of the camera is located lower than a position of the face of the person, a direction of an optical axis of the camera represents an angle of elevation from a horizontal direction, and the angle of elevation is 20°

˜

60°

so that the camera inputs the image including both pupils and both nostrils of the face of the person.

13. A method for processing an image, comprising:

inputting an image of a face of a person to be recognized using a camera;

detecting a face area from the input image;

detecting a plurality of facial parts from the face area;

identifying the person using a facial pattern having the plurality of facial parts; and

leading at least one of a gaze direction and a facial position of the person to one of a predetermined direction and a position,

wherein a view position of the camera is located lower than a position of the face of the person, a direction of an optical axis of the camera represents an angle of elevation from a horizontal direction, and the angle of elevation is 20°

˜

60°

so that the camera inputs the image including both pupils and both nostrils of the face of the person.

14. A computer readable memory containing computer readable instructions, comprising:

instruction means for causing a computer to input an image of a face of a person to be recognized using a camera;

instruction means for causing a computer to generate a difference image between the input image and a predetermined pattern;

instruction means for causing a computer to detect a recognition area whose value is above a threshold from the difference image;

instruction means for causing a computer to convert the recognition area to predetermined input data; and

instruction means for causing a computer to calculate a similarity by comparing the predetermined input data with predetermined dictionary data,

wherein a view position of the camera is located lower than a position of the face of the person, a direction of an optical axis of the camera represents an angle of elevation from a horizontal direction, and the angle of elevation is 20°

˜

60°

so that the camera inputs the image including both pupils and both nostrils of the face of the person.

15. A computer readable memory containing computer readable instructions, comprising:

instruction means for causing a computer to input an image of a face of a person to be recognized using a camera;

instruction means for causing a computer to detect a face area from the input image;

instruction means for causing a computer to detect a plurality of facial parts from the face area; and

instruction means for causing a computer to detect a gaze direction of the person from the plurality of facial parts,

wherein a view position of the camera is located lower than a position of the face of the person, a direction of an optical axis of the camera represents an angle of elevation from a horizontal direction, and the angle of elevation is 20°

˜

60°

so that the camera inputs the image including both pupils and both nostrils of the face of the person.

16. A computer readable memory containing computer readable instructions, comprising:

instruction means for causing a computer to input an image of a face of a person to be recognized using a camera;

instruction means for causing a computer to detect a face area from the input image;

instruction means for causing a computer to detect a plurality of facial parts from the face area;

instruction means for causing a computer to identify the person using a facial pattern having the plurality of facial parts; and

instruction means for causing a computer to lead at least one of a gaze direction and a facial position of the person to one of a predetermined direction and a position,

wherein a view position of the camera is located lower than a position of the face of the person, a direction of an optical axis of the camera represents an angle of elevation from a horizontal direction, and the angle of elevation is 20°

˜

60°

so that the camera inputs the image including both pupils and both nostrils of the face of the person.

17. An image processing apparatus, comprising:

a camera configured to input an image of a face of a person to be recognized;

a recognition area detection unit configured to generate a difference image between the input image and a predetermined pattern, and to detect a recognition area whose value is above a threshold from the difference image;

an input data generation unit configured to convert the recognition area to predetermined input data; and

a similarity calculation unit configured to calculate a similarity by comparing the predetermined input data with predetermined dictionary data,

wherein a view position of the camera is located lower than a position of the face of the person, a direction of an optical axis of the camera represents an angle of elevation from a horizontal direction, and the angle of elevation is 20°

˜

60°

so that the camera inputs the image including both pupils and both nostrils of the face of the person.

18. An image processing apparatus, comprising:

a camera configured to input an image of a face of a person to be recognized;

a face detection unit configured to detect a face area from the input image;

a facial part detection unit configured to detect a plurality of facial parts from the face area; and

a gaze direction detection unit configured to detect a gaze direction of the person from the plurality of facial parts,

wherein a view position of the camera is located lower than a position of the face of the person, a direction of an optical axis of the camera represents an angle of elevation from a horizontal direction, and the angle of elevation is 20°

˜

60°

so that the camera inputs the image including both pupils and both nostrils of the face of the person.

19. An image processing apparatus, comprising:

a camera configured to input an image of a face of a person to be recognized;

a face detection unit configured to detect a face area from the input image;

a facial part detection unit configured to detect a plurality of facial parts from the face area;

a person identification unit configured to identify the person using a facial pattern having the plurality of facial parts; and

a target configured to lead at least one of a gaze direction and a facial position of the person to one of a predetermined direction and a position,

wherein a view position of the camera is located lower than a position of the face of the person, a direction of an optical axis of the camera represents an angle of elevation from a horizontal direction, and the angle of elevation is 20°

˜

60°

so that the camera inputs the image including both pupils and both nostrils of the face of the person.