Method and apparatus for collating object

• US 7,593,019 B2
• Filed: 11/26/2007
• Issued: 09/22/2009
• Est. Priority Date: 11/20/2000
• Status: Expired due to Term

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Ishiyama, Rui
• Primary Examiner(s): Nguyen; Hau H
• Application Number:
  US11/944,983
• Publication Number:
  US 20080094393A1
• Time in Patent Office: 666 Days
• Field of Search: 345/582, 345/423, 345/419, 345/427, 345/607, 345/552, 382/118, 382/218, 382/219
• US Class Current: 345/582
• CPC Class Codes: G06V 10/60 relating to illumination properties, e.g. using a reflectance or lighting model
• CPC Class Codes: G06V 10/758 Involving statistics of pixels or of feature values, e.g. histogram matching
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

An object collation method comprising a registration procedure for registering the registered data of a registered object in a database, and a collation procedure for collating the input image of a target object with the registered data. The registration procedure includes a step of storing the three-dimensional shape of the registered object and a texture space defined by a texture group indicating the luminance and/or color information of each position of the object surface under various illumination conditions. The collation procedure includes the steps of: generating an illumination fluctuation space defined by the image group under the various illumination conditions, at the location and position of the target object in the input image from the three-dimensional shape and the texture space; and collating the target object and the registered object based on the distance between the illumination fluctuation space and the input image.

Claims

1. An object collation method comprising:

a registration procedure registering registered data of a registered object in a database; and

a collation procedure collating on an object collation apparatus an input image of a target object with said registered data,

said registration procedure comprising the steps of;

inputting a three-dimensional shape of the registered object and reflectivity of a surface of the registered object;

acquiring a texture group indicating luminance and color information of each location of the surface of the registered object under various illumination conditions by using said three-dimensional shape and said reflectivity;

generating a texture space, which is an image space, defined by said texture group; and

storing said three-dimensional shape and said texture space, and

said collation procedure comprising the steps of;

taking a two-dimensional image of the target object as an input image;

presuming location and position of the target object in said input image;

converting the input image into an input texture by using said three-dimensional shape and said presumed location and position;

calculating distance between said texture space and said texture obtained at said converting step; and

collating the target object and the registered object based on said distance.

2. A method according to claim 1,

wherein said generating step comprises the step of analyzing said texture group statistically to determine a basic texture group of basic vectors of a space covering most of fluctuation factors appearing on the texture in accordance with the illumination conditions,

wherein said storing step comprises the step of storing said basic texture group as the texture group,

wherein said calculating step comprises the steps of determining a correlation between said basic texture group and said input image;

generating a comparison texture which is closest to said input texture from the basic texture group based on said correlation; and

outputting similarity between said comparison texture and said input texture as the distance.

3. A method according to claim 1, wherein location information of a feature portion of the registered object is added to said registered data and is stored.

4. An object collation method comprising:

a registration procedure registering registered data of a registered object in a database; and

a collation procedure collating on an object collation apparatus an input image of a target object with said registered data;

said registration procedure comprising the steps of;

inputting a three-dimensional shape of the registered object and reflectivity of a surface of the registered object;

acquiring a texture group indicating luminance and color information of each location of the surface of the registered object under various illumination conditions by using said thee-dimensional shape and said reflectivity;

generating a texture space, which is an image space, defined by said texture group; and

storing said three-dimensional shape and said texture space; and

said collation procedure comprising the steps of;

taking a two-dimensional image of the target object as an input image;

presuming location and position of the target object in said input image;

generating an illumination fluctuation space, which is defined by an image group under the various illumination conditions, at same location and position as said presumed location and position, by using said three-dimensional shape and said texture space, said fluctuation space being an image space;

calculating distance between said input image and said illumination fluctuation space; and

collating the target object and the registered object based on said distance, wherein location information of a feature portion of the registered object is added to said registered data and is stored.