Method for accurately determining the position and orientation of each of a plurality of identical recognition target objects in a search target image

• US 9,483,712 B2
• Filed: 09/25/2015
• Issued: 11/01/2016
• Est. Priority Date: 07/31/2014
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chiaki, Oishi, Mori, Yumi, Nakano, Hiroki
• Primary Examiner(s): Abdi, Amara
• Application Number:
  US14/865,636
• Publication Number:
  US 20160034781A1
• Time in Patent Office: 403 Days
• Field of Search: 382/103
• US Class Current: 1/1
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 2207/30242 Counting objects in image
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 10/7515 Shifting the patterns to accommodate for positional errors

Abstract

Embodiments of the invention relate to detecting the number, position, and orientation of objects when a plurality of recognition target objects are present in a search target image. Dictionary image data is provided, including a recognition target pattern, a plurality of feature points of the recognition target pattern, and an offset (O_x, O_y) from the coordinates at the center of the image to the coordinates of the feature point. The sizes (R_t) and directions (θ_t) of feature vectors for the coordinates (T_x, T_y) of a plurality of feature points in the target image are also provided. The coordinates (F_x, F_y) of a virtual center point in the target image is derived. Additional virtual center points within a radius of the coordinates (F_x, F_y) is counted. Presence of a recognition target object is recognized near the virtual center point coordinates of the search target image.

Claims

1. A computer implemented method for determining whether one or more recognition target patterns are present in a target image, wherein dictionary image data including a recognition target pattern, a plurality of feature points of the recognition target pattern including a size (R_m) and direction (θ

_m) of a feature vector, and an offset (O_x, O_y) from coordinates at a center of a target image to coordinates of a feature point are provided, and wherein a size (R_t) and direction (θ

_t) feature vector for coordinates (T_x, T_y) of a plurality of feature points in the target image are provided, and wherein calculated coordinates (F_x, F_y) of a virtual center point in the target image derived from T_x, T_y, O_x, O_y, R_m, R_t, θ

_m, and θ

_t are provided, the method comprising;

counting a number of additional virtual center points within a predetermined radius (r) of the coordinates (F_x, F_y) of the virtual center point;

determining whether the number of additional virtual center points exceeds a predetermined threshold value (N_c);

storing the coordinates (F_x, F_y) of the virtual center point and the number of counted virtual center points when the predetermined threshold value has been exceeded; and

establishing the coordinates (F_x, F_y) of the virtual center point of a maximum number of counted virtual center points as a center of a recognition target image.

2. The method of claim 1, further comprising repeating the counting and storing on all feature points in the target image.

3. The method of claim 1, wherein each feature point in the plurality of feature points in the target image is a matching feature point of at least one feature point in the target image and at least one feature point in the recognition target pattern.

4. The method of claim 1, further comprising establishing the coordinate (F_x, F_y) as one recognition target image center and eliminating all of the virtual center points within a predetermined radius (r) of the coordinates (F_x, F_y).

5. The method of claim 1, wherein the coordinates of the virtual center point in the target image are calculated using the following equations:

F_x=T_x+(O_x·

R_t/R_m)(cos(θ

_t−

θ

_m))+(O_y·

R_t/R_m)(sin(θ

_t−

θ

_m))

F_y=T_y+(O_x·

R_t/R_m)(−

sin(θ

_t−

θ

_m))+(O_y·

R_t/R_m)(cos(θ

_t−

θ

_m)).