Detecting specified image identifiers on objects

Patent metadata

Field	Value
Publication number	US-9799119-B2
Application number	US-201514811345-A
Country	US
Kind code	B2
Filing date	Jul 28, 2015
Priority date	Jul 29, 2014
Publication date	Oct 24, 2017
Grant date	Oct 24, 2017

Abstract

Embodiments of the present application relate to a method, apparatus, and system for detecting a specified image identifier. The method includes retrieving a target image to be detected from a predetermined area, binarizing the target image to be detected to obtain a target binary image to be detected, calibrating connected domains of the target binary image to be detected, successively retrieving image features of candidate connected domains, and comparing the image features corresponding to the candidate connected domains to image features of a standard specified identifier image, wherein the candidate connected domains are determined based at least in part on the calibration of the connected domains, and determining a candidate connected domain as the location of the specified identifier image based at least in part on the comparison of the image features corresponding to the candidate connected domains to image features of the standard specified identifier image.

First claim

What is claimed is:

1. A method, comprising:
retrieving, by one or more processors, a target image to be detected from a predetermined area;
binarizing, by the one or more processors, the target image to be detected to obtain a target binary image to be detected, wherein the target binary image to be detected corresponds to a binary image of the target image to be detected and a negative image of the binary image;
calibrating a plurality of connected domains of the target binary image to be detected, wherein each of the plurality of connected domains corresponds to an area of the target binary image;
retrieving, by the one or more processors, a set of one or more image features of a plurality of candidate connected domains, and comparing at least one of the set of one of more image features corresponding to the plurality of candidate connected domains to image features of a standard specified identifier image, wherein the plurality of candidate connected domains are determined based at least in part on a result of calibrating the plurality of connected domains; and
determining, by the one or more processors, a candidate connected domain among the plurality of candidate connected domains as a location of the standard specified identifier image based at least in part on the a result of the comparing of the at least one of the set of one or more image features corresponding to the plurality of candidate connected domains to image features of the standard specified identifier image.

2. The method of claim 1 , wherein the plurality of candidate connected domains correspond to connected domains among the plurality of calibrated connected domains that have a number of pixels that satisfy a threshold value.

3. The method of claim 2 , wherein an upper limit value of the threshold value corresponds to a product of multiplying a width, a height, and an upper limit coefficient of the retrieved target image, and wherein a lower limit value of the threshold value corresponds to a product of multiplying the width, the height, and a lower limit coefficient of the retrieved target image.

4. The method of claim 1 , wherein the candidate connected domain determined as the location of the standard specified identifier image corresponds to a candidate connected domain that is identical to, or that has a highest similarity to, the standard specified identifier image according to the result of the comparing of the at least two of the set of one or more image features corresponding to the plurality of candidate connected domains to image features of the standard specified identifier image.

5. The method of claim 1 , wherein retrieving the target image to be detected from the predetermined area comprises:
retrieving a preview image of an image associated with the predetermined area;
computing an area range of the preview image;
framing the preview image within the area range; and
using the preview image framed within the area range as the target image to be detected.

6. The method of claim 5 , wherein the computation of the area range of the preview image includes retrieving a virtual frame parameter of the framed preview image based on a size parameter of the predetermined area and a resolution ratio parameter of the preview image.

7. The method of claim 6 , wherein the computation of the area range of the preview image comprises:
based on dimensions of the predetermined area, determining whether a product of multiplying a height of the preview image by a width of the predetermined area or image including the predetermined area is greater than a product of multiplying a width of the preview image by a height of the predetermined area or image including the predetermined area;
in the event that the product of multiplying the height of the preview image by the width of the predetermined area or image including the predetermined area is greater than the product of multiplying the width of the preview image or image including the predetermined area by the height of the predetermined area:
determining a width of a virtual frame to correspond to the width of the predetermined area or image including the predetermined area multiplied by the height of the preview image, divided by the height of the predetermined area or image including the predetermined area multiplied by a ratio of the virtual frame to the preview image; and
determining a height of the virtual frame to correspond to the height of the preview image multiplied by the ratio of the virtual frame to the preview image;

in the event that the product of multiplying the height of the preview image by the width of the predetermined area or image including the predetermined area is not greater than the product of multiplying the width of the preview image by the height of the predetermined area or image including the predetermined area:
determining the width of the virtual frame to correspond to the width of the preview image multiplied by the ratio of the virtual frame to the preview image; and
determining the height of the virtual frame to correspond to the height of the predetermined area or image including the predetermined area multiplied by the width of the preview image, divided by the width of the predetermined area or image including the predetermined area multiplied by the ratio of the virtual frame to the preview image; and

determining a top border of the virtual frame, a bottom border of the virtual frame, a left border of the virtual frame, and a right border of the virtual frame, wherein the top border of the virtual frame corresponds to one-half a difference between a height of a display screen and the height of the virtual frame, wherein the bottom border of the virtual frame is one-half a sum of the height of the display screen and the height of the virtual frame, wherein the left border of the virtual frame is one-half a difference between a width of the display screen and the width of the virtual frame, and wherein the right border of the virtual frame is one-half a sum of the width of the display screen and the width of the virtual frame.

8. The method of claim 1 , wherein retrieving the target image to be detected from the predetermined area comprises:
intercepting an area range including the standard specified identifier image to serve as the target image to be detected based at least in part on specified location information of the standard specified identifier image in the predetermined area or predetermined area image.

9. The method of claim 8 , wherein the specified location information corresponds to a position at which the standard specified identifier image is located in the predetermined area or predetermined area image, wherein the position at which the standard specified identifier image is located in the predetermined area is set according to one or more standard specifications associated with the standard specified identifier image.

10. The method of claim 9 , wherein a specified location corresponding to the specified location information is located in an upper right corner, a lower right corner, an upper left corner, or a lower left corner of the predetermined area or image including the predetermined area.

11. The method of claim 8 , wherein the intercepting of the area range including the standard specified identifier image to serve as the target image to be detected comprises:
establishing a standard image template of the predetermined area or image including the predetermined area;
traversing the standard image template, and retrieving location information associated with the standard specified identifier image in the predetermined area or image including the predetermined area based on correspondences between the stand

Assignees

• Alibaba Group Holding Ltd

Inventors

• Cheng Gang
• Chu Rufeng
• Zhang Lun

Classifications

• G06T7/33

  using feature-based methods · CPC title

• G06V10/28 Primary

  Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns · CPC title

• G06V10/25

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title

• G06V10/247

  by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids · CPC title

• G06T7/13

  Edge detection · CPC title