Readable matrix code

• US 9,390,357 B2
• Filed: 12/14/2015
• Issued: 07/12/2016
• Est. Priority Date: 02/21/2012
• Status: Expired due to Fees

• Current Assignee: Alibaba Group Holding Ltd.
• Original Assignee: Eyeconit Ltd. (Alibaba Group Holding Ltd.)
• Inventors: Friedman, Itamar, Alva, Nevo, Peled, Uriel
• Primary Examiner(s): TRAIL, ALLYSON NEEL
• Application Number:
  US14/968,093
• Publication Number:
  US 20160098625A1
• Time in Patent Office: 211 Days
• Field of Search: 235/492, 235/494, 235/375
• US Class Current: 1/1
• CPC Class Codes: G06K 19/06037 multi-dimensional coding
• CPC Class Codes: G06K 19/06103 the marking being embedded in a human recognizable image, e.g. a company logo with an embedded two-dimensional code

Abstract

A method of generating a readable matrix code image encoding a message based on an input image and a readable matrix coding specification, comprising: calculating function areas readable to comply with a function patterns specification; determining an extent of free cells and derived cells according to a code word specification; calculating decode input values for free cells such that the appearance of the free cells compared to respective areas of the input image complies with a visual perceptual similarity criterion and with the code word specification; and calculating decode input values for derived cells based on the free cells decode input values and in compliance with the code word specification.

Claims

1. A computerized method of generating a readable two-dimensional code encoding a message based on an input image, the two-dimensional code including function patterns and cells, the method comprising:

calculating the function patterns; and

calculating decoded values for the cells based on at least the encoded message, such that an appearance of a portion of the cells complies with a visual similarity criterion when compared with respective areas of the input image associated with the portion of the cells.

2. The computerized method according to claim 1, further comprising determining the respective areas of the input image associated with the portion of the cells.

3. The computerized method according to claim 2, wherein said determining the respective areas is based on a saliency criterion.

4. The computerized method according to claim 1, further comprising fusing the input image with the calculated functions patterns and the cells having the calculated decoded values to form the readable two-dimensional code.

5. The computerized method according to claim 3, further comprising fusing the input image with the calculated functions patterns and the cells having the calculated decoded values to form the readable two-dimensional code.

6. The computerized method according to claim 1, wherein the input image is re-sampled to fit dimensions supported by a two-dimensional code specification.

7. The computerized method according to claim 1, wherein the input image is cropped to fit dimensions supported by a two-dimensional code specification.

8. The computerized method according to claim 1, wherein the visual similarity criterion is based on an optimization method.

9. The computerized method according to claim 8, wherein the optimization method is based on a distance measure between pixel colour values of the cells of the readable two-dimensional code and corresponding pixel colour values in the input image.

10. The computerized method according to claim 9, wherein at least two colour ranges of the respective areas of the input image are used in the optimization method, said colour ranges being selected according to a criterion that is based on a probability measure of a likelihood that a printed version of the readable two-dimensional code has a small distance to the input image.