Code recognition method, device and computer readable storage medium for storing code recognition method

• US 8,965,128 B2
• Filed: 12/17/2010
• Issued: 02/24/2015
• Est. Priority Date: 12/01/2010
• Status: Active Grant

• Current Assignee: Institute For Information Industry
• Original Assignee: Institute For Information Industry
• Inventors: Zeng, Yi-Chong, Chen, Jing-Fung
• Primary Examiner(s): Goradia, Shefali
• Assistant Examiner(s): Lee, Jonathan S
• Application Number:
  US12/971,176
• Publication Number:
  US 20120141030A1
• Time in Patent Office: 1,530 Days
• Field of Search: None
• US Class Current: 382/182
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 30/36 Matching; Classification

Abstract

A code recognition method includes the following steps: a first code-image block is received. Wherein, several first codes are displayed on the first code-image block. The first code-image block is partitioned into several second code-image blocks. Wherein, each of the second code-image blocks displays a second code respectively. Each of the second codes is one of the first codes. Each of the second code-image blocks is recognized as several third codes corresponding to each of the second codes respectively. Some of the neighboring second code-image blocks are combined to form several third code-image blocks. Wherein, each of the third code-image blocks displays a first code set, which comprises some of the second codes. Each of the third code-image blocks is recognized as a second code set corresponding to each of the first code sets respectively. Wherein, each of the second code sets includes the codes selected from the third codes.

Claims

1. A code recognition method comprising:

receiving a first code-image block, wherein a plurality of first displayed codes are displayed on the first code-image block;

partitioning the first code-image block into a plurality of second code-image blocks, wherein each of the second code-image blocks displays a second displayed code respectively, each of the second displayed codes displayed in each second code-image block is one of the first displayed codes;

recognizing each of the second code-image blocks as a plurality of third recognized codes corresponding to each of the second displayed codes respectively;

forming a plurality of possible candidates based on the third recognized codes corresponding to adjacent ones of the second displayed codes, wherein each of the possible candidates comprises at least two of the third recognized codes;

combining some of the neighboring second code-image blocks to form a plurality of third code-image blocks, wherein each of the third code-image blocks displays a first displayed code set, which comprises some of the second displayed codes; and

calculating a code-set-image differences between one of the third code-image blocks and each of the possible candidates, and selecting one of the possible candidates according to the code-set-image differences, without considering a grammatical meaning of each of the possible candidates, as a second recognized code set corresponding to the first displayed code set in the one of the third code-image blocks;

wherein the step of recognizing each of the second code-image blocks as the third recognized codes corresponding to each of the second displayed codes respectively comprises;

comparing each of the second code-image blocks with multiple code images of multiple candidate codes stored in a code-image database to obtain the third recognized codes corresponding to each of the second displayed codes selected from the candidate codes.

2. The code recognition method of claim 1, wherein the step of comparing each of the second code-image blocks with the code images of the candidate codes stored in the code-image database comprises:

calculating a plurality of code-image differences between each of the second code-image blocks and the code images of the candidate codes,

wherein the third recognized codes corresponding to each of the second displayed codes are obtained according to the code-image differences.

3. The code recognition method of claim 2, wherein the code-image differences are calculated utilizing a non-linear difference calculating algorithm.

4. The code recognition method of claim 1 further comprising:

receiving an image for recognition; and

capturing the first code-image block from the image for recognition.

5. The code recognition method of claim 1 further comprising:

receiving an image for recognition;

capturing the first code-image block from the image for recognition; and

normalizing the captured first code-image block.

6. The code recognition method of claim 5, wherein the first code-image block is normalized utilizing an affine mapping model, Scale-invariant feature transform (SIFT) or Speeded Up Robust Features (SURF).

7. A non-transitory computer readable storage medium with a computer program to execute a code recognition method, wherein the code recognition method comprises:

receiving a first code-image block, wherein a plurality of first displayed codes are displayed on the first code-image block;

partitioning the first code-image block into a plurality of second code-image blocks, wherein each of the second code-image blocks displays a second displayed code respectively, each of the second displayed codes displayed in each second code-image block is one of the first displayed codes;

recognizing each of the second code-image blocks as a plurality of third recognized codes corresponding to each of the second displayed codes respectively;

forming a plurality of possible candidates based on the third recognized codes corresponding to adjacent ones of the second displayed codes, wherein each of the possible candidates comprises at least two of the third recognized codes;

combining some of the neighboring second code-image blocks to form a plurality of third code-image blocks, wherein each of the third code-image blocks displays a first displayed code set, which comprises some of the second displayed codes; and

calculating a code-set-image differences between one of the third code-image blocks and each of the possible candidates, and selecting one of the possible candidates according to the code-set-image differences, without considering a grammatical meaning of each of the possible candidates, as a second recognized code set corresponding to the first displayed code set in the one of the third code-image blocks;

wherein the step of recognizing each of the second code-image blocks as the third recognized codes corresponding to each of the second displayed codes respectively comprises;

comparing each of the second code-image blocks with multiple code images of multiple candidate codes stored in a code-image database to obtain the third recognized codes corresponding to each of the second displayed codes selected from the candidate codes.

8. A code recognition device comprising:

a processing unit configured to receive a first code-image block, wherein a plurality of first displayed codes are displayed on the first code-image block,

partition the first code-image block into a plurality of second code-image blocks, wherein each of the second code-image blocks displays a second displayed code respectively, each of the second displayed codes displayed in each second code-image block is one of the first displayed codes,

recognize each of the second code-image blocks as a plurality of third recognized codes corresponding to each of the second displayed codes respectively,

form a plurality of possible candidates based on the third recognized codes corresponding to adjacent ones of the second displayed codes, wherein each of the possible candidates comprises at least two of the third recognized codes,

combine some of the neighboring second code-image blocks to form a plurality of third code-image blocks, wherein each of the third code-image blocks displays a first displayed code set, which comprises some of the second displayed codes, and

calculate a code-set-image differences between one of the third code-image blocks and each of the possible candidates, and select one of the possible candidates according to the code-set-image differences, without considering a grammatical meaning of each of the possible candidates, as a second recognized code set corresponding to the first displayed code set in the one of the third code-image blocks;

a code-image database electrically connected to the processing unit, the code-image database storing multiple code images of multiple candidate codes, wherein the processing unit is further configured to compare each of the second code-image blocks with the code images of the candidate codes stored in the code-image database to obtain the third recognized codes corresponding to each of the second displayed codes selected from the candidate codes; and

an output unit electrically connected to the processing unit, configured to output one of the second code sets.

9. The code recognition device of claim 8, wherein the processing unit is further configured to

calculate a plurality of code-image differences between each of the second code-image blocks and the code images of the candidate codes,

wherein the processing unit obtains the third recognized codes are corresponding to each of the second displayed codes according to the code-image differences.

10. The code recognition device of claim 8, wherein the processing unit is further configured to

compare each of the third code-image blocks with the code images corresponding to the third recognized codes stored in the code-image database to obtain the second recognized code sets, which comprises the codes selected from the third recognized codes, corresponding to the first displayed code sets.

11. The code recognition device of claim 8, wherein the processing unit is further configured to receive an image for recognition, and capture the first code-image block from the image.

12. The code recognition device of claim 11 further comprising:

an image sensor, which is electrically connected to the processing unit, for sensing the image.

13. The code recognition device of claim 11 further comprising:

a data transmission interface, which is electrically connected to the processing unit, wherein the image for recognition is received through the data transmission interface.