Image processing apparatus, image processing method and computer-readable storage medium

• US 9,563,812 B2
• Filed: 04/08/2015
• Issued: 02/07/2017
• Est. Priority Date: 04/08/2015
• Status: Active Grant

• Current Assignee: Toshiba Tec Corporation (Toshiba Corporation)
• Original Assignee: Toshiba Tec Corporation (Toshiba Corporation)
• Inventors: Yasunaga, Masaaki, Taira, Kazuki
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US14/681,933
• Publication Number:
  US 20160300116A1
• Time in Patent Office: 671 Days
• Field of Search: 382180-182, 382/190, 382/225
• US Class Current: 1/1
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06V 10/809 of classification results, e.g. where the classifiers operate on the same input data
• CPC Class Codes: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks

Abstract

According to one embodiment, an image processing apparatus includes a calculation unit and a recognition unit. The calculation unit is configured to calculate a first similarity degree group which is composed of similarity degrees between respective characters constituting a first character string appearing on a first image and respective candidate characters in a candidate character group, and to calculate a second similarity degree group which is composed of similarity degrees between respective characters constituting a second character string appearing on a second image and the respective candidate characters in the candidate character group.

Claims

1. An image processing apparatus comprising:

a first interface configured to receive a first image from a first external apparatus;

a second interface configured to receive a second image from a second external apparatus, wherein the first image is different from the second image; and

a processor configured to;

extract a first character string appearing on the first image, and a second character string appearing on the second image;

determine that both the first character string and the second character string correspond to a photographed subject in the first image and second image;

cut out each of the characters constituting the first character string, in units of a character;

cut out each of the characters constituting the second character string, in units of a character;

calculate a first similarity degree group which is composed of similarity degrees between the respective characters constituting the first character string and respective candidate characters in a candidate character group;

calculate a second similarity degree group which is composed of similarity degrees between the respective characters constituting the second character string and the respective candidate characters in the candidate character group; and

recognize a character string of the first subject, based on the first similarity degree group and the second similarity degree group.

2. The image processing apparatus of claim 1,

wherein:

the processor is further configured to determine that both the first character string and the second character string correspond to the subject, based on a positional relationship between the first external apparatus and the second external apparatus, a position of the first character string appearing on the first image, and a position of the second character string appearing on the second image,

the first image is generated by the first external apparatus photographing the subject, and

the second image is generated by the second external apparatus photographing the subject.

3. The image processing apparatus of claim 1, wherein the processor is further configured to:

calculate a first calculation value group based on a value of a sum of the similarity degrees included in the first similarity degree group and the similarity degrees included in the second similarity degree group, in units of each of corresponding digits between the first character string and the second character string and in units of a candidate character in the candidate character group,

extract maximum values in the first calculation value group in the respective digits, and

recognize a set of candidate characters corresponding to the maximum values as the character string in the first subject.

4. The image processing apparatus of claim 3, wherein the processor is further configured to:

multiply each of the similarity degrees included in the first similarity degree group by a first weighting factor, which depends on a position of a character string appearing on an image, based on a position of the second character string appearing on the second image, and

multiply each of the similarity degrees included in the second similarity degree group by the first weighting factor, based on the position of the second character string appearing on the second image.

5. The image processing apparatus of claim 3, wherein the recognition unit processor is further configured to:

multiply each of the similarity degrees included in the first similarity degree group by a second weighting factor, which depends on pixel information of a character string appearing on an image, based on pixel information of the second character string appearing on the second image, and

multiply each of the similarity degrees included in the second similarity degree group by the second weighting factor, based on the pixel information of the second character string appearing on the second image.

6. The image processing apparatus of claim 1, wherein each of the similarity degrees included in the first similarity degree group and each of the similarity degrees included in the second similarity degree group is a likelihood.

7. The image processing apparatus of claim 1, wherein the similarity degrees included in the first similarity degree group have no relationship of dependency, and the similarity degrees included in the second similarity degree group have no relationship of dependency.

8. An image processing method comprising:

extracting a first character string appearing on a first image received from a first external apparatus;

extracting a second character string appearing on a second image received from a second external apparatus, wherein the first image is different from the second image;

determining that both the first character string and the second character string correspond to a photographed subject in the first image and second image;

cutting out each of the characters constituting the first character string, in units of a character;

cutting out each of the characters constituting the second character string, in units of a character;

calculating a first similarity degree group which is composed of similarity degrees between the respective characters constituting the first character string and respective candidate characters in a candidate character group;

calculating a second similarity degree group which is composed of similarity degrees between the respective characters constituting the second character string and the respective candidate characters in the candidate character group; and

recognizing a character string of the first subject, based on the first similarity degree group and the second similarity degree group.

9. A computer-readable, non-transitory storage medium having stored thereon a program which is executable by a computer, the program controlling the computer to execute functions of:

extracting a first character string appearing on a first image received from a first external apparatus;

extracting a second character string appearing on a second image received from a second external apparatus, wherein the first image is different from the second image;

determining that both the first character string and the second character string correspond to a first photographed subject in the first image and second image;

cutting out each of the characters constituting the first character string, in units of a character;

cutting out each of the characters constituting the second character string, in units of a character;

calculating a first similarity degree group which is composed of similarity degrees between the respective characters constituting the first character string and respective candidate characters in a candidate character group;

calculating a second similarity degree group which is composed of similarity degrees between the respective characters constituting the second character string and the respective candidate characters in the candidate character group; and

recognizing a character string of the first subject, based on the first similarity degree group and the second similarity degree group.