Device and method for determining characteristics of a currency note

Patent metadata

Field	Value
Publication number	US-10339377-B2
Application number	US-201715810376-A
Country	US
Kind code	B2
Filing date	Nov 13, 2017
Priority date	Nov 13, 2017
Publication date	Jul 2, 2019
Grant date	Jul 2, 2019

Abstract

Embodiment of the present disclosure discloses method and device for determining one or more characteristics of currency note. The currency evaluating device is configured to receive image of currency note and detect text from one or more predefined first regions of image. Further, language associated with detected text is identifies and one of single nationality and plurality of nationalities associated with language of currency note is obtained from data source associated with currency evaluating device. When single nationality is obtained, nationality of currency note is identified to be said single nationality. When plurality of nationalities is obtained, nationality of currency note is identified from plurality of nationalities using Optical Character Recognition (OCR). Upon identifying nationality, one or more characteristics of currency note is identified by extracting object features on image based on identified nationality.

First claim

The invention claimed is:

1. A method for determining one or more characteristics of a currency note, comprising:
receiving, by a currency evaluating device, an image of a currency note;
detecting, by the currency evaluating device, text from one or more predefined first regions of the image;
identifying, by the currency evaluating device, language associated with the detected text;
obtaining, by the currency evaluating device, one of a single nationality or a plurality of nationalities associated with the language of the currency note from a data source associated with the currency evaluating device;
identifying, by the currency evaluating device, nationality of the currency note as said single nationality, when the single nationality is obtained;
identifying, by the currency evaluating device, nationality of the currency note from the plurality of nationalities using Optical Character Recognition (OCR), when the plurality of nationalities is obtained; and
determining, by the currency evaluating device, the one or more characteristics of the currency note by extracting object features of the image based on the identified nationality.

2. The method as claimed in claim 1 , wherein the one or more predefined first regions are selected based on a predefined probability ranking.

3. The method as claimed in claim 1 , wherein the identifying the nationality using the OCR comprises:
performing electronic OCR on the detected text to digitize the detected text;
obtaining information associated with the digitized detected text from the data source; and
identifying the nationality based on the information, wherein the information is compared with predefined information in the data source to identify the nationality.

4. The method as claimed in claim 1 , wherein the object features are extracted from one or more predefined second regions of the image, wherein the one or more predefined second regions are selected based on the identified nationality.

5. The method as claimed in claim 4 , wherein extracting the object features comprises:
performing object segmentation on the one or more predefined second regions;
detecting one or more objects on the image based on the object segmentation and predefined object features in the data source; and
extracting the object features based on the detected one or more objects.

6. The method as claimed in claim 1 , wherein the one or more characteristics comprises at least one of series and denomination of the currency note.

7. A currency evaluating device for determining one or more characteristics of a currency note, comprises:
a processor; and
a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which, on execution, cause the processor to:
receive an image of a currency note;
detect text from one or more predefined first regions of the image;
identify language associated with the detected text;
obtain one of a single nationality or a plurality of nationalities associated with the language of the currency note from a data source associated with the currency evaluating device;
identify nationality of the currency note as said single nationality, when the single nationality is obtained;
identify nationality of the currency note from the plurality of nationalities using Optical Character Recognition (OCR), when the plurality of nationalities is obtained; and
determine the one or more characteristics of the currency note by extracting object features of the image based on the identified nationality.

8. The currency evaluating device as claimed in claim 7 , wherein the one or more predefined first regions are selected based on a predefined probability ranking.

9. The currency evaluating device as claimed in claim 7 , wherein the identifying the nationality using the OCR comprises:
performing electronic OCR on the detected text to digitize the detected text;
obtaining information associated with the digitized detected text from the data source; and
identifying the nationality based on the information, wherein the information is compared with predefined information in the data source to identify the nationality.

10. The currency evaluating device as claimed in claim 7 , wherein the object features are extracted from one or more predefined second regions on the image, wherein the one or more predefined second regions are selected based on the identified nationality.

11. The currency evaluating device as claimed in claim 10 , wherein extracting the object features comprises:
performing object segmentation on the one or more predefined second regions;
detecting one or more objects on the image based on the object segmentation and predefined object features in the data source; and
extracting the object features based on the detected one or more objects.

12. The currency evaluating device as claimed in claim 7 , wherein the one or more characteristics comprises at least one of series and denomination of the currency note.

Assignees

• Toshiba Kk
• Toshiba Infrastructure Systems & Solutions Corp

Inventors

• Joseph Rajkumar
• Sukumar Arya
• TIRUVEEDHULA Vijaya Kumar

Classifications

• G06V30/147 Primary

  Determination of region of interest · CPC title

• G06V30/416

  Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors · CPC title

• G06V30/153

  using recognition of characters or words · CPC title

• G06V30/10

  Character recognition · CPC title

• G06K9/4642

  Physics · mapped topic