Description:FIELD OF INVENTION

[001] The present invention relates to field of image processing. Particularly, the present invention relates to character recognition; recognizing digital ink; Document-oriented image-based pattern recognition (scanning, transmission or reproduction of documents). More particularly, the present invention is used for optical character recognition so that they can be electronically edited, searched, stored more compactly, displayed online, and used in machine processes such as cognitive computing, machine translation, (extracted) text-to-speech, key data and text mining.

BACKGROUND OF THE INVENTION

[002] Optical character recognition or optical character reader (OCR) is the electronic or mechanical conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene photo (for example the text on signs and billboards in a landscape photo) or from subtitle text superimposed on an image (for example: from a television broadcast). Widely used as a form of data entry from printed paper data records – whether passport documents, invoices, bank statements, computerized receipts, business cards, mail, printed data, or any suitable documentation – it is a common method of digitizing printed texts so that they can be electronically edited, searched, stored more compactly, displayed online, and used in machine processes such as cognitive computing, machine translation, (extracted) text-to-speech, key data and text mining.

[003] Despite significant technical advancement in OCR technology, current implementations face notable limitations. Many OCR systems rely on remote connections to large database or cloud based resources to perform text recognition. This dependency often introduces latency, as the system must transmit data to external servers, process it, and then retrieve results. Such delays can hinder real time applications or increase processing time in scenario with limited or unstable internet connectivity. Additionally, reliance on external server raises concern about data security and privacy. Particularly, for sensitive and confidential information. Moreover, to match the scanned text with large databases takes huge time and processing capacity that creates another challenge in fast recognition of optical characters.

[004] There are several patent applications comprising a system for optical character recognition. The United States Application US20020012462A1 discloses an image processing method or device invented to reduce the ratio of erroneously recognized non-character elements in optical character recognition (OCR) regarding a color document that includes character images and other types of images, wherein the extracted character image data is checked to determine whether a color change exists in each character image, and wherein if no color change exists, the character image data is converted into character code data, but where a color change does exist, the character image data is not converted into character code data. However, the cited applications does not contain localized database, thereby creating huge time for character recognition.

[005] In order to overcome the problem associated with the state of arts, there is a need for the development of an efficient system for optical character recognition using multiple databases that can overcome the aforesaid limitations in a more efficient manner.

OBJECTIVE OF THE INVENTION

[006] The primary objective of the present invention is to provide a system and method for optical character recognition using multiple databases.

[007] Another objective of the present invention is to provide fast recognition of characters from document through the localized database.

[008] Another objective of the present invention is to provide a simple and cost-effective way for optical character recognition.

[009] Yet another objective of the present is to provide a scalable and versatile system.

[0010] Yet another objective of the present invention is to provide a system for optical character recognition system that is capable of working in system with low processing capability.

[0011] Yet another objective of the present invention is to provide an optical character recognition system that utilizes multiple databases for optical character recognition.

[0012] Yet another objective of the present invention is to achieve high accuracy in optical character recognition even through a low storage and low computing power handheld devices.

[0013] Other objectives and advantages of the present invention will become apparent from the following description taken in connection with the accompanying drawings, wherein, by way of illustration and example, the aspects of the present invention are disclosed.

BRIEF DESCRIPTION OF DRAWINGS
[0014] The present invention will be better understood after reading the following detailed description of the presently preferred aspects thereof with reference to the appended drawings, in which the features, other aspects and advantages of certain exemplary embodiments of the invention will be more apparent from the accompanying drawing in which:

[0015] Figure 1 illustrates a system for optical character recognition using multiple databases; and

[0016] Figure 2 illustrates flowchart for an exemplary use case of the system for optical character recognition using multiple databases.

SUMMARY OF THE INVENTION
[0017] The present invention relates to a system for optical character recognition using multiple databases. The system for optical character recognition using multiple databases, comprises of a plurality of handheld devices; one or more camera integrated on the each of the plurality of handheld devices for scanning a document; one or more processors integrated on each of the plurality of handheld device and connected to the one or more camera; a memory connected to the one or more processors, comprising a first database; an optical character recognition module for analyzing the shapes and structures of characters in the document and match them to corresponding text in a predefined set of characters and/or templates stored in the first database so as to convert text of the document into a digital format capable of being edited, searched, and processed by computers; and a server wirelessly connected to the plurality of handheld devices, comprising: a second database, a third database, a fourth database. Further, the processor is configured to sequentially match the analyzed text with the second database, third database, and fourth database, upon not detecting a match in the preceding databases.

[0018] The present invention also provides a method for optical character recognition using multiple databases. The method comprising steps of: scanning of the document through the one or more camera; preprocessing the image of the document through the optical character recognition module to enhance the quality and readability through noise reduction, image straightening, and contrast enhancement to improve the clarity of text; segmenting the preprocessed image by the optical character recognition module to identify regions containing text by detecting patterns and shapes that resemble characters, words, and paragraphs within the document; and analyzing the shapes and patterns of individual characters by comparing the visual features of each character against a predefined set of templates stored in the first database to determine the character match.

DETAILED DESCRIPTION OF INVENTION
[0019] The following detailed description and embodiments set forth herein below are merely exemplary out of the wide variety and arrangement of instructions which can be employed with the present invention. The present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. All the features disclosed in this specification may be replaced by similar other or alternative features performing similar or same or equivalent purposes. Thus, unless expressly stated otherwise, they all are within the scope of the present invention.

[0020] Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the invention. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.

[0021] The terms and words used in the following description and claims are not limited to the bibliographical meanings but are merely used to enable a clear and consistent understanding of the invention. Accordingly, it should be apparent to those skilled in the art that the following description of exemplary embodiments of the present invention are provided for illustration purpose only and not for the purpose of limiting the invention.

[0022] It is to be understood that the singular forms “a,” “an,” and “the” include plural referents unless the context clearly dictates otherwise.

[0023] It should be emphasized that the term “comprises/comprising” when used in this specification is taken to specify the presence of stated features, integers, steps, or components but does not preclude the presence or addition of one or more other features, integers, steps, components, or groups thereof.

[0024] Accordingly, the present invention relates to field of image processing. Particularly, the present invention relates to character recognition; recognizing digital ink; Document-oriented image-based pattern recognition (scanning, transmission or reproduction of documents). More particularly, the present invention is used for optical character recognition so that they can be electronically edited, searched, stored more compactly, displayed online, and used in machine processes such as cognitive computing, machine translation, (extracted) text-to-speech, key data and text mining.

[0025] In an embodiment, as shown in Figure 1, a system for optical character recognition using multiple databases comprises of a plurality of handheld devices (102); one or more camera (104) integrated on the each of the plurality of handheld devices (102) for scanning a document; one or more processors (106) integrated on each of the plurality of handheld device (102) and connected to the one or more camera (104); a memory (108) connected to the one or more processors (106), comprising a first database (110); an optical character recognition module (112) operably connected to the one or more processors (106) for analyzing the shapes and structures of characters in the document and match them to corresponding text in a predefined set of characters and/or templates stored in the first database (110) so as to convert text of the document into a digital format capable of being edited, searched, and processed by computers; and a server (114) wirelessly connected to the plurality of handheld devices (102), comprising: a second database (116), a third database (118), a fourth database (120).

[0026] The plurality of handheld devices (102) are configured to provide optical character recognition. The handheld devices (102) may comprises of a user interface (102a) to access the optical character recognition module (112) so as to detect the characters in the document. In an exemplary embodiment, the user interface (102a) may be accessible through an application installed on the handheld device (102), a website accessible through a browser installed on the handheld device (102), and the alike. In an exemplary embodiment of the present invention, the handheld device (102) may be selected from a group consisting of such as, but not limited to, a smart phone, a tablet, laptop, phablet, and the alike.

[0027] The one or more cameras (104) are integrated on the each of the plurality of handheld devices (102). The one or cameras (104) are configured to capture the images of the document. In an exemplary embodiment of the present invention, the document may be selected from a group consisting of such as, but not limited to, a photo of a document, a scene photo such as text on signs and billboards in a photo, or from subtitle text superimposed on an image, and the alike. In another exemplary embodiment, the plurality of handheld device (104) is configured to receive scanned file of the document through Wi-Fi, Bluetooth, internet connection, and the alike.

[0028] The one or more processors (106) are integrated on each of the plurality of handheld device (102) and connected to the one or more camera (104). The processor (106) is configured to process images captured by the one or more cameras (104) to enhance the quality and extract relevant information from digital images before the digital images are further analyzed and processed. The one or more processors (106) are configured to correct, filter, normalize, or enhance the images in order to improve their suitability for subsequent analysis.

[0029] The processor (106) is configured to perform operations such as noise reduction, which reduces unwanted artifacts or random variations in the image; image resizing, which adjusts the image dimensions to meet specific requirements; contrast enhancement, which adjusts the image to improve visibility of objects or features; and image normalization, which ensures that the pixel values are scaled to a consistent range. Other operations may involve color space conversion, edge detection, morphological operations, or image segmentation, and the alike. By applying image pre-processing techniques, the quality and reliability of detection by optical character recognition module (112) is significantly improved.

[0030] The memory (108) is connected to the one or more processors (106). The memory (108) comprises of the first database (110). The one or more processors (106) are configured to store the characters in the first database (110) that are detected by the optical character recognition module (112) above a predefined number of time. The one or more processors (110) are configured to store the frequently detected characters in the localized first database (110) so as to accelerate the detection process.

[0031] The server (114) is wirelessly connected to the plurality of handheld devices (102). The server (114) is a computing device or a group of computing device that provides information to the other devices called clients. In an embodiment, the server (114) may work on an architecture called the client–server model. The servers (114) may provide various functionalities, often called "services", such as sharing data or resources among multiple clients or performing computations for a client. In an exemplary embodiment, the server (114) may be selected from a group consisting of such as, but not limited to, database servers, file servers, mail servers, print servers, web servers, game servers, and application servers, and the alike, or a combination thereof. The server (114) comprising: a second database (116), a third database (118), and a fourth database (120). The fourth database (120) is real time information available on internet.

[0032] The optical character recognition module (112) is operably connected to the one or more processors (106) for analyzing the shapes and structures of characters in the document and match them to corresponding text in a predefined set of characters and/or templates stored in the first database (110) so as to convert text of the document into a digital format capable of being edited, searched, and processed by computers.

[0033] The optical character recognition module (112) is configured to preprocess the image to enhance the quality and readability through noise reduction, image straightening, and contrast enhancement to improve the clarity of text; segmenting the preprocessed image to identify regions containing text by detecting patterns and shapes that resemble characters, words, and paragraphs within the document; analyzing the shapes and patterns of individual characters by comparing the visual features of each character against a predefined set of templates stored in the first database (110) to determine the character match. The optical character recognition module (112) utilized orchestrator and parser.

[0034] The optical character recognition module (112) is configured to: match the analyzed text with the second database (116), upon not detecting a match in the first database (110); match the analyzed text with the third database (118), upon not detecting a match in the second database (116); match the analyzed text with the fourth database (118), upon not detecting a match in the third database (116).

[0035] In an exemplary use case of the present invention, as shown in Figure 2, we consider the USE CASE of doctor’s prescription, an user interface (102a) running on doctors handheld device (102) i.e. mobile may just have a PERSONAL library/First database (110) (which is again self-trainable and editable for multiple languages) which makes doctors app very light weight. If we capture the most used words by the doctor in the prescription, we will be surprised to find that, a doctor, over an extensively longer period of time, typically uses approximately 300-500 medicines in entire life of his practice. So if we can capture these 500 medicines, and we train our solution to recognize these words first, then recognition can happen quickly on mobile. This is first level of storage called PERSONAL Dictionary, in LOCAL space of the handheld device (102). As first database (110) is a small list the checking can be done at lightning speed, this will allow low end mobile sets can even do this job easily, in very short time line. If the computing power is good then we can also store the next dictionary called GROUP Dictionary/second database (116) on the handheld device (102), and carry out next OCR activity. Next level of dictionary is called ORGANISATION/SPECIALISATION based Dictionary stored in the third database (118), and the solution will look into dictionary stored in the third database (118), upon not detecting the word in GROUP dictionary stored in the second database (116). And lastly it is whole WEB/ fourth database (120).

[0036] In an embodiment, the present invention also provides a method for optical character recognition using multiple databases, comprising the following steps:-
• scanning of the document through the one or more camera (104);
• preprocessing the image of the document through the optical character recognition module (112) to enhance the quality and readability through noise reduction, image straightening, and contrast enhancement to improve the clarity of text;
• segmenting the preprocessed image by the optical character recognition module (112) to identify regions containing text by detecting patterns and shapes that resemble characters, words, and paragraphs within the document;
• analyzing the shapes and patterns of individual characters by comparing the visual features of each character against a predefined set of templates stored in the first database (110) to determine the character match.

[0037] In an embodiment, as shown in Figure 2, the method for optical character recognition using multiple databases, comprises of the following steps:-
• matching the analyzed text with the second database (116), upon not detecting a match in the first database (110);
• matching the analyzed text with the third database (118), upon not detecting a match in the second database (116);
• matching the analyzed text with the fourth database (118), upon not detecting a match in the third database (116).

[0038] In an embodiment the advantages of the present invention are enlisted herein:
• The present invention provides fast recognition of characters from document through the localized database.
• The present invention provides a simple and cost-effective way for optical character recognition.
• The present provides a scalable and versatile system for optical character recognition.
• The present invention provides a system for optical character recognition system that is capable of working in system with low processing capability.
• The present invention saves time of user by eliminating the need to manually enter the data.
• The present invention makes the texts of scanned document searchable.
• The present invention provides a system for optical character recognition that utilizes multiple databases for optical character recognition.
• The present invention achieves high accuracy in optical character recognition even through a low storage and low computing power handheld devices.

[0039] While this invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims.
, Claims:1. A system for optical character recognition, comprising:
• a plurality of handheld devices (102);
• one or more camera (104) integrated on the each of the plurality of handheld devices (102) for scanning a document;
• one or more processors (106) integrated on each of the plurality of handheld device (102) and connected to the one or more camera (104);
• a memory (108) connected to the one or more processors (106), comprising a first database (110);
• an optical character recognition module (112) operably connected to the one or more processors (106) for analyzing the shapes and structures of characters in the document and match them to corresponding text in a predefined set of characters and/or templates stored in the first database (110) so as to convert text of the document into a digital format capable of being edited, searched, and processed by computers; and
• a server (114) wirelessly connected to the plurality of handheld devices (102), comprising: a second database (116), a third database (118), a fourth database (120).

2. The system (100) as claimed in claim 1, wherein the document is selected from a photo of a document, a scene photo such as text on signs and billboards in a photo, or from subtitle text superimposed on an image.

3. The system (100) as claimed in claim 1, wherein the fourth database (120) is real time information available on internet.

4. The system (100) as claimed in claim 1, wherein the optical character recognition module () is configured to:
a. preprocess the image to enhance the quality and readability through noise reduction, image straightening, and contrast enhancement to improve the clarity of text;
b. segmenting the preprocessed image to identify regions containing text by detecting patterns and shapes that resemble characters, words, and paragraphs within the document;
c. analyzing the shapes and patterns of individual characters by comparing the visual features of each character against a predefined set of templates stored in the first database (110 )to determine the character match;

5. The system (100) as claimed in claim 1, wherein the optical character recognition module (112) is configured to:
a. match the analyzed text with the second database (116), upon not detecting a match in the first database (110);
b. match the analyzed text with the third database (118), upon not detecting a match in the second database (116);
c. match the analyzed text with the fourth database (118), upon not detecting a match in the third database (116);

6. The system (100) as claimed in claim 1, wherein the one or more processors (110) are configured to store the characters in the first database (110), that are detected by the optical character recognition module (112) above a predefined number of time.

7. A method for optical character recognition using the system (100) as claimed in claim 1, comprising steps of:
a. scanning of the document through the one or more camera (104);
b. preprocessing the image of the document through the optical character recognition module (112) to enhance the quality and readability through noise reduction, image straightening, and contrast enhancement to improve the clarity of text;
c. segmenting the preprocessed image by the optical character recognition module (112) to identify regions containing text by detecting patterns and shapes that resemble characters, words, and paragraphs within the document;
d. analyzing the shapes and patterns of individual characters through the optical character recognition module (112) by comparing the visual features of each character against a predefined set of templates stored in the first database (110) to determine the character match;

8. The method as claimed in claim 7, wherein the method for optical character recognition using multiple database comprising steps of:
a. matching the analyzed text with the second database (116) through the optical character recognition module (112), upon not detecting a match in the first database (110);
b. matching the analyzed text with the third database (118) through the optical character recognition module (112), upon not detecting a match in the second database (116);
c. matching the analyzed text with the fourth database (118) through the optical character recognition module (112), upon not detecting a match in the third database (116);