Optical character recognition or optical character reader (OCR) is the
electronic
Electronic may refer to:
*Electronics, the science of how to control electric energy in semiconductor
* ''Electronics'' (magazine), a defunct American trade journal
*Electronic storage, the storage of data using an electronic device
*Electronic co ...
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
Data entry is the process of digitizing data by entering it into a computer system for organization and management purposes. It is a person-based process and is "one of the important basic" tasks needed when no machine-readable version of the inf ...
from printed paper data records – whether passport documents, invoices,
bank statements, computerized receipts, business cards, mail, printouts of static-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 on-line, and used in machine processes such as
cognitive computing
Cognitive computing (CC) refers to technology platforms that, broadly speaking, are based on the scientific disciplines of artificial intelligence and signal processing. These platforms encompass machine learning, reasoning, natural languag ...
,
machine translation
Machine translation, sometimes referred to by the abbreviation MT (not to be confused with computer-aided translation, machine-aided human translation or interactive translation), is a sub-field of computational linguistics that investigates t ...
, (extracted)
text-to-speech
Speech synthesis is the artificial production of human speech. A computer system used for this purpose is called a speech synthesizer, and can be implemented in software or hardware products. A text-to-speech (TTS) system converts normal langua ...
, key data and
text mining
Text mining, also referred to as ''text data mining'', similar to text analytics, is the process of deriving high-quality information from text. It involves "the discovery by computer of new, previously unknown information, by automatically extract ...
. OCR is a field of research in
pattern recognition
Pattern recognition is the automated recognition of patterns and regularities in data. It has applications in statistical data analysis, signal processing, image analysis, information retrieval, bioinformatics, data compression, computer graphics ...
,
artificial intelligence
Artificial intelligence (AI) is intelligence—perceiving, synthesizing, and inferring information—demonstrated by machines, as opposed to intelligence displayed by animals and humans. Example tasks in which this is done include speech r ...
and
computer vision.
Early versions needed to be trained with images of each character, and worked on one font at a time. Advanced systems capable of producing a high degree of recognition accuracy for most fonts are now common, and with support for a variety of digital image file format inputs. Some systems are capable of reproducing formatted output that closely approximates the original page including images, columns, and other non-textual components.
History
Early optical character recognition may be traced to technologies involving telegraphy and creating reading devices for the blind.
In 1914,
Emanuel Goldberg
Emanuel Goldberg ( he, עמנואל גולדברג; yi, עמנואל גאָלדבערג; russian: Эмануэль Гольдберг) (born: 31 August 1881; died: 13 September 1970) was an Israeli physicist and inventor. He was born in Moscow a ...
developed a machine that read characters and converted them into standard telegraph code. Concurrently, Edmund Fournier d'Albe developed the
Optophone, a handheld scanner that when moved across a printed page, produced tones that corresponded to specific letters or characters.
In the late 1920s and into the 1930s,
Emanuel Goldberg
Emanuel Goldberg ( he, עמנואל גולדברג; yi, עמנואל גאָלדבערג; russian: Эмануэль Гольдберг) (born: 31 August 1881; died: 13 September 1970) was an Israeli physicist and inventor. He was born in Moscow a ...
developed what he called a "Statistical Machine" for searching
microfilm
Microforms are scaled-down reproductions of documents, typically either photographic film, films or paper, made for the purposes of transmission, storage, reading, and printing. Microform images are commonly reduced to about 4% or of the origin ...
archives using an optical code recognition system. In 1931, he was granted USA Patent number 1,838,389 for the invention. The patent was acquired by
IBM.
Blind and visually impaired users
In 1974,
Ray Kurzweil
Raymond Kurzweil ( ; born February 12, 1948) is an American computer scientist, author, inventor, and futurist. He is involved in fields such as optical character recognition (OCR), text-to-speech synthesis, speech recognition technology, and e ...
started the company Kurzweil Computer Products, Inc. and continued development of omni-
font OCR, which could recognize text printed in virtually any font (Kurzweil is often credited with inventing omni-font OCR, but it was in use by companies, including CompuScan, in the late 1960s and 1970s.
[) Kurzweil decided that the best application of this technology would be to create a reading machine for the blind, which would allow blind people to have a computer read text to them out loud. This device required the invention of two enabling technologiesthe CCD ]flatbed scanner
An image scanner—often abbreviated to just scanner—is a device that optically scans images, printed text, handwriting or an object and converts it to a digital image. Commonly used in offices are variations of the desktop ''flatbed scanner'' w ...
and the text-to-speech synthesizer. On January 13, 1976, the successful finished product was unveiled during a widely reported news conference headed by Kurzweil and the leaders of the National Federation of the Blind
The National Federation of the Blind (NFB) is an organization of blind people in the United States. It is the oldest and largest organization led by blind people in the United States. Its national headquarters are in Baltimore, Maryland.
Overvie ...
. In 1978, Kurzweil Computer Products began selling a commercial version of the optical character recognition computer program. LexisNexis
LexisNexis is a part of the RELX corporation that sells data analytics products and various databases that are accessed through online portals, including portals for computer-assisted legal research (CALR), newspaper search, and consumer info ...
was one of the first customers, and bought the program to upload legal paper and news documents onto its nascent online databases. Two years later, Kurzweil sold his company to Xerox
Xerox Holdings Corporation (; also known simply as Xerox) is an American corporation that sells print and electronic document, digital document products and services in more than 160 countries. Xerox is headquartered in Norwalk, Connecticut (ha ...
, which had an interest in further commercializing paper-to-computer text conversion. Xerox eventually spun it off as Scansoft
Nuance Communications, Inc. is an American multinational computer software technology corporation, headquartered in Burlington, Massachusetts, that markets speech recognition and artificial intelligence software.
Nuance merged with its compe ...
, which merged with Nuance Communications
Nuance Communications, Inc. is an American multinational computer software technology corporation, headquartered in Burlington, Massachusetts, that markets speech recognition and artificial intelligence software.
Nuance merged with its compe ...
.
In the 2000s, OCR was made available online as a service (WebOCR), in a cloud computing
Cloud computing is the on-demand availability of computer system resources, especially data storage ( cloud storage) and computing power, without direct active management by the user. Large clouds often have functions distributed over mu ...
environment, and in mobile applications like real-time translation of foreign-language signs on a smartphone
A smartphone is a portable computer device that combines mobile telephone and computing functions into one unit. They are distinguished from feature phones by their stronger hardware capabilities and extensive mobile operating systems, whic ...
. With the advent of smart-phones and smartglasses
Smartglasses or smart glasses are eye or head-worn wearable computers that offer useful capabilities to the user. Many smartglasses include displays that add information alongside or to what the wearer sees. Alternatively, smartglasses are som ...
, OCR can be used in internet connected mobile device applications that extract text captured using the device's camera. These devices that do not have OCR functionality built into the operating system will typically use an OCR API
An application programming interface (API) is a way for two or more computer programs to communicate with each other. It is a type of software interface, offering a service to other pieces of software. A document or standard that describes how ...
to extract the text from the image file captured and provided by the device. The OCR API returns the extracted text, along with information about the location of the detected text in the original image back to the device app for further processing (such as text-to-speech) or display.
Various commercial and open source OCR systems are available for most common writing system
A writing system is a method of visually representing verbal communication, based on a script and a set of rules regulating its use. While both writing and speech are useful in conveying messages, writing differs in also being a reliable fo ...
s, including Latin, Cyrillic, Arabic, Hebrew, Indic, Bengali (Bangla), Devanagari, Tamil, Chinese, Japanese, and Korean characters.
Applications
OCR engines have been developed into many kinds of domain-specific OCR applications, such as receipt OCR, invoice OCR, check OCR, legal billing document OCR.
They can be used for:
* Data entry
Data entry is the process of digitizing data by entering it into a computer system for organization and management purposes. It is a person-based process and is "one of the important basic" tasks needed when no machine-readable version of the inf ...
for business documents, e.g. Cheque
A cheque, or check (American English; see spelling differences) is a document that orders a bank (or credit union) to pay a specific amount of money from a person's account to the person in whose name the cheque has been issued. The pers ...
, passport, invoice, bank statement and receipt
* Automatic number plate recognition
Automatic number-plate recognition (ANPR; see also other names below) is a technology that uses optical character recognition on images to read vehicle registration plates to create vehicle location data. It can use existing closed-circuit te ...
*In airports, for passport recognition and information extraction
Information extraction (IE) is the task of automatically extracting structured information from unstructured and/or semi-structured machine-readable documents and other electronically represented sources. In most of the cases this activity concer ...
* Automatic insurance documents key information extraction
* Traffic sign recognition
* Extracting business card information into a contact list
* More quickly make textual versions of printed documents, e.g. book scanning
Book scanning or book digitization (also: magazine scanning or magazine digitization) is the process of converting physical books and magazines into digital media such as images, electronic text, or electronic books (e-books) by using an imag ...
for Project Gutenberg
Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to "encourage the creation and distribution of eBooks."
It was founded in 1971 by American writer Michael S. Hart and is the oldest digital libr ...
* Make electronic images of printed documents searchable, e.g. Google Books
Google Books (previously known as Google Book Search, Google Print, and by its code-name Project Ocean) is a service from Google Inc. that searches the full text of books and magazines that Google has scanned, converted to text using optical ...
* Converting handwriting in real-time to control a computer (pen computing
Pen computing refers to any computer user-interface using a pen or Stylus (computing), stylus and tablet, over input devices such as a keyboard or a mouse.
Pen computing is also used to refer to the usage of mobile devices such as tablet computers ...
)
* Defeating CAPTCHA
A CAPTCHA ( , a contrived acronym for "Completely Automated Public Turing test to tell Computers and Humans Apart") is a type of challenge–response test used in computing to determine whether the user is human.
The term was coined in 2003 b ...
anti-bot systems, though these are specifically designed to prevent OCR. The purpose can also be to test the robustness of CAPTCHA anti-bot systems.
* Assistive technology for blind and visually impaired users
*Writing the instructions for vehicles by identifying CAD images in a database that are appropriate to the vehicle design as it changes in real time.
*Making scanned documents searchable by converting them to searchable PDFs
Types
* Optical character recognition (OCR)targets typewritten text, one glyph or character at a time.
* Optical word recognitiontargets typewritten text, one word at a time (for languages that use a space
Space is the boundless three-dimensional extent in which objects and events have relative position and direction. In classical physics, physical space is often conceived in three linear dimensions, although modern physicists usually cons ...
as a word divider
In punctuation, a word divider is a glyph that separates written words. In languages which use the Latin, Cyrillic, and Arabic alphabets, as well as other scripts of Europe and West Asia, the word divider is a blank space, or ''whitespace''. ...
). (Usually just called "OCR".)
* Intelligent character recognition
In computer science, intelligent character recognition (ICR) is an advanced optical character recognition (OCR) or — rather more specific — handwriting recognition system that allows fonts and different styles of handwriting to be learned by a ...
(ICR)also targets handwritten printscript or cursive text one glyph or character at a time, usually involving machine learning
Machine learning (ML) is a field of inquiry devoted to understanding and building methods that 'learn', that is, methods that leverage data to improve performance on some set of tasks. It is seen as a part of artificial intelligence.
Machine ...
.
* Intelligent word recognition
Intelligent Word Recognition, or IWR, is the recognition of unconstrained handwritten words. IWR recognizes entire handwritten words or phrases instead of character-by-character, like its predecessor, optical character recognition (OCR). IWR tec ...
(IWR)also targets handwritten printscript or cursive text, one word at a time. This is especially useful for languages where glyphs are not separated in cursive script.
OCR is generally an "offline" process, which analyses a static document. There are cloud based services which provide an online OCR API service. Handwriting movement analysis can be used as input to handwriting recognition
Handwriting recognition (HWR), also known as handwritten text recognition (HTR), is the ability of a computer to receive and interpret intelligible handwritten input from sources such as paper documents, photographs, touch-screens and other de ...
. Instead of merely using the shapes of glyphs and words, this technique is able to capture motions, such as the order in which segments are drawn, the direction, and the pattern of putting the pen down and lifting it. This additional information can make the end-to-end process more accurate. This technology is also known as "on-line character recognition", "dynamic character recognition", "real-time character recognition", and "intelligent character recognition".
Techniques
Pre-processing
OCR software often "pre-processes" images to improve the chances of successful recognition. Techniques include:
* De- skewIf the document was not aligned properly when scanned, it may need to be tilted a few degrees clockwise or counterclockwise in order to make lines of text perfectly horizontal or vertical.
* Despeckle
Noise reduction is the process of removing noise from a signal. Noise reduction techniques exist for audio and images. Noise reduction algorithms may distort the signal to some degree. Noise rejection is the ability of a circuit to isolate an un ...
remove positive and negative spots, smoothing edges
* BinarisationConvert an image from color or greyscale
In digital photography, computer-generated imagery, and colorimetry, a grayscale image is one in which the value of each pixel is a single sample representing only an ''amount'' of light; that is, it carries only intensity information. Gray ...
to black-and-white (called a " binary image" because there are two colors). The task of binarisation is performed as a simple way of separating the text (or any other desired image component) from the background. The task of binarisation itself is necessary since most commercial recognition algorithms work only on binary images since it proves to be simpler to do so. In addition, the effectiveness of the binarisation step influences to a significant extent the quality of the character recognition stage and the careful decisions are made in the choice of the binarisation employed for a given input image type; since the quality of the binarisation method employed to obtain the binary result depends on the type of the input image (scanned document, scene text image, historical degraded document etc.).
* Line removalCleans up non-glyph boxes and lines
* Layout analysis or "zoning"Identifies columns, paragraphs, captions, etc. as distinct blocks. Especially important in multi-column layouts and tables
Table may refer to:
* Table (furniture), a piece of furniture with a flat surface and one or more legs
* Table (landform), a flat area of land
* Table (information), a data arrangement with rows and columns
* Table (database), how the table d ...
.
* Line and word detectionEstablishes baseline for word and character shapes, separates words if necessary.
* Script recognitionIn multilingual documents, the script may change at the level of the words and hence, identification of the script is necessary, before the right OCR can be invoked to handle the specific script.
* Character isolation or "segmentation"For per-character OCR, multiple characters that are connected due to image artifacts must be separated; single characters that are broken into multiple pieces due to artifacts must be connected.
* Normalize aspect ratio and scale
Segmentation of fixed-pitch fonts is accomplished relatively simply by aligning the image to a uniform grid based on where vertical grid lines will least often intersect black areas. For proportional font
A typeface (or font family) is the design of lettering that can include variations in size, weight (e.g. bold), slope (e.g. italic), width (e.g. condensed), and so on. Each of these variations of the typeface is a font.
There are thousands ...
s, more sophisticated techniques are needed because whitespace between letters can sometimes be greater than that between words, and vertical lines can intersect more than one character.
Text recognition
There are two basic types of core OCR algorithm, which may produce a ranked list of candidate characters.
* ''Matrix matching'' involves comparing an image to a stored glyph on a pixel-by-pixel basis; it is also known as "pattern matching", "pattern recognition
Pattern recognition is the automated recognition of patterns and regularities in data. It has applications in statistical data analysis, signal processing, image analysis, information retrieval, bioinformatics, data compression, computer graphics ...
", or " image correlation". This relies on the input glyph being correctly isolated from the rest of the image, and on the stored glyph being in a similar font and at the same scale. This technique works best with typewritten text and does not work well when new fonts are encountered. This is the technique the early physical photocell-based OCR implemented, rather directly.
* ''Feature extraction'' decomposes glyphs into "features" like lines, closed loops, line direction, and line intersections. The extraction features reduces the dimensionality of the representation and makes the recognition process computationally efficient. These features are compared with an abstract vector-like representation of a character, which might reduce to one or more glyph prototypes. General techniques of feature detection in computer vision are applicable to this type of OCR, which is commonly seen in "intelligent" handwriting recognition
Handwriting recognition (HWR), also known as handwritten text recognition (HTR), is the ability of a computer to receive and interpret intelligible handwritten input from sources such as paper documents, photographs, touch-screens and other de ...
and indeed most modern OCR software. Nearest neighbour classifiers such as the k-nearest neighbors algorithm
In statistics, the ''k''-nearest neighbors algorithm (''k''-NN) is a non-parametric supervised learning method first developed by Evelyn Fix and Joseph Hodges in 1951, and later expanded by Thomas Cover. It is used for classification and regre ...
are used to compare image features with stored glyph features and choose the nearest match.
Software such as Cuneiform
Cuneiform is a logo-syllabic script that was used to write several languages of the Ancient Middle East. The script was in active use from the early Bronze Age until the beginning of the Common Era. It is named for the characteristic wedge-sh ...
and Tesseract
In geometry, a tesseract is the four-dimensional analogue of the cube; the tesseract is to the cube as the cube is to the square. Just as the surface of the cube consists of six square faces, the hypersurface of the tesseract consists of e ...
use a two-pass approach to character recognition. The second pass is known as "adaptive recognition" and uses the letter shapes recognized with high confidence on the first pass to recognize better the remaining letters on the second pass. This is advantageous for unusual fonts or low-quality scans where the font is distorted (e.g. blurred or faded).
Modern OCR software include Google Docs OCR, ABBYY FineReader and Transym. Others like OCRopus
OCRopus is a free document analysis and optical character recognition (OCR) system released under the Apache License v2.0 with a very modular design using command-line interfaces.
OCRopus is developed under the lead of Thomas Breuel from the ...
and Tesseract uses neural networks which are trained to recognize whole lines of text instead of focusing on single characters.
A new technique known as iterative OCR automatically crops a document into sections based on page layout. OCR is performed on the sections individually using variable character confidence level thresholds to maximize page-level OCR accuracy. A patent from the United States Patent Office has been issued for this method
The OCR result can be stored in the standardized ALTO format, a dedicated XML schema maintained by the United States Library of Congress
The Library of Congress (LOC) is the research library that officially serves the United States Congress and is the ''de facto'' national library of the United States. It is the oldest federal cultural institution in the country. The library ...
. Other common formats include hOCR
hOCR is an open standard of data representation for formatted text obtained from optical character recognition (OCR). The definition encodes text, style, layout information, recognition confidence metrics and other information using Extensible Ma ...
and PAGE XML.
For a list of optical character recognition software see Comparison of optical character recognition software
This comparison of optical character recognition software includes:
* OCR engines, that do the actual character identification
* Layout analysis software, that divide scanned documents into zones suitable for OCR
* Graphical interfaces to one or m ...
.
Post-processing
OCR accuracy can be increased if the output is constrained by a lexicona list of words that are allowed to occur in a document. This might be, for example, all the words in the English language, or a more technical lexicon for a specific field. This technique can be problematic if the document contains words not in the lexicon, like proper noun
A proper noun is a noun that identifies a single entity and is used to refer to that entity (''Africa'', ''Jupiter'', '' Sarah'', ''Microsoft)'' as distinguished from a common noun, which is a noun that refers to a class of entities (''continent, ...
s. Tesseract uses its dictionary to influence the character segmentation step, for improved accuracy.
The output stream may be a plain text
In computing, plain text is a loose term for data (e.g. file contents) that represent only characters of readable material but not its graphical representation nor other objects (floating-point numbers, images, etc.). It may also include a limit ...
stream or file of characters, but more sophisticated OCR systems can preserve the original layout of the page and produce, for example, an annotated PDF that includes both the original image of the page and a searchable textual representation.
"Near-neighbor analysis" can make use of co-occurrence In linguistics, co-occurrence or cooccurrence is an above-chance frequency of occurrence of two terms (also known as coincidence or concurrence) from a text corpus alongside each other in a certain order. Co-occurrence in this linguistic sense ca ...
frequencies to correct errors, by noting that certain words are often seen together. For example, "Washington, D.C." is generally far more common in English than "Washington DOC".
Knowledge of the grammar of the language being scanned can also help determine if a word is likely to be a verb or a noun, for example, allowing greater accuracy.
The Levenshtein Distance
In information theory, linguistics, and computer science, the Levenshtein distance is a string metric for measuring the difference between two sequences. Informally, the Levenshtein distance between two words is the minimum number of single-charac ...
algorithm has also been used in OCR post-processing to further optimize results from an OCR API.
Application-specific optimizations
In recent years, the major OCR technology providers began to tweak OCR systems to deal more efficiently with specific types of input. Beyond an application-specific lexicon, better performance may be had by taking into account business rules, standard expression, or rich information contained in color images. This strategy is called "Application-Oriented OCR" or "Customized OCR", and has been applied to OCR of license plate
A vehicle registration plate, also known as a number plate (British English), license plate (American English), or licence plate (Canadian English), is a metal or plastic plate attached to a motor vehicle or trailer for official identificatio ...
s, invoice
An invoice, bill or tab is a commercial document issued by a seller to a buyer relating to a sale transaction and indicating the products, quantities, and agreed-upon prices for products or services the seller had provided the buyer.
Payment ...
s, screenshots, ID cards, driver license
A driver's license is a legal authorization, or the official document confirming such an authorization, for a specific individual to operate one or more types of motorized vehicles—such as motorcycles, cars, trucks, or buses—on a public r ...
s, and automobile manufacturing
The automotive industry comprises a wide range of companies and organizations involved in the design, development, manufacturing, marketing, and selling of motor vehicles. It is one of the world's largest industries by revenue (from 16 % such ...
.
''The New York Times
''The New York Times'' (''the Times'', ''NYT'', or the Gray Lady) is a daily newspaper based in New York City with a worldwide readership reported in 2020 to comprise a declining 840,000 paid print subscribers, and a growing 6 million paid d ...
'' has adapted the OCR technology into a proprietary tool they entitle, ''Document Helper'', that enables their interactive news team to accelerate the processing of documents that need to be reviewed. They note that it enables them to process what amounts to as many as 5,400 pages per hour in preparation for reporters to review the contents.
Workarounds
There are several techniques for solving the problem of character recognition by means other than improved OCR algorithms.
Forcing better input
Special fonts like OCR-A
OCR-A is a font created in 1968, in the early days of computer optical character recognition, when there was a need for a font that could be recognized not only by the computers of that day, but also by humans. OCR-A uses simple, thick strokes to ...
, OCR-B
OCR-B is a monospace font developed in 1968 by Adrian Frutiger for Monotype by following the European Computer Manufacturer's Association standard. Its function was to facilitate the optical character recognition operations by specific electroni ...
, or MICR
Magnetic ink character recognition code, known in short as MICR code, is a character recognition technology used mainly by the banking industry to streamline the processing and clearance of cheques and other documents. MICR encoding, called the ' ...
fonts, with precisely specified sizing, spacing, and distinctive character shapes, allow a higher accuracy rate during transcription in bank check processing. Ironically, however, several prominent OCR engines were designed to capture text in popular fonts such as Arial or Times New Roman, and are incapable of capturing text in these fonts that are specialized and much different from popularly used fonts. As Google Tesseract can be trained to recognize new fonts, it can recognize OCR-A, OCR-B and MICR fonts.
"Comb fields" are pre-printed boxes that encourage humans to write more legiblyone glyph per box. These are often printed in a "dropout color" which can be easily removed by the OCR system.
Palm OS
Palm OS (also known as Garnet OS) was a mobile operating system initially developed by Palm, Inc., for personal digital assistants (PDAs) in 1996. Palm OS was designed for ease of use with a touchscreen-based graphical user interface. It is pro ...
used a special set of glyphs, known as "Graffiti
Graffiti (plural; singular ''graffiti'' or ''graffito'', the latter rarely used except in archeology) is art that is written, painted or drawn on a wall or other surface, usually without permission and within public view. Graffiti ranges from s ...
" which are similar to printed English characters but simplified or modified for easier recognition on the platform's computationally limited hardware. Users would need to learn how to write these special glyphs.
Zone-based OCR restricts the image to a specific part of a document. This is often referred to as "Template OCR".
Crowdsourcing
Crowdsourcing humans to perform the character recognition can quickly process images like computer-driven OCR, but with higher accuracy for recognizing images than that obtained via computers. Practical systems include the Amazon Mechanical Turk and reCAPTCHA
reCAPTCHA is a CAPTCHA system that enables web hosts to distinguish between human and automated access to websites. The original version asked users to decipher hard to read text or match images. Version 2 also asked users to decipher text or ...
. The National Library of Finland
The National Library of Finland ( fi, Kansalliskirjasto, sv, Nationalbiblioteket) is the foremost research library in Finland. Administratively the library is part of the University of Helsinki. From 1919 to 1 August 2006, it was known as the ...
has developed an online interface for users to correct OCRed texts in the standardized ALTO format. Crowd sourcing has also been used not to perform character recognition directly but to invite software developers to develop image processing algorithms, for example, through the use of rank-order tournaments.
Accuracy
Commissioned by the U.S. Department of Energy (DOE), the Information Science Research Institute (ISRI) had the mission to foster the improvement of automated technologies for understanding machine printed documents, and it conducted the most authoritative of the ''Annual Test of OCR Accuracy'' from 1992 to 1996.
Recognition of Latin-script, typewritten text is still not 100% accurate even where clear imaging is available. One study based on recognition of 19th- and early 20th-century newspaper pages concluded that character-by-character OCR accuracy for commercial OCR software varied from 81% to 99%; total accuracy can be achieved by human review or Data Dictionary Authentication. Other areas—including recognition of hand printing, cursive handwriting, and printed text in other scripts (especially those East Asian language characters which have many strokes for a single character)—are still the subject of active research. The MNIST database is commonly used for testing systems' ability to recognise handwritten digits.
Accuracy rates can be measured in several ways, and how they are measured can greatly affect the reported accuracy rate. For example, if word context (basically a lexicon of words) is not used to correct software finding non-existent words, a character error rate of 1% (99% accuracy) may result in an error rate of 5% (95% accuracy) or worse if the measurement is based on whether each whole word was recognized with no incorrect letters. Using a large enough dataset is so important in a neural network based handwriting recognition solutions. On the other hand, producing natural datasets is very complicated and time-consuming.
An example of the difficulties inherent in digitizing old text is the inability of OCR to differentiate between the "long s
The long s , also known as the medial s or initial s, is an archaic form of the lowercase letter . It replaced the single ''s'', or one or both of the letters ''s'' in a 'double ''s sequence (e.g., "ſinfulneſs" for "sinfulness" and "poſ ...
" and "f" characters.
Web-based OCR systems for recognizing hand-printed text on the fly have become well known as commercial products in recent years (see Tablet PC history). Accuracy rates of 80% to 90% on neat, clean hand-printed characters can be achieved by pen computing
Pen computing refers to any computer user-interface using a pen or Stylus (computing), stylus and tablet, over input devices such as a keyboard or a mouse.
Pen computing is also used to refer to the usage of mobile devices such as tablet computers ...
software, but that accuracy rate still translates to dozens of errors per page, making the technology useful only in very limited applications.
Recognition of cursive text is an active area of research, with recognition rates even lower than that of hand-printed text. Higher rates of recognition of general cursive script will likely not be possible without the use of contextual or grammatical information. For example, recognizing entire words from a dictionary is easier than trying to parse individual characters from script. Reading the ''Amount'' line of a cheque
A cheque, or check (American English; see spelling differences) is a document that orders a bank (or credit union) to pay a specific amount of money from a person's account to the person in whose name the cheque has been issued. The pers ...
(which is always a written-out number) is an example where using a smaller dictionary can increase recognition rates greatly. The shapes of individual cursive characters themselves simply do not contain enough information to accurately (greater than 98%) recognize all handwritten cursive script.
Most programs allow users to set "confidence rates". This means that if the software does not achieve their desired level of accuracy, a user can be notified for manual review.
An error introduced by OCR scanning is sometimes termed a "scanno" (by analogy with the term "typo").[http://www.hoopoes.com/jargon/entry/scanno.shtml Dead link]
Unicode
Characters to support OCR were added to the Unicode
Unicode, formally The Unicode Standard,The formal version reference is is an information technology Technical standard, standard for the consistent character encoding, encoding, representation, and handling of Character (computing), text expre ...
Standard in June 1993, with the release of version 1.1.
Some of these characters are mapped from fonts specific to MICR
Magnetic ink character recognition code, known in short as MICR code, is a character recognition technology used mainly by the banking industry to streamline the processing and clearance of cheques and other documents. MICR encoding, called the ' ...
, OCR-A
OCR-A is a font created in 1968, in the early days of computer optical character recognition, when there was a need for a font that could be recognized not only by the computers of that day, but also by humans. OCR-A uses simple, thick strokes to ...
or OCR-B
OCR-B is a monospace font developed in 1968 by Adrian Frutiger for Monotype by following the European Computer Manufacturer's Association standard. Its function was to facilitate the optical character recognition operations by specific electroni ...
.
See also
References
External links
Unicode OCRHex Range: 2440-245F
Optical Character Recognition in Unicode
{{DEFAULTSORT:Optical Character Recognition
Applications of artificial intelligence
Applications of computer vision
Automatic identification and data capture
Computational linguistics
Unicode
Symbols
Machine learning task