OCR (Optical Character Recognition) document scanner software refers to the situation where the electronic device (e.g., portable scanner or digital camera) check characters printed on paper, by detecting the dark light pattern to determine the shape, then through the shape of the character recognition translating the text into computer process ; that is: ensure the text data is scanned, and then via the image file analysis and processing to get the text and layout information. How to debug or use auxiliary information to improve the recognition accuracy is the most important issue of OCR, the noun ICR (Intelligent Character Recognition) is thus produced. The measuring indicators of a good or bad performance OCR system are: rejection rate, friendly error rate, recognition speed, user interface, product stability, ease of use and feasibility.OCRs are mainly used in scanners, for document scanners,portable scanners and some of the best scanners,which are classified as office supplies.
Optical character recognition concept is created in 1929 by German scientist Tausheck, and later an US scientists Handel also proposed the ideas of the use of technology to identify character. The earliest printed Chinese character recognition research is IBM's Casey and Nagy, in 1966, they published the first article on Chinese character recognition using the template matching method to identify the 1000 printed characters.
Early in the 1960s and 1970s, the world began to research on the OCR, and initial research, mostly research is based on text recognition and text recognition is only confined to the digits 0 to 9. For instance, Japan also has a blocked texts,, around 1960 they began to study the basic OCR recognition theory, the initial stage they focus on the digital object, then they began to have some simple products, such as printed text recognition system between ZIP until 1965-1970, ZIP code identifying the message to help the post office as a letter-area operations; thereafter each country has advocated the zip code address writing style.
Early 1970s, Japanese scholars began to study Chinese character recognition, and did a lot of work. Chinese study in OCR technology started late, they only began to identify numbers, letters and symbols to in their studies in the 1970s, the late 1970s they started to study Chinese character recognition, till 1986 they entered a substantive character recognition stage, many research institutions have launched a Chinese OCR product. Early OCR software, due to various factors and product recognition rate, failed to meet the actual requirements in the application of scanner industry for portable scanners,document scanners,office best scanners. Meanwhile, the high cost of hardware and with the running is slow, they failed to get practical result. Only a few sectors, such as the information sector, the press and publishing units,office supplies have the use of OCR software. OCR after 1986 has made great progress in the Chinese character modeling and identification method; they have the innovation, research and development applications in the system have achieved fruitful results, many units have launched a Chinese OCR products for document scanners. After the beginning of the 20th century, with extensive use of flatbed scanners,OCR document scanner and automation of information and office automation ,they contributed significantly to the further development of OCR technology, the OCR recognition rate and recognition speed are able to meet the majority of users requirement for document scanners and office scanners.
Because of the scanner software's popularity and widespread application, OCR software only needs to be provided with an interface with the portable document scanner, using a scanner driver software, then they can function and work for you.