News classification
Contact us
- Add: No. 9, North Fourth Ring Road, Haidian District, Beijing. It mainly includes face recognition, living detection, ID card recognition, bank card recognition, business card recognition, license plate recognition, OCR recognition, and intelligent recognition technology.
- Tel: 13146317170 廖经理
- Fax:
- Email: 398017534@qq.com
OCR technology past life
OCR technology past life
OCR technology past life
【Abstract】 With the rapid development of computer network, information electronic has become an inevitable trend of the times, OCR technology can be achieved on the text data scanning, and then the image file analysis and processing, access to text and layout-related information, this paper describes the OCR Development and application of the status quo, and the application of OCR technology prospects for a forward-looking.
【Key words】 optical character recognition (OCR) research progress forward
1 Overview
OCR (Optical Character Recognition), that is, optical character recognition, refers to the electronic equipment (such as a scanner or digital camera) to check the characters printed on paper, by detecting the dark, bright mode to determine its shape, and then use the character recognition method to shape translation Into the process of computer text; that is, the text data to scan, and then the image file analysis and processing, access to text and layout information process.
With the rapid development of computer networks, information electronic has become an inevitable trend of the times. Text as the most important information, the most concentrated carrier, the electronic process is particularly important. OCR technology is the text of the electronic process of the most important part, it changed the traditional paper media information input concept. For example, through OCR technology, users can be through the camera, scanner and other optical input way to get the press, books, documents, forms and other print image information can be used for computer identification and processing of text information. Therefore, OCR technology greatly improves the efficiency of data storage, retrieval and processing compared with the traditional manual entry method. OCR products currently in line with banks, securities, insurance, tax, public security, customs, airports, industry and commerce, military and other industries have been relatively mature, they have been market tested and used by large-scale users [1-4].
2, the origin and development of OCR technology
The origins of the OCR were first traced back to the year 1992, when German scientist Taushcck obtained the patent for optical character recognition technology [5], but for the development of science and technology at the time, everything was only a vision until the birth of the computer made the idea a reality The After nearly a hundred years of development, OCR has become one of the most active branches of today's pattern recognition. It combines the digital image processing, computer graphics and artificial intelligence and other aspects of theoretical knowledge, and in the computer and its related fields has been a very wide range of applications. In recent years, it has become a focus of research and attention with voice recognition, behavior recognition and so on.
In the 1960s and 1970s, the world has launched optical character recognition research, such as our neighboring countries, in the mid-sixties there will be postal code identification system products come out, the system can identify the mail Of the postal code to help the post office for regional communication operations, which also makes the postal code has been in use today [6]. Subsequently, after the efforts of scientific research scholars, said the Sanyo, Fuji, Ricoh, Panasonic and other well-known companies have also have character recognition system products available.
China's optical character recognition research started relatively late abroad, but the development is very rapid. From the early simple monomer recognition to the development of a variety of fonts mixed array of multi-body recognition, from the Chinese printing material identification to the development of Chinese and English mixed printing materials, dual language recognition, the current system can support Jane, traditional Chinese characters , But also support the Chinese, English, Korean and other multi-language recognition system, which solve the multi-body multi-font mixed text recognition problem, for a simple layout can be carried out quantitative analysis, while the Chinese character recognition rate has reached 98% the above.
3, OCR technology applications
Foreign OCR technology is relatively mature, including the old M, Motorola, HP and Microsoft and other world-class companies have launched this research, in their products bound OCR technology. The optical character recognition device reads printed characters on newspapers, magazines and other printed materials into computer memory. OCR software can be used with any popular operating system. In addition to identifying printed characters, OCRs may also identify column layouts that appear in newspapers. For example, Microsoft's latest office suite, Microsoft Office XP, not only strengthens the support for existing handwriting input, but also adds new tools for optical character recognition (OCR). The wide application of character recognition products has promoted the development of relevant theories such as pattern recognition and promoted the popularization of computer applications. In 2008, Google also announced that it will begin using OCR technology in web spiders, so that many non-formatted text and images can be identified and indexed to the database.
Today, OCR technology in China's application is also very broad, there can be said that there are places where the existence of OCR technology applications exist. In the increasingly popular information technology and computer technology today, how to easily and quickly enter the text into the computer has become an important problem affecting the efficiency of human-computer interface, but also related to the computer can really be popular in our country and application.
Chinese characters input is divided into artificial keyboard input and machine automatic recognition input two. Which manual input is slow and labor intensity; automatic input is divided into Chinese character recognition input and voice recognition input. From the difficulty of recognizing technology, handwriting recognition is more difficult than print recognition, and in handwriting recognition, the difficulty of offline handwriting is far more than online handwriting recognition. So far, in addition to offline handwriting digital recognition has been practical application, the Chinese characters and other text offline handwriting recognition is still in the laboratory stage. In simple terms, from the image to the results of the output, subject to image input, image preprocessing, text feature extraction, matching recognition, and finally by artificial correction will correct the text correction, the results of the output process.
With the full popularity of China's information technology, OCR technology application prospects will be more broad. On the current demand from the industry point of view, finance, insurance, taxation, industry and commerce, e-commerce and other industries on the demand for information identification has become increasingly widespread, and promote the large-scale application of identification technology. And individual consumers on the electronic data, handwriting recognition technology and other aspects of the demand is to expand the OCR identification technology in this area of application of the road, on the other hand, the rapid development of the Internet era of personal data, business office automation, etc. The voice of demand has become increasingly high.
4, the conclusion
When the computer, mobile phones and all kinds of IT products common to the times, the world is digitally dominated by the world, not only IT technology hot spots, even the hot spots of life will be transferred to the human-computer intelligence interactive technology, man-machine intelligence Interactive technology will become our understanding of the world, understand the world, and become a computer to understand our exports.
In this paper, OCR technology is briefly summarized, and combined with the current development of the status of several applications are being identified in the identification of software products. OCR technology has made great progress, and its research has become one of the most advanced research contents in the field of pattern recognition, which reflects the latest progress of cognitive science, artificial intelligence and manufacturing process.
It can be said that the popularity of the Internet and the computer for the development of OCR provides a broader application of the stage. At present, the direction of scientific research scholars to focus on the main focus on handwritten Chinese character recognition, full font recognition, graphic mixed document text recognition, video image recognition and so on. In the future development process, OCR technology and its products will continue to improve, the application will be more extensive, and its in-depth study can not only lead to pattern recognition, artificial intelligence and other related disciplines and branch development, and can be closer And the distance between the computer, to promote the great development of human science, and better services for human science and technology life.
【Abstract】 With the rapid development of computer network, information electronic has become an inevitable trend of the times, OCR technology can be achieved on the text data scanning, and then the image file analysis and processing, access to text and layout-related information, this paper describes the OCR Development and application of the status quo, and the application of OCR technology prospects for a forward-looking.
【Key words】 optical character recognition (OCR) research progress forward
1 Overview
OCR (Optical Character Recognition), that is, optical character recognition, refers to the electronic equipment (such as a scanner or digital camera) to check the characters printed on paper, by detecting the dark, bright mode to determine its shape, and then use the character recognition method to shape translation Into the process of computer text; that is, the text data to scan, and then the image file analysis and processing, access to text and layout information process.
With the rapid development of computer networks, information electronic has become an inevitable trend of the times. Text as the most important information, the most concentrated carrier, the electronic process is particularly important. OCR technology is the text of the electronic process of the most important part, it changed the traditional paper media information input concept. For example, through OCR technology, users can be through the camera, scanner and other optical input way to get the press, books, documents, forms and other print image information can be used for computer identification and processing of text information. Therefore, OCR technology greatly improves the efficiency of data storage, retrieval and processing compared with the traditional manual entry method. OCR products currently in line with banks, securities, insurance, tax, public security, customs, airports, industry and commerce, military and other industries have been relatively mature, they have been market tested and used by large-scale users [1-4].
2, the origin and development of OCR technology
The origins of the OCR were first traced back to the year 1992, when German scientist Taushcck obtained the patent for optical character recognition technology [5], but for the development of science and technology at the time, everything was only a vision until the birth of the computer made the idea a reality The After nearly a hundred years of development, OCR has become one of the most active branches of today's pattern recognition. It combines the digital image processing, computer graphics and artificial intelligence and other aspects of theoretical knowledge, and in the computer and its related fields has been a very wide range of applications. In recent years, it has become a focus of research and attention with voice recognition, behavior recognition and so on.
In the 1960s and 1970s, the world has launched optical character recognition research, such as our neighboring countries, in the mid-sixties there will be postal code identification system products come out, the system can identify the mail Of the postal code to help the post office for regional communication operations, which also makes the postal code has been in use today [6]. Subsequently, after the efforts of scientific research scholars, said the Sanyo, Fuji, Ricoh, Panasonic and other well-known companies have also have character recognition system products available.
China's optical character recognition research started relatively late abroad, but the development is very rapid. From the early simple monomer recognition to the development of a variety of fonts mixed array of multi-body recognition, from the Chinese printing material identification to the development of Chinese and English mixed printing materials, dual language recognition, the current system can support Jane, traditional Chinese characters , But also support the Chinese, English, Korean and other multi-language recognition system, which solve the multi-body multi-font mixed text recognition problem, for a simple layout can be carried out quantitative analysis, while the Chinese character recognition rate has reached 98% the above.
3, OCR technology applications
Foreign OCR technology is relatively mature, including the old M, Motorola, HP and Microsoft and other world-class companies have launched this research, in their products bound OCR technology. The optical character recognition device reads printed characters on newspapers, magazines and other printed materials into computer memory. OCR software can be used with any popular operating system. In addition to identifying printed characters, OCRs may also identify column layouts that appear in newspapers. For example, Microsoft's latest office suite, Microsoft Office XP, not only strengthens the support for existing handwriting input, but also adds new tools for optical character recognition (OCR). The wide application of character recognition products has promoted the development of relevant theories such as pattern recognition and promoted the popularization of computer applications. In 2008, Google also announced that it will begin using OCR technology in web spiders, so that many non-formatted text and images can be identified and indexed to the database.
Today, OCR technology in China's application is also very broad, there can be said that there are places where the existence of OCR technology applications exist. In the increasingly popular information technology and computer technology today, how to easily and quickly enter the text into the computer has become an important problem affecting the efficiency of human-computer interface, but also related to the computer can really be popular in our country and application.
Chinese characters input is divided into artificial keyboard input and machine automatic recognition input two. Which manual input is slow and labor intensity; automatic input is divided into Chinese character recognition input and voice recognition input. From the difficulty of recognizing technology, handwriting recognition is more difficult than print recognition, and in handwriting recognition, the difficulty of offline handwriting is far more than online handwriting recognition. So far, in addition to offline handwriting digital recognition has been practical application, the Chinese characters and other text offline handwriting recognition is still in the laboratory stage. In simple terms, from the image to the results of the output, subject to image input, image preprocessing, text feature extraction, matching recognition, and finally by artificial correction will correct the text correction, the results of the output process.
With the full popularity of China's information technology, OCR technology application prospects will be more broad. On the current demand from the industry point of view, finance, insurance, taxation, industry and commerce, e-commerce and other industries on the demand for information identification has become increasingly widespread, and promote the large-scale application of identification technology. And individual consumers on the electronic data, handwriting recognition technology and other aspects of the demand is to expand the OCR identification technology in this area of application of the road, on the other hand, the rapid development of the Internet era of personal data, business office automation, etc. The voice of demand has become increasingly high.
4, the conclusion
When the computer, mobile phones and all kinds of IT products common to the times, the world is digitally dominated by the world, not only IT technology hot spots, even the hot spots of life will be transferred to the human-computer intelligence interactive technology, man-machine intelligence Interactive technology will become our understanding of the world, understand the world, and become a computer to understand our exports.
In this paper, OCR technology is briefly summarized, and combined with the current development of the status of several applications are being identified in the identification of software products. OCR technology has made great progress, and its research has become one of the most advanced research contents in the field of pattern recognition, which reflects the latest progress of cognitive science, artificial intelligence and manufacturing process.
It can be said that the popularity of the Internet and the computer for the development of OCR provides a broader application of the stage. At present, the direction of scientific research scholars to focus on the main focus on handwritten Chinese character recognition, full font recognition, graphic mixed document text recognition, video image recognition and so on. In the future development process, OCR technology and its products will continue to improve, the application will be more extensive, and its in-depth study can not only lead to pattern recognition, artificial intelligence and other related disciplines and branch development, and can be closer And the distance between the computer, to promote the great development of human science, and better services for human science and technology life.