The development of OCR technology in the process of file digitization

OCR, that is, using a book scanner to scan text. The result is stored in the image format (.bmp) into the computer. Then use the OCR recognition system to convert. Finally, use WORD to modify the edit.

The following teaches you how to use ORC: OCR is the abbreviation of English Optical Character Recognition. Translating into Chinese means to recognize words through optical technology. It is an important aspect in the field of automatic identification technology research and application. It is a kind of ability The text automatically recognizes the software technology that is entered into the computer. It is the main software that is compatible with the book scanner. It belongs to the non-keyboard input category. The image input device is mainly matched by the book scanner. Now OCR mainly refers to the text recognition software. In 1996 Before Tsinghua Unisplendour began to work with Chinese recognition software, the scanners and OCR software on the market were sold separately. Book scanner manufacturers have now sold professional OCR software with their own scanners. The rapid development of OCR technology is inseparable from the widespread use of scanners. In the past two years, with the popularity of book scanners and the future of OCR technology Perfect. OCR has become the right assistant for most scanner users.

The development of OCR technology

Since the first generation of OCR products began in the early 1960s. After more than 30 years of continuous improvement and improvement, the research on various OCR technologies including handwriting has achieved remarkable results. People's functional requirements for OCR products are also original. Simple attention to recognition rate. Development to the recognition speed of the entire OCR system. User interface friendliness. Operational simplicity. Product stability, adaptability, reliability and easy upgradeability. Pre-sales and after-sales service quality and other aspects higher requirement.

IBM first developed OCR products. In 1965, at the New York World's Fair, IBM's OCR product, IBMl287, was exhibited. At the time, this product only recognized the number of printed characters, English letters and some symbols. It must be specified. Fonts. In the late 1960s, Hitachi and Fujitsu also developed their own OCR products. The world's first automatic letter sorting system for handwritten postal code recognition was developed by Toshiba Corporation of Japan. Two years later. NEC also introduced the same system. By 1974, the automatic sorting rate of letters reached 92%. It was widely used in the postal system. It played a good role. In 1983, Toshiba released its identification printing. The OCR system OCRV595 of Japanese-Chinese characters has a recognition speed of 70-100 Chinese characters per second. The recognition rate is 99.5%. Later, Toshiba began the research work on handwritten Japanese kanji recognition.

China's research work on OCR technology started relatively late. In the 1970s, research on the identification of numbers and English letters and symbols began. In the late 1970s, research on Chinese character recognition began. 1986. National 863 The planning information field organized Tsinghua University. Beijing Information Engineering College. Shenyang Automation Institute jointly carried out the development of Chinese OCR software. Tsinghua University took the lead in launching the first Chinese OCR software--Tsinghua Wentong TH-OCR1.0 version At this point, Chinese OCR officially went from the laboratory to the market. Tsinghua OCR printed Chinese character recognition software later introduced TH-OCR 92 high-performance practical simple/traditional. Multi-font. Multi-function printing Chinese character recognition system. The technology has made significant progress. The TH-OCR 94 high-performance Chinese-English mixed-print text recognition system launched in 1994 was identified by experts as [the first Chinese-English mixed-print text recognition system introduced at home and abroad. The international leading level". In the mid-to-late 1990s, the Department of Electronic Engineering of Tsinghua University proposed and conducted a comprehensive study of Chinese character recognition. The Chinese character recognition technology was printed. Text. Online handwritten Chinese character recognition. Offline handwritten Chinese character recognition and offline handwritten digital symbol recognition and other fields have achieved important results. The representative result is TH-OCR 97 integrated integrated Chinese character recognition system. It can complete multi-language (Han.English. Japanese) printed text. Online handwritten Chinese characters. Offline handwritten Chinese characters and handwritten digits recognition input. In addition to Tsinghua Wentong TH-OCR. Others such as Shangshu SH-OCR and other styles of OCR software The Chinese OCR market has expanded steadily. Users are all over the world.

It can be said that the recognition technology of the printed OCR has reached a high level. The OCR product has been developed from the early identification of only the specified print digits. English letters and partial symbols. It can be automatically analyzed for layout. Table recognition. Implement mixed text. Multi-font. Multi-font size. Powerful computer information quick entry tool for horizontal and vertical sorting recognition. The recognition rate of printed Chinese characters is over 98%. Even for texts with poor print quality, the recognition rate is over 95%. It recognizes the simple and traditional Chinese fonts such as the Song dynasty. The black body. The corpus callosum. The imitation of the Song dynasty and so on. It can also recognize the mixed typesetting of various fonts and different font sizes. The recognition rate of handwritten Chinese characters reaches 70% or more. Especially the Chinese character OCR technology After more than ten years of hard work, it has overcome the difficulty of starting the late. The Chinese character set is extremely large. The recognition speed of the single word (refers to the number of words extracted from the feature extraction to the recognition result in the unit time) can reach 70 words/second or more. OCR products are widely used in news, printing, publishing, library, office automation, etc. due to the mature OCR Chinese character recognition technology. .

Professional OCR products are mostly for specific industries. It is suitable for departments that need to process a large number of forms of information input every day. For example, postal, tax, customs, statistics, etc. This professional OCR system for specific industries has a fixed format. The recognized character set is relatively small. It is often used in conjunction with dedicated input devices. It is therefore fast and efficient, such as automatic mail sorting systems.

The recognition of handwritten manuscripts was not available until 1996.1997. It is also provided as an additional function of the printed document recognition product. The habit of writing is very different. It is very difficult to realize free handwriting recognition. So the field of handwritten OCR technology is Online handwriting recognition. That is, people write while the computer recognizes. It is a real-time recognition method.

The development of OCR technology in the process of file digitization

Number of matches A2 high precision file scanner OS12002

If you need to digitize large format documents, precious books, calligraphy, files and files, the OS12002 product family can provide the most forward-looking solutions for your needs. Applicable to universities, libraries, archives, museums, land, surveying, machinery, art, printing and so on.

facial mask

Facial Mask:We are specialized facial mask manufacturers & suppliers/factory from China. Good absorbent of water and other liquid, can absorb high-concentrations nutrients and can prevent the loss of evaporation of nutritional components effectively.Wholesale facial mask with high quality as low price/cheap, one of the facial mask leading brands from China, Shaoxing Extra Beauty Hygienics Co., Ltd.


Dry Facial Mask Sheet,Facial Mask Dry,Facial Masks For Skin,OEM Facial Mask.Face Mask Facial,Facial Mask Beauty

Shaoxing Extra Beauty Hygienics Co.,Ltd , https://www.cnextrabeauty.com