Solution
Hanvon OCR government&office e-government information acquisition system solutio
AddTime：2020-01-13 15:14:20 Hits：0
Bill/form/documents recognition---The application of“Hanvon OCR SDK”in government offices
With the pace of society information continually accelerating,people have unprecedented desires for fast and ordered information.Especially,the fast development of Internet/Intranet technology provides guarantees for the exchange and share of information as well as team collaboration and it also brings fresh information exchanges and application modes.Our construction of e-government affairs also enters a brand-new stage.With the improvement of information degree of all industries,applications of OA and ERP become more and more popularized in government agencies,enterprises and public institutions.In recent years,state organs,public institutions and large and medium enterprises all puts the most money into the infrastructure of network hardware.However,many enterprises have already set up OA systems without resource or fragmentary resources that troubles leaders cannot make decisions according to complete information.Now there are some strange phenomena in many enterprises.On the one hand,with high cost,OA system can not be made full use due to incomplete information,on the other hand,secretaries have original documents in hand walking among each department.With further application of Hanvon OCR technology in office automation system,this technology has laid a firm foundation for state organs,enterprises and public institutions to truly achieve paperless office.
The foundation of OA is the understanding of management and accumulation of information while technology is the only tool of OA.Only when we have profound understanding of management as well as management services,will OA comes to play,so does that when the information occurring in the office process has ordered accumulation and sedimentary accretion.
The application of Hanvon OCR technology can achieve documents’automatic type-in,storage and management,which not only thoroughly works out the problem of resource starvation and incompleteness,but also makes paperless office possible.
The application of Hanvon OCR technology completes and enriches OA resources which makes leaders can make decisions on the basis of complete information and let secretaries relax from tedious typing.It really achieves rapid delivery of e-documents in LAN or WAN.
1、user requirements
Information accumulation is the foundation to truly realize OA.Office,actually,refers to the process of documents’making,modification,delivery,identification,saving,destroying and archiving.Traditional mode mainly uses paper-based medium,but in the tide of information revolution,it obviously can not meet the needs of highly efficient and fast-paced modern work and life.How to realize automation of information processing and paperless OA has gradually attracted people’s attention.
Traditional office modes leave us millions of paper documents.How to rapidly transfer paper information into computer-readable digital information,the inputting way seems to be especially important.OA users will achieve the overall goal of paper document input way in the following aspects:
1)Realize automatic type-in,storage and management of various documents
2)Realize resource sharing truly and fully
3)Eliminate and avoid“dead space”of document circulation to make information operation flexible vertically and horizontally.
4)Offer leaders sufficient and complete data for decisions.
5)Improve work efficiency,lower cost and avoid overlapping investment.
6)Easy to use;try to combine with traditional office mode
2、Hanvon OCR technology in government office/E-government affairs system
In the information era,people generally use a computer to improve personal work efficiency.The notion of OA has been raised for years,but its effect is not obvious.People still remain at OA’s primary stage of single-machine word and form processing.How to increase the overall productivity?The key point is to establish a safe,reliable,open and efficient information network,OA,and information management computerization system.This system provides modern daily office conditions for administrative department and ample integrated information services.It realizes archives management automation and office TP automation that improves office efficiency and management level.Besides,this system also makes daily business work of each department standard,electronic and normal and enhances manageability to documentary archives,personnel archives,technical record,finance files etc.In addition,the system realizes information on-line inquiry and on-line borrowing and finally achieves paperless office.
OA system integrator integrates“Hanvon standard print form OCR SDK development kit”with its developed OA system by organic integration of OCR technology and scanners,which efficiently solves the bottleneck problem of information inputting in other related fields including information-based government administration and enterprise information etc.
Flow chart of“Hanvon OCR technology”application in government office/E-government affairs system is as shown in the figure below:
Date sorting：
For ease of scanning and data classification,dismount,name and number for further inquiring and searching.
Scanning：
Scanning is a process to input paper manuscript images into computer.Generally,the related manuscripts are orderly scanned and after automatic detection and amendment of scanning quality control procedure,the scanned manuscripts will automatically save into data base.
Image processing：
In order to increase recognition rate,images will be eliminated blue and cleaned,that is,to remove noise that may effect image recognition rate,such as pocking marks,underline etc.Image quality control procedure will automatically monitor picture processing quality.
Layout Analysis：
Automatically understand and locate layouts,distinguish restricted places from horizontal text area,vertical text area,form area and image area,automatic layout analysis runs in background and operator can affirm on the front ending with manual intervention when necessary.
Recognition：
Transfer character images into computer language code;recognize Chinese in block letter(simplified Chinese character&complicated Chinese character)form,Chinese and English hybrid alignment;the recognized character encodes include GB,BIG5,GBK.Recognition process runs in the background.
Vertical Proof-reading：
Powerful error checking and correcting capabilities;it is to recognize one image or some images into a same character image to display in rank and highlight colors to mark doubtful words for ease of finding and modifying mistakes.
Horizontal Proof-reading：
It is a traditional manual proofreading method that operator can directly compare recognition results and original images for finding error characters.System will automatically call out corresponding image and make comparison,at the same time,use striking color to mark characters with low reliability.
Layout Restore：
Restore the modified text into the same layout as the original one for online reading and inquiring digitization documents in RTF、PDF、HTML.
Data Loading：
Storage of digitization documents
The process of OCR inputting data base includes scanning&inputting,image processing,layout analysis,recognition,vertical proof-reading,horizontal proof-reading,layout restore etc.
Inputting functions of common paper documents：
The supported document layout is leading in China that supports division and recognition of complex layout.Legends are as follow:
Inputting functions of official document：
It can exactly recognize areas of title,main body and official seal;and accurately restore recognized results according to original layout.Graphic symbols are as follow:
Form inputting function:
Hanvon OCR form recognition technology has strong recognition function and can provides operation relations between data logic and arithmetic.Particular processing function has been designed for forms that can meet various complex recognition needs and it supports modification before data loading,which ensures the final loading data meet the demand.
3、Comparison between“Hanvon standard print form OCR SDK development kit”recognized results and original images
As mentioned above in the function introduction of“Hanvon standard print form OCR SDK development kit”,adopting“Hanvon standard print form OCR SDK development kit”can realize recognition of text information in designated areas,acquire text information（area in the image,typeface,reliability and candidate characters）,save recognition results in forms of TXT、RTF、PDF etc.thereinto,RTF and PDF support layout restore of original layout.The following is the comparison between original image and specimen image as well as its recognition results by using Hanvon OCR technology
Previous Article ：Hanvon OCR VAT invoice automatic input system solutions
Next Article ：Hanvon “Easy Recognition” almighty image-text recognition system application sch
