VietOCR is open source software developed by Vietnamese people, which can recognize characters in po..
5.7.5| License: Free |
| Released: Quan Nguyen |
| Request: Windows NT/2000/2003/XP/Vista/7/8/8.1/10 |
| Last updated: 25-08-2021 |
| OS: Window |
| Version: 5.7.5 |
| Total download: 5522 |
| Capacity: 11,1 MB |
VietOCR is open source software developed by Vietnamese people, which can recognize characters in popular images. Support built-in scanning mode, as well as post-processing mechanism to fix semantic and spelling errors after processing.
VietOCR is used as a standalone optical character recognizer, helping to process image files and available data quickly. Besides, it also combines with scanning functions to process documents loaded from the outside.
The conversion of characters from images to text saves you a lot of time and effort while using it.
Normally, when scanning a text document, the received file will be saved as an image document and cannot be processed (deleting text, inputting data, editing content, ...) like the original. VietOCR will be in charge of converting these documents to text so that you will be able to process them easily. VietOCR supports many image formats such as jpg, bmp, png, tiff, but does not support gif format.
To use the program, you must install the Visual C 2008 SP1 package (if it is not already installed on your system), and then go to the menu File > Open, under
strong>File of types you choose All Image Files and load into the text file to be processed. Done, press the Open.
. button
Next, on the main interface, you will see 2 areas: the area on the left contains the content of the newly added document file, the right frame will be the document after extracting from the image file. Photo. When the content is loaded, click the OCR Language heading (upper right corner of the screen) and select Vietnamese. Then, press the OCR button to start the content translation process, the speed is fast or slow depending on the length, short of the text and the processing speed of the computer.
After compiling, you will have the text data immediately, which can be deleted or changed easily. One good point of VietOCR is the ability to integrate Vietnamese percussion (operating based on Unikey percussion), which makes it easy to change the content of accented text without the permanent Unikey percussion in the taskbar. To set the percussion in VietOCR, go to the menu Settings> Viet Input Method and choose one of the typing methods: VNI, Telex, VIQR with the built-in Unicode default Font.
In case you only need to identify a certain area, hold the left mouse button and drag it to the text area you need to extract. Then, only the content of this area will be displayed on the right pane of the screen. If you want to compile a multi-page document, go to the menu Command > OCR All Pages.
To "try" to test the program's ability to recognize text in different formats, the writer used the available text sample library (C:\Program Files\VietUnicode\VietOCR.NET\ samples) and use Windows' MS Paint software to save in other formats such as: PNG, JPG and BMP (256 bit) from the original file in .TIFF format
As a result, all 3 cases can recognize the text relatively accurately. However, the punctuation is not correct and some words are still misspelled, the meaning is unclear, but the level of compilation compared to the original version is relatively standard.
If your need is to process external documents through the program's scanning system, you need to install an additional scanner. To do this, go to the installation folder of VietOCR, find and copy the WIAAut.dll file (C:\Program Files\VietUnicode\VietOCR.NET) to the folder C:\Windows\System32.
Then, you go to Start > Run, type the command regsvr32 C:\Windows\System32\WIAAut.dll to register this library with Windows. When registration is complete, install the scanner driver and start the word processing process as above.
Attention:
- While compiling, sometimes you will encounter the error message Attemp to read or write protected memory, one of the causes of this error is because the text has been incorrectly defined. direction (displacement, instead of horizontal, the text has changed to vertical), you just need to press the Rotate button a few times to get the correct orientation.
- If you don't have a scanner and you still want to "experience" the software functionality, you'll be able to download the ImagePrinter utility, which helps you convert any document to its 4 supported formats. program (bmp, png, tiff, jpg). In case if you want to change the program interface to Vietnamese, you access the menu Settings> User Interface Language, select Vietnamese.
Similar to the image document recognition process above, in this case the scanned document will be divided into 2 types to check: plain text (text) and text with images. The process of processing and compiling is started as in step 1. The result is that the program recognizes the plain text well and encounters an OCR Operation error condition for documents with images. This also works for other formats.
1 thing to pay attention to, for the image recognition process to be accurate, the resolution of the scan must be 300dpi, not blurry, as clean and clear as possible.
Extraagrave;i can recognize image documents, VietOCR can also process PDF documents. To use this function in VietOCR, you must install the GPL package GhostScript 8.7. After the installation is complete, you do the same processing as above (for PDF documents containing images, the result is still the same error as in case 2).
Overall, VietOCR can handle Vietnamese text well, has relatively high accuracy and is compatible with many different image formats in plain text (no images), you will have You can use the text after processing to serve the job without having to spend a lot of time editing.
PDF Candy or PDF Candy Desktop is a free tool to convert files fr..
Full Font Set will provide you with all the most popular Vietname..
WPS Office Suite 2021 Free is a free office editing suite that pr..
XNote Stopwatch is a free stopwatch utility on PC. The XNote Stop..
Bluesofts AccHelper (Accounting Helper) is an Add-ins in Excel, w..
5
4
3
2
1
