Community

Post Processing in ABBYY Finereader

Abbyy OCR often outputs characters like '0' as 'O' , 'l' as '1' and a few more.Such similar characters are not getting recognized properly.Is there any workaround for this problem?? 

I have been trying to solve this on my own.Kindly let me know a solution/workaround for this problem.

Was this article helpful?

0 out of 0 found this helpful

Comments

1 comment

  • Avatar
    Permanently deleted user

    Hey,

    I had the same problem. You can try the following things:

    • Choose a correct language
    • Add the words to a custom dictionary and use it with the RecognizerParams 
    • Use regular expressions while comparing 

    User dictionary example:

    private FREngine.TextLanguage fillLangDatabase() {
    
                string dictionaryFileName = "D:\\Sample.amd";
                string sName = "UserTL";
    
                // Create a LanguageDatabase object
                FREngine.LanguageDatabase languageDatabase = engineLoader.Engine.CreateLanguageDatabase();
                FREngine.TextLanguage textLanguage = languageDatabase.CreateTextLanguage();
    
                // Copy all attributes from the predefined English language
                FREngine.TextLanguage englishLanguage = engineLoader.Engine.PredefinedLanguages.Find("English").TextLanguage;
                textLanguage.CopyFrom(englishLanguage);
                textLanguage.InternalName = "SampleTL";
    
                // Bind new dictionary to the first (and only) BaseLanguage object within TextLanguage
                FREngine.BaseLanguage baseLanguage = textLanguage.BaseLanguages[0];
                baseLanguage.InternalName = "SampleBL";      
    
                // Create new dictionary
                string dictionaryFilePath = dictionaryFileName;
                FREngine.Dictionary dictionary = languageDatabase.CreateNewDictionary(dictionaryFilePath, FREngine.LanguageIdEnum.LI_EnglishUnitedStates);
                dictionary.Name = "Sample";
    
                // Add words with space to the dictionary
                dictionary.AddWord("TestWord", 100);
                ...   
                ... // Get the collection of dictionary descriptions and remove all items FREngine.DictionaryDescriptions dictionaryDescriptions = baseLanguage.DictionaryDescriptions; //dictionaryDescriptions.DeleteAll(); FREngine.IDictionaryDescription dic = dictionaryDescriptions.AddNew(FREngine.DictionaryTypeEnum.DT_UserDictionary); FREngine.UserDictionaryDescription userDic = dic.GetAsUserDictionaryDescription(); userDic.FileName = dictionaryFilePath; return textLanguage; }

     

     

    0

Please sign in to leave a comment.