lundi 23 juin 2014

tesseract ocr not recognizing a single word


Vote count:

0




i'm using tesseract ocr as below :



Dim image As New Bitmap(path)
Dim ocr As New tessnet2.Tesseract()
ocr.SetVariable("tessedit_char_whitelist", "0123456789٠‎١‎٢‎٣‎٤‎٥‎٦٧‎٨‎٩abcdefghijklmnopqrstuvwxyz")
'ocr.SetVariable("tessedit_char_whitelist", "jocelyne")
' If digit only
Dim nb As String = ""
Dim OcrPath As String = GetConfig("OCRFOLDER")

ocr.Init(OcrPath, "eng", False)
' To use correct tessdata
Dim result As List(Of tessnet2.Word) = ocr.DoOCR(image, Rectangle.Empty)


on the image i'm using i have 2 words ( one numeric and the other is alpha numeric) but what i'm facing is that the ocr is reading 7 words.. which means that every word is being cut into several words... the ocr is not reading the word as a single word



asked 53 secs ago






Aucun commentaire:

Enregistrer un commentaire