TextExtract 1.0.0

Tesseract Optimize is a optimize version of Tesseract to provide better text recognition.

Overview :

TextExtract is a optimize version of Tesseract to provide better text recognition.

Features :

1. Extract text from any image
2. Extract text which match expected text

Installation :

Prerequisite :

• Python 3.6+ (https://www.python.org/downloads/)
• Tesseract.exe file and DLLs('liblept177.dll','libtesseract400.dll','vcomp140.dll')
• Tesseract version used is : tesseract 4.0.0-beta.3

Using pip :

pip install TextExtract

Usage :

from TextExtract.TextExtractApi.TextExtract import TextExtractFunctions  
  
#Get single text without comparing text with expected  
result,scale=TextExtractFunctions.image_to_string_only("MenuIcon.png",lang='eng')
  
#Get texts from list of scaled images text with highest matching with expected text
result,match=TextExtractFunctions.image_to_string_matched("MenuIcon.png",expected_text='Menu',lang='eng')
  
#Get list of result with matches results  
finalresult,scaled_results=TextExtractFunctions.image_to_string_matched("MenuIcon.png",expected_text='Menu',all_results=True)

Contact Information :

Email: [e-mail]