{"id":79752,"date":"2020-08-28T19:54:44","date_gmt":"2020-08-28T14:24:44","guid":{"rendered":"https:\/\/techvidvan.com\/tutorials\/?p=79752"},"modified":"2026-06-03T14:55:20","modified_gmt":"2026-06-03T09:25:20","slug":"extract-text-from-image-with-python-opencv","status":"publish","type":"post","link":"https:\/\/techvidvan.com\/tutorials\/extract-text-from-image-with-python-opencv\/","title":{"rendered":"Extract Text from Image with Python & OpenCV"},"content":{"rendered":"

Python will automatically find and extract text from an image. Yes, Python can do amazing things. Let’s start working on this interesting Python project.<\/p>\n

A picture is worth a thousand words<\/p><\/blockquote>\n

You must have heard the quote many times right! Well, the saying is very true because sometimes the picture says it all.<\/p>\n

We have discussed the importance of a single picture so far and now it\u2019s time to learn something more interesting about it. In this python project, we will learn how to extract text content from images using openCV and tesseract. Now let\u2019s see how we can create this.<\/p>\n

What is Tesseract?<\/h3>\n

It is an open-source engine for optical character recognition (OCR). It efficiently reads text from images and is very easy to use. As mentioned earlier it is open source so it is free to use.<\/p>\n

Prerequisites<\/h3>\n

To implement this project you should have basic knowledge of:<\/p>\n

    \n
  1. Python<\/li>\n
  2. Tessaract<\/li>\n
  3. OpenCV.<\/li>\n
  4. Tkinter<\/li>\n<\/ol>\n

    Download Project Code<\/h3>\n

    Before proceeding ahead, please download the source code of Text Extraction Project: Extract Text from Image with Python<\/strong><\/a>.<\/p>\n

    Steps to start text extraction<\/h2>\n

    Let’s start the text detection and extraction project development<\/p>\n

    Install required libraries<\/h3>\n

    To install the libraries use pip installer from the command prompt \/ terminal:<\/p>\n

    Pip install opencv-python\r\nPip install pytesseract\r\npip install tkinter\r\n<\/pre>\n
    Create main.py<\/h3>\n
    Create main.py file and add the following code<\/p>\n
    Code:<\/strong><\/p>\n
    from tkinter import *\r\nfrom tkinter import filedialog\r\nfrom PIL import ImageTk, Image\r\nimport cv2\r\nimport pytesseract \r\n\r\npytesseract.pytesseract.tesseract_cmd = 'C:\\\\Program Files (x86)\\\\Tesseract-OCR\\\\tesseract.exe'\r\n\r\nroot = Tk()\r\nroot.title('TechVidvan Text from image project') \r\n\r\nnewline= Label(root)\r\nuploaded_img=Label(root)\r\nscrollbar = Scrollbar(root)\r\nscrollbar.pack( side = RIGHT, fill = Y )\r\n\r\n\r\ndef extract(path):\r\n    Actual_image = cv2.imread(path)\r\n    Sample_img = cv2.resize(Actual_image,(400,350))\r\n    Image_ht,Image_wd,Image_thickness = Sample_img.shape\r\n    Sample_img = cv2.cvtColor(Sample_img,cv2.COLOR_BGR2RGB)\r\n    texts = pytesseract.image_to_data(Sample_img) \r\n    mytext=\"\"\r\n    prevy=0\r\n    for cnt,text in enumerate(texts.splitlines()):\r\n        if cnt==0:\r\n            continue\r\n        text = text.split()\r\n        if len(text)==12:\r\n            x,y,w,h = int(text[6]),int(text[7]),int(text[8]),int(text[9])\r\n            if(len(mytext)==0):\r\n                prey=y\r\n            if(prevy-y>=10 or y-prevy>=10):\r\n                print(mytext)\r\n                Label(root,text=mytext,font=('Times',15,'bold')).pack()\r\n                mytext=\"\"\r\n            mytext = mytext + text[11]+\" \"\r\n            prevy=y\r\n    Label(root,text=mytext,font=('Times',15,'bold')).pack()\r\n\r\ndef show_extract_button(path):\r\n    extractBtn= Button(root,text=\"Extract text\",command=lambda: extract(path),bg=\"#2f2f77\",fg=\"gray\",pady=15,padx=15,font=('Times',15,'bold'))\r\n    extractBtn.pack()\r\n\r\ndef upload():\r\n    try:\r\n        path=filedialog.askopenfilename()\r\n        image=Image.open(path)\r\n        img=ImageTk.PhotoImage(image)\r\n        uploaded_img.configure(image=img)\r\n        uploaded_img.image=img\r\n        show_extract_button(path)\r\n    except:\r\n        pass  \r\n\r\nuploadbtn = Button(root,text=\"Upload an image\",command=upload,bg=\"#2f2f77\",fg=\"gray\",height=2,width=20,font=('Times',15,'bold')).pack()\r\nnewline.configure(text='\\n')\r\nnewline.pack()\r\nuploaded_img.pack()\r\n\r\nroot.mainloop()\r\n<\/pre>\n
    Explanation:<\/strong><\/p>\n
      \n
    1. Import all the required libraries (opencv, tkinter, tesseract)<\/li>\n
    2. Provide the location of the tesseract.exe file.<\/li>\n
    3. Tkinter provides GUI functionalities: open an image dialog box so user can upload an image<\/li>\n
    4. Let’s jump to the extract function which takes the path of the image as a parameter\n