This is my first real project. Where I have to predict the intent of website from the screenshot of the home page of a website that in which category it falls.
- Educational Website
- E-commerce Website
- Job Website
The project inlcude the following step
- Data Gathering: I first gather the data which was taking screen from the whole home page of the website and saving in the pc. I gather the data in three categories
1.Education
2.Job
3.E-commerce
- The File name Text Extraction from Images do extract the text the from the images with help pytersseract. It contain the code the how to extract text from the image and store in the csv file
- I then store the data from the output.csv to X, y and do some preprocessing
- Tfidf Vectorizer is to convert the text to embedding to then apply model on it
- A model is train on the data from which I gather and get an accuracy 90.01 something
The Model is Complete and have accurately predict the other Websites. If you need any help contact me at (pirzadahasnain.18@gmail.com)