• sagarika N
• Saleem Sultani
• Shaik Rehan Hussain
• Shaik K Rizwan

A subset of artificial intelligence, machine learning is seeing significant global research progress. It has the capacity to learn on its own, drawing on its prior knowledge and experience, without the aid of humans or any explicit programming. Conventional scanners have several limitations, though, including their size but also somewhat laborious operation. Researchers recognise handwritten text and text extracted from photos using a variety of machine learning techniques and tools before scanning it. A machine learning approach called optical character recognition (OCR) enables us to recognise and extract text information from documents, turning it into editable and searchable data. In this study, we examine the necessity of document scanning and how, by converting scanned documents, this portable application can assist users in bridging the linguistic gap across states depending on regional language. The proposed method uses Natural Language Processing (NLP) to intelligently recognise and extract text. Convolutional Neural Network (CNN) is implemented with OCR. Moreover, OCR produces results of the recognised text, which are then obtained using Python libraries. Hence, it provides a solution for text detection and extraction, that are crucial and often complex. The goal of this research is to make communication easier for people around the world to read and comprehend any written language and the model obtained an accuracy of 96%.

— Text extraction, Text detection, Pre-Processing, Segmentation, Machine Learning Algorithms, Optical Character Recognition (OCR).

"Text extraction and detection using machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.c329-c333, May-2023, Available :http://www.jetir.org/papers/JETIR2305247.pdf

"Text extraction and detection using machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppc329-c333, May-2023, Available at : http://www.jetir.org/papers/JETIR2305247.pdf