This study shows an in-depth analysis of optical character recognition (OCR) techniques for extracting and distinguishing Gujarati and English text from documents that contain both languages is provided in this paper. Gujarati script presents unique issues that are addressed, including its complex structure, diacritical marks, and conjunct letters, which make text extraction quite challenging, especially in multilingual documents. To efficiently separate and process Gujarati and English information, our suggested system makes use of advanced pre-processing techniques, good text segmentation, and precise language identification. The existing OCR engines are assessed, and any necessary changes are made to improve their ability to process documents in various languages. This research advances digital document processing and multilingual text extraction by enhancing OCR for Gujarati and English and providing solutions applicable to other languages with comparable difficulties. This work lays the groundwork for the development of more reliable multilingual OCR systems that can be applied to other languages with comparable complexity, in addition to advancing OCR technology for regional languages. Our research contributes to the larger objective of attaining accurate and efficient text extraction in an increasingly multilingual digital context by filling the gap in OCR capabilities.