Automated text summarization is a crucial task in natural language processing, aimed at reducing the length of texts while preserving essential information. This work explores the integration of Optical Character Recognition (OCR) using EasyOCR and text summarization using Hugging Face Transformers to develop an efficient summarization system. The proposed system extracts textual data from images and generates concise summaries, making information retrieval more efficient and accessible. The methodology involves leveraging the pre-trained EasyOCR model for text extraction and the Transformer-based models from Hugging Face for generating summaries. The system's performance is evaluated based on its ability to produce coherent and relevant summaries. This approach can be particularly beneficial for applications requiring quick extraction and summarization of textual content from images, such as digital libraries, educational resources, and news media. The results indicate that combining OCR with advanced text summarization models can significantly enhance information processing capabilities, providing a robust solution for automated text summarization tasks.