Implementing Image Recognition Technique to Find and Read Objects or Data from Images
Khan, Moeez (2025)
2025
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2025051612482
https://urn.fi/URN:NBN:fi:amk-2025051612482
Tiivistelmä
Data extraction from images and Image recognition are important tasks in many fields, enabling automatic visual information processing such as searching.*
This project implements a simple web application that allows a user to upload an image, which is then processed using an AI-based method to identify objects and extract textual data. The methodology involved building a web page in HTML/CSS for the image upload interface, using a Flask Python backend to receive the image and send it to the ChatGPT vision-capable API. The returned objects and text are again displayed to the user by the frontend.
The project demonstrates the feasibility of using large language models for image analysis, highlights practical challenges (such as image size limits and cost), and suggests future improvements.
This project implements a simple web application that allows a user to upload an image, which is then processed using an AI-based method to identify objects and extract textual data. The methodology involved building a web page in HTML/CSS for the image upload interface, using a Flask Python backend to receive the image and send it to the ChatGPT vision-capable API. The returned objects and text are again displayed to the user by the frontend.
The project demonstrates the feasibility of using large language models for image analysis, highlights practical challenges (such as image size limits and cost), and suggests future improvements.