Inverse Cooking AI: Image-Based Food Recognition and Recipe Generation Using GUI Applications

Authors

  • GOTTUMUKKALA TEJASWINI, V.SARALA Author

DOI:

https://doi.org/10.62643/

Keywords:

Inverse Cooking, Image Processing, Recipe Generation, Tkinter GUI, Food Recognition, Artificial Intelligence, Computer Vision, Human-Computer Interaction

Abstract

The advancement of artificial intelligence and computer vision has enabled innovative applications that bridge the gap between visual perception and semantic understanding. One such application is inverse cooking, where a system predicts recipes and ingredients from food images. This project presents an intelligent desktop-based graphical user interface (GUI) system that performs image-based food recognition and generates corresponding recipes using a lightweight AI-inspired approach. The proposed system integrates image processing techniques with a rule-based prediction model to identify food items from user-provided images. The system is developed using Python and the Tkinter framework, ensuring simplicity, portability, and ease of use. The application allows users to upload food images, processes them to ensure compatibility (handling different image formats and color modes), and predicts the most likely dish based on filename heuristics. Although the model is simplified compared to deep learning-based approaches, it effectively demonstrates the concept of inverse cooking in a resourceefficient manner. The system maintains a structured food database containing recipes, ingredients, cooking instructions, nutritional values, preparation time, servings, and difficulty levels. Upon detecting the food type, the system retrieves and displays relevant information in a user-friendly format. The GUI is designed with modern aesthetics, including dark-themed layouts and intuitive controls, enhancing user experience. One of the key contributions of this project is the robust handling of image formats, including RGB and RGBA conversions, which eliminates common errors related to unsupported image modes. Additionally, the application ensures stability by managing large image sizes and providing error handling for invalid inputs. This work highlights the feasibility of building an inverse cooking assistant without relying on heavy machine learning models, making it suitable for low-resource environments. It serves as a foundational prototype that can be extended with advanced deep learning models such as convolutional neural networks (CNNs) or transformer-based architectures for more accurate food recognition. In conclusion, the system demonstrates how AI concepts can be integrated into practical applications to enhance everyday tasks like cooking. It opens avenues for future improvements, including real-time image recognition, integration with
online recipe databases, and personalized dietary recommendations.

Downloads

Published

04-04-2026

How to Cite

Inverse Cooking AI: Image-Based Food Recognition and Recipe Generation Using GUI Applications. (2026). International Journal of Engineering Research and Science & Technology, 22(2), 983-992. https://doi.org/10.62643/