Published Paper Details:

The ubiquity of food images on social media and recipe-sharing platforms has created an opportunity for automating the generation of cooking recipes from visual cues. In this study, we propose a novel method for generating recipes from food images by harnessing Convolutional Neural Networks (CNNs). Our approach leverages the power of deep learning to analyze the visual features of food images and extract key ingredients and cooking instructions.We begin by collecting a diverse dataset of food images paired with corresponding recipes. We then design a CNN architecture tailored for this task, enabling it to recognize ingredients, cooking utensils, and cooking techniques from the images. The model's ability to understand the visual context of the ingredients is enhanced by incorporating attention mechanisms.Experimental results demonstrate the effectiveness of our method, with the generated recipes achieving high fidelity to the input images. We conduct thorough evaluations, including recipe quality assessments and user studies, to validate the practical utility of our approach.Our work paves the way for innovative applications in the culinary domain, such as automated recipe recommendation systems, real-time cooking assistance, and content generation for food-related platforms. We believe that our novel method for generating recipes from food images using CNNs represents a significant step forward in the convergence of computer vision and culinary arts.