Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{160326,
        author = {Tilak Patil and Sohan Shrungare and Gaurav Lokhande and Govind Pole},
        title = {Deep Learning Instance Segmentation for Estimating the Nutritional Value of Food},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {10},
        number = {1},
        pages = {200-207},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=160326},
        abstract = {Poor dietary choices can have detrimental effects on health, impacting overall well-being. Consuming a diet containing excess of saturated fats and sugar, also overconsumption of processed foods can increase the risk of obesity and increase the susceptibility to heart disease, diabetes, high blood pressure, and certain cancers. Conversely, inadequate intake of essential nutrients such as vitamins, minerals, and fiber can lead to malnutrition, resulting in a weakened immune system, impaired growth and development, and heightened vulnerability to infections and diseases. Mental health and cognitive function can also be adversely affected by a suboptimal diet. It is crucial to maintain a balanced and diverse diet that provides nutrients required for optimal health. To address this issue, one potential solution is the daily consumption of quantified food. Recent advancements in computer vision and deep learning have facilitated the estimation of food calories from images, leading to the development of mobile applications that employ food image recognition to not only identify food items but also estimate their calorie content. This paper provides research on image-based food estimation for accurate calorie counts, evaluating aspects such as scalability, feasibility, and potential avenues for future work. This research paper introduces an image-based approach for estimating the nutrient content of food items from their images. The study explores various methodologies, including Fast R-CNN and Mask R-CNN, to achieve accurate nutrient estimation. The paper delves into the details of these methodologies and evaluates their effectiveness in this context.},
        keywords = {Body Mass Index (BMI), Word2Vec, VGG16, Calorie Estimation, Convolution Neural Network, Recurrent Neural Network.},
        month = {},
        }