Food Vision: Ai- Based Food Detection And Calorie Estimation Using Yolov8

• Author(s):

  Sanchita Gadkari | Vaishnavi Khedkar | Sayali Ahire | Vanita Thite | Prof.Vikram Chavan

• Keywords:

  Food Detection, YOLOv8, Calorie Estimation, Deep Learning, Computer Vision, Flask, Nutrition Analysis, Artificial Intelligence.

• Abstract:

  The Growing Interest In Healthy Eating And Nutritional Tracking Has Led To A Need For Smart Systems That Can Automatically Identify Food Items And Estimate Their Calorie Content. Traditional Calorie Tracking Apps Rely Heavily On Manual User Input, Which Can Be Inaccurate And Time-consuming. To Address These Issues, Food-vision Is Introduced As An AI-based Food Detection And Calorie Estimation Platform That Uses Advanced Deep Learning Techniques. The System Uses The YOLOv8 Object Detection Model To Identify Multiple Indian Food Items From Uploaded Images And Estimate Calorie Values From A Structured Nutritional Database. Unlike Standard Image Classification Systems That Can Only Recognize One Food Item At A Time, This Solution Detects Multiple Food Categories Simultaneously, Including Biryani, Dosa, Idli, Rice, Roti, Dal, Chloe, , Jalebi, Shahi Paneer, Palak Paneer, Pooh, And Samosa. The System Runs Through A Flask-based Web Application That Lets Users Upload Food Images And Get Instant Detection Results Along With Calorie Information. A Custom Annotated Dataset Of Thousands Of Food Images Was Created For Training And Validation. The YOLOv8 Architecture Delivers High Detection Accuracy While Ensuring Efficient Processing Speed. Experimental Results Show That This Approach Effectively Combines Computer Vision, Deep Learning, And Nutritional Analysis To Support Users In Dietary Monitoring And Health Management.

---

Other Details

• Paper id:

  IJSARTV12I6105617

• Published in:

  Volume: 12 Issue: 6 June 2026

• Publication Date:

  2026-06-07

Download Article