| --- |
| license: gpl-3.0 |
| library_name: tensorflow |
| tags: |
| - tensorflow |
| - keras |
| - image-classification |
| - computer-vision |
| - food |
| - nutrition |
| - nutrivision |
| --- |
| |
| # NutriVision CNN Model |
|
|
| This repository contains the trained CNN model used by **NutriVision**, a mobile application designed to analyze food and nutrition labels from images. |
|
|
| The model is distributed separately from the main NutriVision source repository because the trained weights are a relatively large binary file and are better suited to dedicated model hosting. |
|
|
| ## About NutriVision |
|
|
| NutriVision is a full-stack mobile application that combines image processing, OCR, machine learning, and nutrition/ingredient parsing to turn information from food packaging into structured results that are easier to understand. |
|
|
| The overall pipeline looks roughly like this: |
|
|
| ```text |
| Food / Nutrition Label |
| │ |
| â–¼ |
| Camera Image |
| │ |
| â–¼ |
| Image Processing |
| │ |
| â–¼ |
| OCR |
| (EasyOCR) |
| │ |
| â–¼ |
| Nutrition / Ingredient |
| Parsing |
| │ |
| â–¼ |
| CNN Processing |
| │ |
| â–¼ |
| Structured Analysis |
| │ |
| â–¼ |
| NutriVision App |
