In this project, developed a computer vision system using Convolutional Neural Networks (CNN) to automatically recognize and detect different food items in images. The goal was to enable users to take a picture of their meal and get instant recipe suggestions based on the identified food items.
I trained the CNN model on a large dataset of food images with corresponding recipe labels. The model learned to identify various ingredients and dishes accurately. To achieve this, I preprocessed the images, extracted relevant features, and fine-tuned the CNN architecture to optimize its performance.
The application of the project involves taking a photo of a dish or meal, passing it through the trained model, and then displaying a list of possible recipes that match the detected ingredients. The user can select a recipe of their choice to get detailed cooking instructions.
The project aims to simplify cooking experiences, assist people in discovering new recipes based on the ingredients they have, and help in reducing food waste by suggesting recipes that utilize leftover ingredients effectively.
Throughout the development process, I encountered challenges related to data collection, model training, and fine-tuning to achieve accurate predictions. The project taught me valuable skills in deep learning, image processing, and dataset management.
In conclusion, "Recipe Detection of Food Image using Deep Learning (CNN)" is a practical and innovative project that leverages machine learning techniques to make cooking more convenient and enjoyable for users.
Recipe Detection Of Image Using Deep Learning.pptx
1. SIDDHANT COLLEGE OF ENGINEERING, SUDUMBARE, PUNE
SAVITRIBAI PHULE PUNE UNIVERSITY
Department of Information Technology
A.Y 2022-2023
GROUP MEMBERS Seat number
• Dhawal Tank T190448536
• Pradeep Paymode T190448531
• Sanyam Gandhi T190448512
• Sanket Ghorpade T190448514
Recipe Detection of Food Images using Deep Learning
GUIDED BY -: Prof. Rashmi Kulkarni (IT
Department)
2. INTRODUCTION TO PROJECT
• Our main purpose of project is to find out Recipe by using Image
Processing. Given input as image of food like (panner tikka, Dum-biryani,
aloo mutter etc.) give output of Food Recipe as well as we also showing the
nutrients present in the food for the health factor.
• The purpose of our project is the processing of images obtained from
various sensors, the selection of images and their subsequent classification.
• Today, high results in pattern recognition are obtained using convolutional
neural networks (CNN). With a sufficiently large size, CNN has a small
number of configurable parameters and trained quite quickly, which allows
them to be called the most universal and effective neural network models for
food images problems.
3. PROBLEM STATEMENT
People are always tempted to try out new dishes which they find on the web
and social media watching pics and videos of different food items around the
globe and seek for information on how to cook them.
This could be a very tricky and long process.Also in Indian culture still many
of the housewifes are not much skilled into surfing the web for finding
information about something based on just its image.
4. OBJECTIVE OF THE PROJECT
1.All user give input as food image then pre-processing on given input
removing unwanted data, and feature Extraction and then classify the image
using CNN And give output
2. To detect the nutrition value in the food.
3. Link for making of the deteted Image.
4. To help user identify the recommended food item
9. Sr. No. Author Title Result
1 Sosuke Amano,
Kiyoharu Aizawa.
Food Category
Representatives: Extracting
Categories from Meal Names
in Food Recordings and
Recipe Data
FoodLog is a multimedia recording
tool for producing food records for
many individuals.
2 Pakawan Pugsee,
Monsinee Niyomvanich.
Suggestion Analysis for Food
Recipe Improvement
Suggestion analysis for food
recipe improvement is to identify
helpful suggestions from user
comments to improve the recipes.
3 David J. Attokaren, Ian
G. Fernandes, A.
Sriram, Y.V. Srinivasa
Murthy, and Shashidhar
G. Koolagudi
Food Classification from
Images Using Convolutional
Neural Networks (2017)
In this paper, The process of
identifying food items from an
image is quite an interesting field
with various applications.
10. ALGORITHM
CNN Algorithm:-
Convolutional Neural Networks specialized for applications in image & video
recognition. CNN is mainly used in image analysis tasks like Image
recognition, Object detection & Segmentation.
There are Four types of layers in Convolutional Neural Networks
1) Convolutional Layer: In a typical neural network each input neuron is
connected to the next hidden layer. In CNN, only a small region of the input
layer neurons connect to the neuron hidden layer.
2) Pooling Layer: The pooling layer is used to reduce the dimensionality of
the feature map. There will be multiple activation & pooling layers inside the
hidden layer of the CNN.
11. 3) Flatten: Flattening is converting the data into a 1-dimensional
array for inputting it to the next layer. We flatten the output of the
convolutional layers to create a single long feature vector.
4) Fully-Connected layer: Fully Connected Layers form the last
few layers in the network. The input to the fully connected layer is the
output from the final Pooling or Convolutional Layer, which is flattened
and then fed into the fully connected layer.
14. User access
Real time
Streaming
Frontend
UI Will fetch the data from real time monitoring
system
API
Interface Cleaning
Pre-processing
Detection
Classification
Backend Processing
by model
Result
s
15. FUNCTIONAL REQUIREMENTS
• EXTERNAL INTERFACE REQUIREMENT
• User Interface Application Based Food classification.
• Hardware Interfaces: RAM : 8 GB As we are using Machine Learning Algorithm and
Various High Level Libraries Laptop RAM minimum required is 8 GB.
• Hard Disk : 40 GB Data Set of CT Scan images is to be used hence minimum 40 GB
Hard Disk memory is required.
• Processor : Intel i5 Processor Pycharm IDE that Integrated Development Environment
is to be used and data loading should be fast hence Fast Processor is required
16. IDE : PYCHARM BEST INTEGRATED DEVELOPMENT ENVIRONMENT AS IT
GIVES POSSIBLE SUGGESTIONS AT THE TIME OF TYPING CODE SNIPPETS
THAT MAKES TYPING FEASIBLE AND FAST.
CODING LANGUAGE : PYTHON VERSION 3.5 HIGHLY SPECIFIED
PROGRAMMING LANGUAGE FOR MACHINE LEARNING BECAUSE OF
AVAILABILITY OF HIGH PERFORMANCE LIBRARIES.
OPERATING SYSTEM : WINDOWS 10 LATEST OPERATING SYSTEM THAT
SUPPORTS ALL TYPE OF INSTALLATION AND DEVELOPMENT
ENVIRONMENT
SOFTWARE INTERFACES OPERATING SYSTEM: WINDOWS 10
IDE: PYCHARM ,SPYDER
PROGRAMMING LANGUAGE : PYTHON
17. NON FUNCTIONAL DESIGN
• Performance Requirements The performance of the functions and every
module must be well. The overall performance of the software will enable
the users to work exactly. Performance of encryption of data should be fast.
Performance of the providing virtual environment should be fast
• Software Quality Attributes Our software has many quality attribute that
are given below:-
1. Adaptability: This software is adaptable by all users. Availability: This
software is freely available to all users. The availability of the software is
easy for everyone. College Short Form Name, Department of Computer
Engineering
18. • Maintainability: After the deployment of the project if any error occurs then
it can be easily maintained by the software developer.
Reliability: The performance of the software is better which will increase the
reliability of the Software.
User Friendliness: Since, the software is a GUI application; the output
generated is much user friendly in its behavior.
Integrity: Integrity refers to the extent to which access to software or data
by unauthorized persons can be controlled.
24. In this proposed system, the Convolutional Neural Network, a Deep
learning technique is used to classify the food images in to their
respective classes. The dataset considered is the Indian food dataset
and train dataset using CNN algorithm. Indian food image classification
system, classify the which type of food and recipe and also to
automatically analyze the nutritional and calorie information.
CONCLUSION
25. FUTURE SCOPE
As far as the future enhancement is concerned, the task of classification
can be improved by removing noise from the dataset. The same
research can be carried out on larger dataset with a greater number of
classes and a greater number of images in each class, as larger
dataset improves the accuracy by learning more features and reduces
the loss rate. The weights of the model can be saved and used to
design a web app or mobile app for image classification and further
calories extraction of the classified food.
26. REFERENCES
[1] Zhou, L., Zhang, C., Liu, F., Qiu, Z., & He, Y, “Application of Deep Learning in Food: A Review,”
Comprehensive Reviews in Food Science and Food Safety, vol. 18, pp. 1793-1811, 2019.
[2] Xia, J., Ghamisi, P., Yokoya, N., & Iwasaki, A., “Random Forest Ensembles and Extended Multiextinction
Profiles for Hyperspectral Image Classification,” IEEE Transactions on Geoscience and Remote Sensing,
vol. 56 , pp. 202-216, 2018, doi:10.1109/TGRS.2017.2744662.
[3] Wang, M., Wan, Y., Ye, Z., & Lai, X.,“Remote sensing imageclassification based on the optimal support
vector machine andmodified binary coded ant colony optimization algorithm,’Information Sciences, vol. 402,
pp. 50-68, 2017
[4] Farinella, G. M., Moltisanti, M., & Battiato, S., “Classifying food images represented as Bag of Textons,” IEEE
International Conference on Image Processing (ICIP), Paris, pp. 5212-5216, doi: 10.1109/ICIP.2014.7026055, 2014.
[5] Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., & Oliva, A., “Learning deep features for scene recognition using places
database,” Proceedings of the 27th International Conference on Neural Information Processing Systems, vol. 1, pp. 487-
