Food Snap AI

Ai/aiModel.py

@@ -0,0 +1,85 @@
+import keras
+from keras.models import Sequential
+from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout
+#from keras.preprocessing.image import ImageDataGenerator
+from keras.src.legacy.preprocessing.image import ImageDataGenerator
+from keras.layers import GlobalAveragePooling2D
+import matplotlib.pyplot as plt
+
+ # Food Snap AI Model
+
+model = Sequential([
+
+    # Conv2D extracts features like edges, texttures, colors of fruits and its patterns
+    Conv2D(32, (3,3), activation="relu", input_shape=(244,244,3)),
+    # Pooling layer used to reduce dimenstions of feature map from previous layers before passing to next layer, Make computation faster while keeping relevant info
+    MaxPooling2D(pool_size=(2,2)),
+
+    Conv2D(64, (3,3), activation='relu'),
+    MaxPooling2D(pool_size=(2,2)),
+
+    Conv2D(128, (3,3), activation='relu'),
+    MaxPooling2D(pool_size=(2,2)),
+
+    GlobalAveragePooling2D(),
+    # converts 2D feature maps into a single vector for classification
+    Flatten(),
+
+    Dense(128, activation='relu'),
+    # prevents overfitting, so model generalizes better.
+    Dropout(0.5), # Reduces overfitting
+    # Uses Softmax for multi-class classification
+    Dense(3, activation="softmax") # 3 output classes (Apple, Banana, Mango)
+])
+
+model.compile(
+    optimizer='adam',
+    loss='categorical_crossentropy',
+    metrics=['accuracy']
+)
+
+#Data Augmentation
+train_datagen = ImageDataGenerator(
+    rescale =1./255, #Normalize pixel values (0 to 1 instead of 0 to 255)
+    rotation_range = 20, # Randomly rotate image by up to 20 degress
+    width_shift_range = 0.2, # Shift image width randomly by 20% (left or right)
+    height_shift_range = 0.2, # Shift image height randomly by 20% (up or down)
+    horizontal_flip = True, # Flip images randomly (left-right)
+    validation_split = 0.2 # reserve 20% data for validation
+)
+
+#Loading Images from folder
+train_generator = train_datagen.flow_from_directory(
+    'dataset/', 
+    target_size = (224, 224),
+    batch_size = 32,
+    class_mode = 'categorical', #Automatically assigns labels based on folder names
+    subset = 'training' #uses 80% images for training
+)
+
+# Preparing Validation Data
+val_generator = train_datagen.flow_from_directory(
+    'dataset/',
+    target_size = (244, 244),
+    batch_size = 32,
+    class_mode = 'categorical',
+    subset = 'validation'
+)
+
+#Start CNN training
+history = model.fit(
+    train_generator,
+    validation_data= val_generator,
+    epochs= 30
+)
+
+# Elavuate & Visualize results
+plt.plot(history.history['accuracy'], label='Training Accuracy')
+plt.plot(history.history['val_accuracy'], label='Validation Accuracy')
+plt.xlabel('Epochs'),
+plt.ylabel('Accuracy')
+plt.legend()
+plt.show()
+
+# Save model
+model.save("food_classifier_model_v2.h5")

Ai/aiModelApp.py

@@ -0,0 +1,39 @@
+from flask import Flask, request, jsonify
+from keras.models import load_model
+import numpy as np
+from PIL import Image
+
+# To Run  flask --app .\aiModelApp.py run
+
+app = Flask(__name__)
+model = load_model("food_classifier_model_v2.h5")
+
+def preprocess_image(image):
+    image = Image.open(image).resize((224,224)) #Resize to match CNN input
+    image = np.array(image) / 255.0 #normalize pixel value
+    image = np.expand_dims(image, axis=0)
+    return image
+
+@app.route('/detect-image', methods=['POST'])
+def detectImage():
+    file = request.files['image']
+    processed_image = preprocess_image(file)
+
+    prediction = model.predict(processed_image)
+    food_classes = ['Apple', 'Banana', 'Mango']
+
+    predicted_index = np.argmax(prediction)
+    predicted_class = food_classes[predicted_index]
+    confidence_score = float(prediction[0][predicted_index] * 100)
+
+    # convet full prediction into dict
+    prediction_dict = {food_classes[i]: round(float(prediction[0][i])* 100, 2) for i in range(len(food_classes))}
+
+    return jsonify({
+        "prediction": predicted_class,
+        "confidence": round(confidence_score, 2), #rounded to 2 decimal places
+        "fullPrediction": prediction_dict #show all
+        })
+
+if __name__ == '__main__':
+    app.run(port=5000, debug=True)

Ai/dataset/dataPreProcess.py

@@ -0,0 +1,14 @@
+import cv2
+import os
+import tensorflow as tf
+
+folderList = ["apple", "banana", "mango"]
+
+for folder in folderList:
+    for fileName in os.listdir(f"dataset/{folder}"):
+        image = cv2.imread(f"dataset/{folder}/{fileName}")
+        resized = cv2.resize(image, (224, 224)) #Resize to match CNN input
+
+        cv2.imwrite(f"dataset/{folder}/{fileName}", resized)
+
+

Client/.editorconfig

@@ -0,0 +1,17 @@
+# Editor configuration, see https://editorconfig.org
+root = true
+
+[*]
+charset = utf-8
+indent_style = space
+indent_size = 2
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+[*.ts]
+quote_type = single
+ij_typescript_use_double_quotes = false
+
+[*.md]
+max_line_length = off
+trim_trailing_whitespace = false

Client/.gitignore

@@ -0,0 +1,42 @@
+# See https://docs.github.com/get-started/getting-started-with-git/ignoring-files for more about ignoring files.
+
+# Compiled output
+/dist
+/tmp
+/out-tsc
+/bazel-out
+
+# Node
+/node_modules
+npm-debug.log
+yarn-error.log
+
+# IDEs and editors
+.idea/
+.project
+.classpath
+.c9/
+*.launch
+.settings/
+*.sublime-workspace
+
+# Visual Studio Code
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+.history/*
+
+# Miscellaneous
+/.angular/cache
+.sass-cache/
+/connect.lock
+/coverage
+/libpeerconnection.log
+testem.log
+/typings
+
+# System files
+.DS_Store
+Thumbs.db

Client/.vscode/extensions.json

@@ -0,0 +1,4 @@
+{
+  // For more information, visit: https://go.microsoft.com/fwlink/?linkid=827846
+  "recommendations": ["angular.ng-template"]
+}

Client/.vscode/launch.json

@@ -0,0 +1,20 @@
+{
+  // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "name": "ng serve",
+      "type": "chrome",
+      "request": "launch",
+      "preLaunchTask": "npm: start",
+      "url": "http://localhost:4200/"
+    },
+    {
+      "name": "ng test",
+      "type": "chrome",
+      "request": "launch",
+      "preLaunchTask": "npm: test",
+      "url": "http://localhost:9876/debug.html"
+    }
+  ]
+}

Client/.vscode/tasks.json

@@ -0,0 +1,42 @@
+{
+  // For more information, visit: https://go.microsoft.com/fwlink/?LinkId=733558
+  "version": "2.0.0",
+  "tasks": [
+    {
+      "type": "npm",
+      "script": "start",
+      "isBackground": true,
+      "problemMatcher": {
+        "owner": "typescript",
+        "pattern": "$tsc",
+        "background": {
+          "activeOnStart": true,
+          "beginsPattern": {
+            "regexp": "(.*?)"
+          },
+          "endsPattern": {
+            "regexp": "bundle generation complete"
+          }
+        }
+      }
+    },
+    {
+      "type": "npm",
+      "script": "test",
+      "isBackground": true,
+      "problemMatcher": {
+        "owner": "typescript",
+        "pattern": "$tsc",
+        "background": {
+          "activeOnStart": true,
+          "beginsPattern": {
+            "regexp": "(.*?)"
+          },
+          "endsPattern": {
+            "regexp": "bundle generation complete"
+          }
+        }
+      }
+    }
+  ]
+}

Client/README.md

@@ -0,0 +1,27 @@
+# Client
+
+This project was generated with [Angular CLI](https://github.com/angular/angular-cli) version 18.2.11.
+
+## Development server
+
+Run `ng serve` for a dev server. Navigate to `http://localhost:4200/`. The application will automatically reload if you change any of the source files.
+
+## Code scaffolding
+
+Run `ng generate component component-name` to generate a new component. You can also use `ng generate directive|pipe|service|class|guard|interface|enum|module`.
+
+## Build
+
+Run `ng build` to build the project. The build artifacts will be stored in the `dist/` directory.
+
+## Running unit tests
+
+Run `ng test` to execute the unit tests via [Karma](https://karma-runner.github.io).
+
+## Running end-to-end tests
+
+Run `ng e2e` to execute the end-to-end tests via a platform of your choice. To use this command, you need to first add a package that implements end-to-end testing capabilities.
+
+## Further help
+
+To get more help on the Angular CLI use `ng help` or go check out the [Angular CLI Overview and Command Reference](https://angular.dev/tools/cli) page.