[Tutorial] : Automated Quality Inspection System Using AI & Favoriot

Step-by-Step Guide: Automated Quality Inspection System Using AI & Favoriot

This guide outlines how to develop an Automated Quality Inspection System using AI, a camera, and the Favoriot IoT platform. The provided code is in Python, along with detailed explanations.

Step 1: Hardware & Software Preparation

Before getting started, ensure you have:

Raspberry Pi (or any computer with a camera)
HD Camera (Raspberry Pi Camera or USB Camera)
Python Installed
OpenCV & TensorFlow Libraries for image analysis
Internet Connection to send data to Favoriot

Step 2: Install Required Software

Run the following commands to install the necessary libraries:

sudo apt update && sudo apt upgrade -y sudo apt install python3-pip -y pip3 install opencv-python numpy requests tensorflow

Step 3: Train an AI Model for Defect Detection

You can use Transfer Learning with a pre-trained model like MobileNetV2. Below is an example of training the model:

import tensorflow as tf from tensorflow.keras.preprocessing.image import ImageDataGenerator  # Dataset configuration dataset_path = "dataset_defects" batch_size = 32 img_size = (224, 224)  datagen = ImageDataGenerator(rescale=1./255, validation_split=0.2)  train_data = datagen.flow_from_directory(     dataset_path,     target_size=img_size,     batch_size=batch_size,     class_mode="binary",     subset="training" )  val_data = datagen.flow_from_directory(     dataset_path,     target_size=img_size,     batch_size=batch_size,     class_mode="binary",     subset="validation" )  # Transfer Learning Model base_model = tf.keras.applications.MobileNetV2(input_shape=(224, 224, 3), include_top=False, weights="imagenet") base_model.trainable = False  model = tf.keras.Sequential([     base_model,     tf.keras.layers.GlobalAveragePooling2D(),     tf.keras.layers.Dense(1, activation="sigmoid") ])  model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])  # Train the model model.fit(train_data, validation_data=val_data, epochs=10)  # Save the model model.save("defect_detection_model.h5")

Step 4: Real-Time Defect Detection with Camera

This code captures images from the camera and detects defects using the trained AI model.

import cv2 import numpy as np import tensorflow as tf  # Load trained model model = tf.keras.models.load_model("defect_detection_model.h5")  # Start camera cap = cv2.VideoCapture(0)  while True:     ret, frame = cap.read()     if not ret:         break      # Preprocess image     img = cv2.resize(frame, (224, 224))     img = np.expand_dims(img, axis=0) / 255.0      # Predict defects     prediction = model.predict(img)[0][0]      # Display result on screen     label = "Defect Detected!" if prediction > 0.5 else "Product OK"     color = (0, 0, 255) if prediction > 0.5 else (0, 255, 0)      cv2.putText(frame, label, (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, color, 2)     cv2.imshow("Quality Inspection", frame)      # Exit when 'q' is pressed     if cv2.waitKey(1) & 0xFF == ord('q'):         break  cap.release() cv2.destroyAllWindows()

Step 5: Send Defect Reports to Favoriot

The system automatically sends the data to the Favoriot IoT Platform if a defect is detected.

1. Create a Device on Favoriot

Log in to Favoriot.
Navigate to Devices → Add Device.
Copy the Device ID and API Key.

2. Code to Send Data to Favoriot

import requests import json  # Favoriot credentials DEVICE_ID = "YOUR_DEVICE_ID" API_KEY = "YOUR_FAVORIOT_API_KEY" URL = "https://apiv2.favoriot.com/v2/streams"  def send_data_to_favoriot(status):     payload = {         "device_developer_id": DEVICE_ID,         "data": {             "status": status         }     }          headers = {         "Content-Type": "application/json",         "Apikey": API_KEY     }          response = requests.post(URL, data=json.dumps(payload), headers=headers)     print("Response from Favoriot:", response.json())  # Example usage (send data if defect detected) if prediction > 0.5:     send_data_to_favoriot("Defect Detected!") else:     send_data_to_favoriot("Product OK")

Step 6: Monitor Data on Favoriot

Go to Favoriot Dashboard → Streams to view defect reports.
You can also create a dashboard to visualize real-time defect detection data.

Conclusion

With this system, you can:

✅ Automatically detect defects using AI.
✅ Display results in real-time on the screen.
✅ Send defect reports to Favoriot for remote monitoring.

This system can be enhanced by adding Telegram notifications or advanced analytics on Favoriot.