Wabi-Sabi

The Project Wabi-Sabi aims to help special children by employing our very own Machine Learning Model and Interactive Quiz specially designed by our developers.

Goals

To Successfully invent a software that recognizes emotions and compares it with a reference feature to predict if emotion accurate or not

Software used:

• Python
• Tensorflow or PyTorch
• Keras
• OpenCV
• PyGame
• NLTK(Natural Language Toolkit)
• Flask or Django

Solution Approach:

• build a emotional thermometer using Childs own emotions.
• building a mode to use camera to point at ppl and tell the emotions showed
• Use a chatbot to help roleplay emotional behaviour.
• daily reminder system for practice.
• create a fun interactive ways to test learning.
• compare emotions of the child and shown feature in realtime and reward points
• points can be used to redeem in app purchases
• teach body language.

Technical Approach:

Sure! Here's a more detailed description of how to make a Python program to help autistic children understand emotions using AI:

1. Setting up the Environment:
   • Install Python: Download and install Python from the official website (https://www.python.org/) based on your operating system.
   • Install Required Libraries: Use the package manager pip to install the necessary libraries such as TensorFlow, Keras, OpenCV, NLTK, and Pygame. You can install them by running commands like pip install tensorflow, pip install opencv-python, pip install nltk, etc.
2. Preparing the Emotion Recognition Model:
   • Choose a suitable deep learning model architecture for emotion recognition, such as a CNN or RNN. You can explore existing pre-trained models or train your own using appropriate datasets.
   • Load the trained model in your Python program using TensorFlow or Keras.
3. Building the User Interface:
   • Decide on the type of user interface you want to create, such as a command-line interface, GUI, or web interface.
   • Use appropriate libraries like Pygame or web frameworks like Flask or Django to create the desired user interface. For example, if you're using Pygame, you can create a game window, buttons, and other interactive elements.
4. Capturing and Analyzing Facial Expressions:
   • Prompt the user to input a picture or video containing facial expressions.
   • Use OpenCV to detect faces in the input media. You can utilize the pre-trained Haar cascades or more advanced deep learning-based face detection models.
   • For each detected face:
     • Extract facial landmarks and features using OpenCV. This step helps in capturing important information for emotion analysis.
     • Preprocess the facial data by resizing, normalizing, or applying any other required transformations to make it suitable for inputting into the emotion recognition model.
     • Pass the preprocessed data through the trained emotion recognition model to obtain the predicted emotion.
     • Display the predicted emotion alongside the face image on the user interface.
5. Incorporating Text and Audio Analysis (Optional):
   • If you want to enhance emotion understanding by analyzing accompanying text or audio data, use libraries like NLTK for sentiment analysis or speech processing.
   • Process the text or audio data to extract relevant emotional cues and provide additional insights alongside the predicted emotion.
6. Providing Supplementary Information:
   • Display additional information or resources related to the predicted emotion. For example, you can show a short description of the emotion, play an audio clip explaining the emotion, or provide relevant educational materials.
7. Repeat or Exit:
   • Ask the user if they want to input another picture or video. If yes, go back to step 5; otherwise, proceed to step 9.
8. Program Termination:
   • End the program gracefully, closing any open windows or resources.