[enhancement] Face-Mask-Detection folder

**Is your feature request related to a problem? Please describe.**
The current face mask detection model, while functional, lacks sufficient sample data for diverse and comprehensive evaluation. This may lead to less accurate predictions in real-world scenarios. Additionally, there is a need for visual representation of the model's performance metrics and prediction results for better interpretability.

**Describe the solution you'd like**
I would like to improve the face mask detection project by:

1. Adding more sample images to the dataset to improve the robustness and accuracy of the model.
2. Implementing visualizations such as accuracy/loss graphs to provide clear insights into the model's performance.
3. Integrating a feature to dynamically predict and display results on new images with corresponding graphs.

**Describe alternatives you've considered**
1. Experiment with different CNN architectures or hybrid models to compare performance and select the best one.
2. Use a pre-trained model on a large dataset and fine-tune it on the face mask detection dataset to potentially achieve better performance.

**Approach to be followed (optional)**
1. Data Collection and Preprocessing:
- Gather additional face mask and non-mask images from various sources.
- Preprocess the images (resize, normalize, etc.) to ensure consistency with the current dataset.

2. Model Training:
- Train the CNN model on the expanded dataset.

3. Performance Evaluation:
- Plot accuracy and loss graphs over epochs to monitor the training process.

4. Dynamic Prediction Interface:
- Create an interface to upload and predict new images.
- Display prediction results along with probability scores.
- Show graphs and metrics related to the prediction for better understanding.

**Additional context**
The project aims to detect whether a person in an image is wearing a face mask or not using a CNN model. The enhanced features will not only improve model accuracy but also provide clear, interpretable visual feedback.