ML-Applications

---

Pic-to-Art

This project demonstrates the application of machine learning techniques to transform ordinary pictures into artistic images. Using neural style transfer, this project blends the content of one image with the style of another to create stunning visual artworks.

Table of Contents

• Project Overview
• Tools Used
• Key Techniques

Project Overview

The Pic-to-Art project leverages neural style transfer to convert photographs into pieces of art by combining the content of a target image with the style of a reference artwork. The project explores various neural network architectures and techniques to achieve optimal results.

Tools Used

• Python: Primary language for developing and running the project.
• TensorFlow/Keras: For implementing and training neural networks.
• OpenCV: For image processing and manipulation.
• Matplotlib: For visualizing results.

Key Techniques

• Neural Style Transfer: Combines content and style from two images using deep neural networks.
• Convolutional Neural Networks (CNNs): Utilized for extracting content and style features.
• Optimization Techniques: Used to minimize the loss function and achieve the desired artistic effect.

---

OpenCV Text Detection

This project focuses on detecting and recognizing text within images using OpenCV and machine learning techniques. It showcases practical applications of text detection algorithms in real-world scenarios.

Table of Contents

• Project Overview
• Tools Used
• Key Techniques

Project Overview

The OpenCV Text Detection project aims to detect and recognize text in various types of images. This project uses a combination of image processing techniques and machine learning models to accurately identify and extract text from images.

Tools Used

• Python: Primary language for developing and running the project.
• OpenCV: For image processing and text detection.
• Tesseract OCR: For optical character recognition.
• NumPy: For numerical operations and handling image data.
• Matplotlib: For visualizing results.

Key Techniques

• Text Detection: Using OpenCV’s EAST (Efficient and Accurate Scene Text Detector) to detect text regions in images.
• Optical Character Recognition (OCR): Using Tesseract OCR to recognize and extract text from detected regions.
• Image Processing: Techniques such as thresholding, contour detection, and filtering to preprocess images for better text detection.

Files and Directories

• text_detection.py: Main script for running the text detection and recognition.
• images/: Directory for input images and output results.
• requirements.txt: List of dependencies and libraries required to run the project.

---

There are some other projects in this repo too, but the above are the main ones :)