Loading repository data…
imehranasgari / repository
A Jupyter Notebook demonstrating various image binarization techniques using OpenCV, including simple thresholding and Otsu's method. This project showcases fundamental concepts in computer vision and image processing, with a focus on practical implementation and clear explanations. Ideal for preprocessing in tasks like OCR and object detection.
This project explores fundamental image binarization techniques using OpenCV. The primary goal is to convert grayscale images into binary (black and white) images by applying various thresholding methods. This is a crucial preprocessing step in many computer vision tasks, as it simplifies image analysis by separating objects from the background. The notebook also serves as a practical demonstration of my ability to implement and explain these core concepts.
I implemented several thresholding techniques to demonstrate their effects on different types of images. The approaches include:
The project uses a small set of sample images (gradient.jpg, Lusin-1.jpg, and plate.jpg) to illustrate the different thresholding methods. These images were chosen to showcase how each technique performs under varying conditions (e.g., gradients, real-world objects).
git clone https://github.com/imehranasgari/Image-Binarization-OpenCV.git
pip install opencv-python numpy matplotlib
jupyter notebook binarization.ipynb
This project is intended to demonstrate conceptual understanding rather than achieving high performance metrics. The key results are the visual outputs that clearly show the differences between various thresholding methods. The inclusion of both manual and automatic (Otsu's) thresholding highlights my ability to select the appropriate tool for a given problem. The interactive demo further showcases my skills in creating practical, user-friendly applications.
This project reinforced my understanding of image binarization as a critical first step in many computer vision pipelines, such as object detection and optical character recognition (OCR). By implementing both simple and adaptive thresholding methods, I gained a deeper appreciation for the trade-offs between manual control and automated, data-driven approaches like Otsu's method. This exploration serves as a solid foundation for tackling more complex image segmentation challenges.
This project represents my initial steps into the practical application of computer vision. The foundational knowledge and guidance for this work were derived from the outstanding OpenCV course taught by Alireza Akhavanpour on the Maktabkhooneh platform. His ability to deconstruct complex topics into clear, actionable steps was instrumental in the successful implementation of this project.
This project is licensed under the Apache 2.0 License – see the LICENSE file for details.
💡 Some interactive outputs (e.g., plots, widgets) may not display correctly on GitHub. If so, please view this notebook via nbviewer.org for full rendering.
Selected from shared topics, language and repository description—not editorial ratings.
Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.
ageron /
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
fastai /
Free online textbook of Jupyter notebooks for fast.ai Computational Linear Algebra course
nteract /
The old electron based nteract notebook
ipython-contrib /
A collection of various notebook extensions for Jupyter