This project is part of the coursework for the Master of Urban Spatial Analytics program at the University of Pennsylvania, focusing on Remote Sensing. The goal of this project is to develop and evaluate classification algorithms capable of distinguishing images of shoes from images of other types of clothing. Specifically, we employ Random Forest and Support Vector Machine (SVM) classification algorithms using a comprehensive tech stack including NumPy, Pandas, Matplotlib, Scikit-learn, and TensorFlow. The project is based on the MNIST Fashion dataset available on Kaggle.
- NumPy: For efficient array operations and numerical processing.
- Pandas: For data manipulation and analysis.
- Matplotlib: For plotting graphs and visualizing the data.
- Scikit-learn: For implementing machine learning algorithms such as Random Forest and SVM.
- TensorFlow: For building and training advanced machine learning models.
The project utilizes the MNIST Fashion dataset from Kaggle. This dataset includes images of 10 different types of clothing, including shoes, which our models aim to recognize and classify accurately. More information about the dataset can be found on the Kaggle dataset page.