Basic Character Recognition Tutorial
The basic character recognition tutorial demonstrates how to extract isolated characters/digits from the images using the scikit-image library which is an image processing in Python and predict the image using the scikit-learn, machine learning in Python, to classify and predict the isolated character/digit images.
- Coding a basic character recognition program using Python programming language.
- Extract isolated characters/digits from the images.
- Create pixel-based method as a feature vector and save into text file.
- Create first model and prediction using Nearest centroid classifier.
- Using another machine learning techniques such as k-nearest neighbor (kNN), decision tree, ensemble method, multi-layer perceptron (MLP), and support vector machine (SVM) to create the model and prediction the isolated character/digit images.
- Tuning parameters using grid search techniques.
- Crop characters/digits
- Create feature vector and simple classification
- Create the kNN classifier model
- Create the decision tree and ensemble classifier models
- Create the MLP classifier model and tuning parameters using the grid search techniques
- Create the SVM classifier model and tuning parameters using the grid search techniques
- Sample MNIST dataset
The Necessary Python Libraries
install the library through pip
pip is a package management system used to install and manage software packages written in Python.
$ sudo pip install scikit-image $ sudo pip install -U scikit-learn $ sudo pip install matplotlib $ sudo pip install numpy $ sudo pip install scipy $ sudo pip install matplotlib