Kannada OCR (Optical Character Recognition) with ML (Machine Learning) classification algorithm involves training a machine learning model to recognize and classify Kannada characters from scanned or digital images.
OCR technology has become increasingly important in recent years due to the growth of digitization and the need to process large volumes of documents quickly and accurately. OCR technology is used in a variety of applications, including data entry, document archiving, and information retrieval.
Kannada OCR with ML classification algorithm is especially important for preserving and digitizing Kannada literature and documents. Kannada is a Dravidian language spoken predominantly in the Indian state of Karnataka. Kannada literature is rich and diverse, with a history that spans over a thousand years. However, much of this literature remains in print form and is not easily accessible to the wider public. OCR technology can help to digitize these documents, making them more easily accessible to scholars and researchers.
ML classification algorithms are used to classify Kannada characters based on their visual features. These algorithms learn from a set of training data, and then use this knowledge to classify new data. Some popular ML classification algorithms for OCR include Support Vector Machines (SVM), Random Forests, and Convolutional Neural Networks (CNN).
Clone the project
git clone https://github.com/AkashHiremath856/Kannada-Character-Recoginition.gitGo to the project directory
cd Kannada-Character-Recoginition unzip test_img.zipInstall dependencies
pip3 install -r requirements.txtStart the server
streamlit run app.pyIf you have any feedback, please reach out to us at akash.hiremath25@gmail.com