Optical character recognition is the conversion of mechanical, electronic (handwritten or printed) text into machine-encoded text. Whether from a scanned document, a photo document. It is widely used as a form of data entry to use in processes such as cognitive computing, machine translation, key data and text mining. OCR is a field of research in pattern recognition, artificial intelligence and computer vision.
Find more here
A character recognition system is needed for an expenses tracker, where it’ll track supermarket receipts searching for Products. The text extraction must be converted into JSON in order to process the information via code.
-
Machine Learning
- Types of learning
- Reinforcement Learning
- Algorithms
- Linear regression
- Regression
- Logistic regression
- Regression
- Decision tree
- Shannon Entropy
- Kullback-Leibler divergence
- Shannon Entropy
- Random forest
- K Nearest Neighbors (KNN)
- Linear regression
- Types of learning
-
Building an OCR
- Pattern recognition
- Feature analysis
- Classification
- Population statistics
- Pre-processing
- Binarization
- Bitmap
- Character isolation or segmentation
- De-skewing
- Despeckling
- Post-processing
- Text recognition
- Feature extraction