Optical Character Recognition Using One-Shot Learning, RNN, and TensorFlow
Too Long; Didn't Read
<a href="https://en.wikipedia.org/wiki/Optical_character_recognition" target="_blank">Optical character recognition</a> (OCR) drives the conversion of typed, handwritten, or printed symbols into machine-encoded text. However, the OCR process brings the need to eliminate possible errors, while extracting only valuable data from ever-growing amount of it. This blog post highlights how employing the <a href="https://en.wikipedia.org/wiki/One-shot_learning" target="_blank">one-shot attention</a> mechanism for token extraction in <a href="https://keras.io/" target="_blank">Keras</a> using TensorFlow as a back end can help out.