Archive for: December 2017

Handwriting Rec. – Connectionist Temporal Classification

Connectionist Temporal Classification After reading the paper from  Farès Menasri et al. “The A2iA French handwriting recognition system at the Rimes-ICDAR2011 competition”, we looked for inquiries about Connectionist Temporal Classification (CTC) as it is a really interesting method to label unsegmented sequences directly. In their article  Alex Graves, Santiago Fernández, Faustino...

Handwriting Rec. – Page segmentation

Page segmentation With tilt and orientation corrections done, we can segment the page to extract lines, then words. To carry out the separation of the letters, we will have to detect the inclination of the handwriting. The document may present deformations, however we will postpone this correction to later,...

Handwriting Rec. – CNN make predictions

Make predictions with a neural network. After building and evaluating neural network models let’s see how they behave to make predictions. We will evaluate model-by-model predictions and then use several training results and models with the bagging and voting method. Bagging and voting are popular methods for combining the...

Navigation

Social Media