Statistical Approach for Text and Non-text Classifier in Off-line Handwritten Document

Hand writing and hand drawing are natural ways to take note. A pen and papers are used to make a note for a long time. In digital era, the notes are often converted into a durable and formal format for further use. Therefore, the conversion application was developed in many fields with many skill such as handwritten recognition, object recognition, object classification, and others. In this paper, we demonstrate a method to classify connected components as flowchart and text. We use the Online Handwritten Flowchart Dataset (OHFD) which contained 419 handwritten flowcharts to benchmark our methodology. The result shown our classification technique get F1-score 77.6%.