Automatic Handwritten words on Touchscreen to Text file converter

Debnath, Bidya; Anika, Adrita; Abrar, Mohammed Abid; Chowdhury, Tanney; Chakraborty, Rajat Subhra; Khan, Asir Intisar; Fattah, Shaikh Anowarul; Shahnaz, Celia

doi:10.1109/tencon.2018.8650269

Cited by 1 publication

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The network consists of layers that are not needed for classifying mathematical equations and uses computing power. Debnath et al [11] have design their own network with 7 layers that could achieve 87.72% recognition accuracy without sacrificing computing power.…”

Section: Introductionmentioning

confidence: 99%

The Application of Image Processing for Conversion of Handwritten Mathematical Expression

Iskandar¹,

Chew²,

Phang³

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Optical character recognition (OCR) is the conversion of printed or written text from a scanned document or image file into a machine-readable form to be used for data processing like editing. Handwriting has been a way of communication for centuries, but modern technology has made it easier with the introduction of modern computers. While people have adapted to typing out words using a keyboard, formulas and mathematical expressions requires additional add-ons installed in the word processor. The process can be time consuming and tedious. Therefore, an alternative method is proposed in this paper in which handwritten mathematical formulas are converted into computer readable text. Horizontal and vertical projection is used for segmentation while convolutional neural network for character recognition is used to increase the recognition accuracy. The proposed method was able to segment out handwritten mathematical equations from lined papers as well as extract out and identify each character written. The handwritten equation was then successfully converted to a digital format.

show abstract

Section: Introductionmentioning

confidence: 99%