International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 175 - Issue 34 |
Published: Dec 2020 |
Authors: Shailendra Singh Kathait, Chirag Sehra |
![]() |
Shailendra Singh Kathait, Chirag Sehra . Detecting Handwritten Text from Forms using Deep Learning. International Journal of Computer Applications. 175, 34 (Dec 2020), 7-14. DOI=10.5120/ijca2020919760
@article{ 10.5120/ijca2020919760, author = { Shailendra Singh Kathait,Chirag Sehra }, title = { Detecting Handwritten Text from Forms using Deep Learning }, journal = { International Journal of Computer Applications }, year = { 2020 }, volume = { 175 }, number = { 34 }, pages = { 7-14 }, doi = { 10.5120/ijca2020919760 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2020 %A Shailendra Singh Kathait %A Chirag Sehra %T Detecting Handwritten Text from Forms using Deep Learning%T %J International Journal of Computer Applications %V 175 %N 34 %P 7-14 %R 10.5120/ijca2020919760 %I Foundation of Computer Science (FCS), NY, USA
Digital Image Processing is an expeditiously emerging field possessing a large number of applications in science and engineering aspects. One of the most used applications in almost every sector is Optical Character Recognition (OCR). OCR is the electronic conversion of handwritten text into digital format which makes information processing from printed papers to data records easy, thus helping to electronically edit, search and store printed texts into machines. This text can then be used in variety of applications like machine translation, speech-to-text, pattern recognition etc. OCR as a piece of software applies pre-processing to improve the recognition in images. This pre-processing step includes skewness correction, despeckling, layout analysis and line and word detection. OCR saves tons of manual effort by recognizing handwritten text with word level detection resulting in an accuracy of 81% to 90%. With form processing, one can capture information in digital format that can save time, labor and money. This helps in achieving a better accuracy in detection. Such systems range from minor application forms to large scale survey forms. Deep Learning algorithms dealing with computer vision related tasks can be used to build a recognition engine.