• V. P. JAY FANTIN
• M.VINOTHINI
• D.YUVENTHA
• M.SHOFIA NASHRIN
• R.S.SUBHIKSHA

Image based content extraction is one of the quickest developing examination territories in the field of sight and sound innovation. The extraction of content from intricate or increasingly vivid pictures was a difficult issue. Content information present in the pictures contains valuable data for routine clarification, ordering and organizing of pictures. Extraction of this data includes identification, confinement, extraction, improvement and acknowledgment of the content from the given picture. We have recommended that we convert the content from picture utilizing profound neural network. In this paper, an optical character acknowledgement framework dependent on Deep Neural Network (DNN) is used. The ANN is prepared utilizing the Back Propagation calculation. In the proposed framework, each composed English letter is represented by binary numbers that are utilized as contribution to a basic element extraction framework whose yields not resisting the information, are fed to a DNN. A while later, the feed forward algorithm gives knowledge about the activities of a neural network followed by the DNN algorithm which Bargains, Trains, Calculates error and modifies weights.

Optical Character Recognition, Binarization, Thinning, Skewing.

"HANDWRITTEN CHARACTER RECOGNITION USING NEURAL NETWORK AND FUZZY LOGIC", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 6, page no.1141-1146, June-2020, Available :http://www.jetir.org/papers/JETIR2006162.pdf

"HANDWRITTEN CHARACTER RECOGNITION USING NEURAL NETWORK AND FUZZY LOGIC", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 6, page no. pp1141-1146, June-2020, Available at : http://www.jetir.org/papers/JETIR2006162.pdf