• Gautami D. Dokhe
• A.S.Vaidya

With quick heightening of existing multimedia documents and mounting demand for information indexing and retrieval, much endeavor has been done on extracting the text from images and videos. The main objective of the proposition is to spot and get out the scene text from video of different unknown regional languages. These languages are recognized and later translated to English. Extracting the scene text from video is requesting due to complex background, varying font size, different style, lower resolution and blurring, position, viewing angle and so on. Text Region Indicator (TRI) is being developed to compute the text usual confidence and candidate region by performing binarization. Convolutional Neural Networks (CNNs) generally utilized as a part of pattern- and image-recognition problems as they have various favorable circumstances contrasted with different strategies. CNN is a special type of feed-forward multilayer trained in supervised mode. Neural network is used as the classifier and Optical Character Recognition (OCR) is used for character verification. Convolution Neural Network Technique is used for processing. CNN is a class of deep, feed- forward artificial neural networks that has successfully been applied to analyze visual imagery.

CNN, Image processing,OCR, Video-to-frames conversion.

"A Complex Text Detection from Image and Video Frames using Convolutional Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 7, page no.322-327, July-2018, Available :http://www.jetir.org/papers/JETIR1807649.pdf

"A Complex Text Detection from Image and Video Frames using Convolutional Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 7, page no. pp322-327, July-2018, Available at : http://www.jetir.org/papers/JETIR1807649.pdf