Text Extraction and Recognition from Picture Document using Edge Information and Connected Components Algorithms

Picture Text is the text data implanted or written in a picture of various structure. Picture text can be found in caught pictures, examined records, magazines, papers, banners and so on These picture messages are exceptionally accessible these days and they are vital in addressing, portraying and moving data which help people groups in correspondence, taking care of issues, accessibility, making of new sorts of occupations, cost viability, efficiency, globalization and social hole and so forth The data from these picture records would give higher productivity and straightforward entry in case it is changed over to message structure. The cycle by which Image Text is changed over into plain text will be Text Extraction. Text Extraction is helpful in data recovering, looking, altering, recording, filing or announcing of picture text. Nonetheless, variety of these texts because of contrasts in size, direction style, and arrangement, text is implanted in complex hued archive pictures, debased reports picture, inferior quality picture, as well as low picture difference and complex foundation make issue text extraction incredibly troublesome and testing one. Various strategies, for example, Connected Component Method, Mathematical Morphology Method, Edged Based Method and Texture Based Method have been utilized already, yet those all have their own restrictions when estimated by various boundaries like accuracy, review. In this paper, text extraction from picture records, utilizing blend of the two amazing techniques Connected Component and Edge Based Method, to improve execution and exactness of text extraction is talked about and execution is finished by incorporated MATLAB code with MATLAB/Simulink instrument and the proposed framework is tried by Digital Image Binarization Competition (DIBCO) 2017 dataset. At last, the separated and perceived words are changed over to discourse for appropriate use for outwardly disabled individuals. Citation: Dr. Marikkannan M, Janani S. "Text Extraction and Recognition from Picture Document using Edge Information and Connected Components Algorithms." Global Research and Development Journal For Engineering 6.10 (2021): 26 - 33.