This is a neural network based marathi character recognition system. Run directly OCR_ANN.m file. and then a GUI will open. Add the template file first for training. Once the excel file is taught, the GUI can recognise the text from scanned images. The neyrak network used is having 2 hidden layers. And 1000 & 500 neurons in each layer respectively.

character_marathi\bpneural.p
.................\char.mat
.................\charpass.p
.................\clip.p
.................\create_templates.p
.................\debug.mat
.................\del_pixel.p
.................\discourser.p
.................\edu_imgresize.p
.................\EraseExcelSheets.p
.................\feature_extractor.p
.................\feature_extractor_2d.p
.................\file_sequencer.p
.................\finddirection.p
.................\findneighbours.p
.................\Imag_seg_ex.p
.................\inouts.mat
.................\ismymember.p
.................\isnotempty.p
.................\isnotintersection.p
.................\isnotmember.p
.................\letters_skel.mat
.................\lineclassifier.p
.................\lines.p
.................\linesegmenter.p
.................\Login.fig
.................\Login.m
.................\Login.p
.................\marathi.jpg
.................\net.mat
.................\OCR.p
.................\OCR_ANN.asv
.................\OCR_ANN.fig
.................\OCR_ANN.m
.................\OCR_ANN.p
.................\prepared.mat
.................\prepinputs.p
.................\prep_image.p
.................\read_letter.p
.................\recognize.p
.................\starter_intersection.p
.................\template.bmp
.................\templates.mat
.................\test.p
.................\test1.p
.................\test2.p
.................\TestIm.mat
.................\testneural.p
.................\tp.p
.................\tp1.p
.................\tp2.p
.................\tushar_sample_database.jpg
.................\xlstest.p
.................\temp
character_marathi

• We are an exchange download platform that only provides communication channels. The downloaded content comes from the internet. Except for download issues, please Google on your own.
• The downloaded content is provided for members to upload. If it unintentionally infringes on your copyright, please contact us.
• Please use Winrar for decompression tools
• If download fail, Try it againg or Feedback to us.
• If downloaded content did not match the introduction, Feedback to us，Confirm and will be refund.
• Before downloading, you can inquire through the uploaded person information

Nothing．