Perform handwriting and signature pattern matching and decipher the English letters

hello. i am an expert in handwriting identification and image processing. your project will contain many steps, location of hand-written medicine name in image, preprocessing step(remove noise and size normalization), shape matching and output readable text. also with training samples a dictionary for each handwritten medicine name must be made. here, the most important steps are location of hand-written medicine name in image and shape matching. i have experiences in pattern recognition and image processing for 6 years. i will do the best. please, send me enough images for training and experiment. Regards. Thanks.

Hi I am PhD in image processing with several years experience in programming and software. what u need here is image segmentation, keywords selection, word extraction. Please check my profile and also let me know if you need further information. Thanks

A proposal has not yet been provided

I would like to bid in this project because I participated in the quite similar project. It is Human Detection. We use HOG feature algorithm and Adaboost to realize whether human is the the picture of not. Thank you so much.

firstly, my bid is actually less than the actual task you want to achieve but, let me tell you the major portions to deal with and also a better way to do it. 1st- creating a database of medicines is far more easy than building one of handwriting of doctors, so this is the first thing to get done. 2nd- we need to perform edge detection and curve fitting algorithms, the latest one being GENETIC-SNAKE algorithm. this is being used to join broken and illegible characters, in our case they would simply be the 26 alphabets. 3rd- after the characters have been made from the illegible handwriting or broken writing, arrange them to form the word, and match it with the medicine database. this could be possible with incomplete words too. 4th-regarding scanning and reading the handwriting, i think the best way is to manually set spacing, lines because these can vary almost every time. so we can manually see a scan and create a rectangle, suppose, around a text and let the system identify the possible outcome of medicine names. i hope it makes more sense now. if you are interested to discuss more, ping me when you are free. thanks.

A proposal has not yet been provided

Hello Thanks for the invitation. Senior CS undergrad. Currently involved in machine learning and OCR research at IIT Bombay. Currently working on Bilingual OCR with focus on indian-languages and segmentationless approaches. Have done a couple of projects in handwriting recognition earlier using matlab and c++. Look forward to work with you.

The best way to do it using deep learning. There are excellent deep learning method for Object classification especially Convolution neural network. I think i can complete it

I am an electronics engineer and worked on image processing and computer vision for more than 3 years. I have also worked on handwritten recognition also.

I am pursuing a PhD in computational Neuroscience and working on 3D biomedical imaging data from last 6 years. Here, I have gained expertise in image processing, data classification, feature extraction, pattern matching and statistical verification of the obtained results. Also, I have been working with MATLAB and C/C++ languages in multi-processing environment for more than 10 years which gave me required experience in programming. During my PhD research project, I have published a few research papers in reputed international journals, the same are listed in my profile.