Simple preprocessing demonstration for character recognition systems

The software in request is a simple image preprocessing and thinning software. The Main purpose of the software is to help students in criminal evidence processing to understand the basic steps applied on an image before it's recognized by the computer Input -Scanned images of specific texts in bmp format containing several specific symbols that are of concern (Details about those symbols will be given after the agreement is made) PreProcessing (what the software will do) -Segmentation algorithms need to be applied in order to separate each symbol from the whole input image -Each symbol needs to have its x and y coordinates displayed and saved to a separate file; we are concerned with the minimum and maximum height and width of the symbol and its center -After coordinates are calculated and saved, a noise removal algorithm must be applied on the input image, the algorithm in use must be kFil or other suggested ones upon agreementl (further info on the algorithms can be provided) -Slant and skew correction algorithms must be applied on the image -Size normalization algorithm must be applied on the input image to make 40 x 40 pixels ( the program must be flexible in changing the target normalized size) - thinning algorithm must be applied on the image yielding a bmp file of the skeleton the preferable algorithm is the zhang-suen algorithm. - a method to change color of the final output skeleton Output - A display and a separate file containing the coordinates of each symbol in the scanned image (one txt file per symbol) - A display and an image file (JPG) or bmp containing the skeleton of every symbol in the scanned image, the number of the symbol must be included in the image itself. - a simple text file containing the name of the input image, number of characters extracted through segmentations, and also a custom copyright message. ## Deliverables we are flexible to a certain extent regarding those requirement as long as the final software meets the purpose, let us know if you have different suggestions 1) Complete and fully-functional working program(s) in executable form as well as complete source code of all work done. 2) Deliverables must be in ready-to-run condition: A software? installation package. 3) All deliverables will be considered "work made for hire" under U.S. Copyright law. Buyer will receive exclusive and complete copyrights to all work purchased. (No GPL, GNU, 3rd party components, etc. unless all copyright ramifications are explained AND AGREED TO by the buyer on the site per the coder's Seller Legal Agreement). 4) Coder must be available for contact to submit a brief semi weekly progress report to give insight on progress, not much is asked here. just to know how the work is going 5)All algorithm to be used must be fully named, described and referenced. however, we can also provide you with algorithms to be used for each functionality 6) The software must have a user friendly GUI which needs to be flexible in editing (details of the GUI can be negotiated after agreement but will mainly consist of a browse button to import the image, buttons to pre-process the image (cleaning, slant corrections, etc) and buttons to display the output) 7) Java is highly preferable, C++ is an option but it is not preferable. 8) Every function needs to be commented on and described in detail 9) Every algorithm needs to be commented on and described in detail 10) Source code and an executable must be delivered Think of the software as an elementary OCR program that only does preprocessing but in a detailed way for demonstration ## Platform Windows XP