Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 7 years ago.
Improve this question
Do you know of any open source (open core) implementations of an OCR for FPGA either in C or in HDL? Where can I find them?
Thanks
As Philippe says above, you will need to find an algorithm and then port that to your FPGA.
I have never heard of an open source OCR engine for specialized hardware and I have been using OCR since 1997 when there were some European machines (CGK) with OCR in hardware. About that time they moved the OCR back into software.
You might find something here.
http://www.codeproject.com/KB/cs/neural_network_ocr.aspx
http://www.codeproject.com/KB/dotnet/simple_ocr.aspx
You also need to find an algorithm that suits the types of images you want to read. Some questions you need to ask :
Are you reading a fixed size font ?
Are you reading a fixed pitch or proportional font ?
Are you processing B/W or color images ?
What resolution or DPI images are you working with ?
Do you need to remove background noise or color or perform thresholding ?
Do the images need deskewing ?
How many characters do you need ? 0-9 only or the whole alphabet ?
How fast does it need to be ?
How accurate does it need to be ?
Is the text in the same place or randomly located ? If random, how do you find the text zones ?
If your needs are fairly simple then you may get away with some if the idea in the CodeProject link. Writing a good commercial OCR engine has taken many companies years of work and they are still fine tuning to improve accuracy vs speed.
Related
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 8 months ago.
Improve this question
Many chat channels (e.g. Omegle, mIRC) produce the the following conversations when engaging a person one doesn't know.
M
asl?
F 25
wonna sexchat?
This behavior is extremely prevalent. Detection of nudity in videos or images is an open research problem. What I am listing here should be simpler to accomplish. Any off-the-shelf solutions? Any language and any open and free library is fine(including papers on how to do it)!
There is a library on Python that name is profanity. Link: profanity-check
With machine learning algorithm I'm super sure that we can handle it easily. For that you should collect whole words as that. After collecting, you can add a label line, like 0 if acceptable, 1 if not. Then, with some successful machine learning algorithms, you can associate the data with the euclidian, manhattan type distance criteria and create a decision mechanism about whether the content is bad or not. It is difficult to predict how much the success rate will be, but I think that with such an approach, a success rate close to 90% can be achieved. I would like to share with you an academician whose work I trust on this subject. Yılmaz Kaya
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 7 years ago.
Improve this question
I have been trying to find a tool (hopefully for MAC OS X but I don't mind migrating) -- that works -- for those dimensions but I had no luck. Maultech mention some, and so does this page but I was unable to make them work. Metre and ccount (listed on that page) seems to cover most of what I wanted. The tools also seem not up to date no anymore with makes me unsure if the outputs can still be trusted.
Is there any current C tool that can do this that is free or open source? Most of what I found is for Java or OO.
By simple metrics I mean for example calculating amount of, characters, blanks, functions, methods, amount of statements, depth of nests, etc.
By Size I mean line of code, and comments.
By Complexity I mean mccabe and halstead metric at the very least.
By Couple and Cohesion I mean interaction between function calls etc (this is a known SE principle).
I usually use Frama-c.
You may want to take a look at its metrics plugin (McCabe's cyclomatic complexity, Halstead complexity, Value analysis coverage estimate, etc)
What is Frama-C ?
Frama-C is an extensible and collaborative platform dedicated to source-code analysis of C software.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 5 years ago.
Improve this question
I'm looking for a graphic API for embedded systems. With "graphic", I mean an API which is able to draw lines, fill areas, blit bitmaps, etc. I need something that is written in pure C (no C++).
With "embedded systems", I'm thinking of small systems where Linux is too big to run. So I would appreciate a library which is not too concerned with file systems, and OS-level access, but just exposes the graphic primitives with a C interface, and draws in memory buffers.
Any suggestion?
Swell Software, offers C/PEG.
Here's an excerpt from the C/PEG product page:
C/PEG is a complete graphics solution for embedded developers written entirely in ANSI C. C/PEG not only provides optimized graphics primitives, text and bitmap drawing; it also supports higher level graphic objects to give the developer a full tool set for rapid application development
We've used EasyGui - http://www.easygui.com/ - for the start of a project (it's currently on hold).
From the bit I've done it seems quite good. You design up the UI on a PC then generate the C code which makes it all happen.
One thing I like is that if you structure your app properly the code that runs the UI can be separate to the actual UI - ie it could be reused on a different screen resolution/colours/etc. We've made up a modular system where we can reuse bits in different projects as long as we follow the appropriate conventions for button numbers, etc
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 7 years ago.
Improve this question
I'm looking for a non-(L)GPL library to decode MPEG-4 stream.
I don't mind it being commercial.
The price is as not important as code quality and support.
Any suggestions are welcome.
Your own experience is even better.
You can only try Commercial ones:
Elcard : http://www.elecard.com/en/download/products.html
Ligos : http://ligos.com/index.php/home/products/mediarig_encoder/
MainConcept : http://www.mainconcept.com/products/sdks/video.html
Rohzet (carbon coder) : http://www.rhozet.com/products.html
Flip factory : http://www.telestream.net/flipfactory/overview.htm
All of these are practically well used in broadcast productions and are of good grade.
The order doesn't reflect any preference. Most of them are either usable as SDK or independent application with dongle or otherwise.
However, your fear is rather fundamental, and fleeing DLL might not be possible to be prevented trivially.
I was under the impression that CoreAVC is by far the best performant H.264 codec. http://corecodec.com/products/coreavc
Depends what you mean by non-GPL. There are many that are LGPL (thus non-viral).
Like the most popular one libavcodec which is part of FFmpeg.
By contrast x264, which is GPL-ed, is only needed for encoding, not for decoding.
FFmpeg makes it clear how to compile it in non-viral way.
Are you going to require your own videocard drivers as well, or what happens if I use a video driver that does whatever I want with what your decoder sends me? Are you going to somehow force users to use only your video cables as well, and somehow destroy any video camera in the vicinity, and wipe clean the users' memories of what they see? Such madness! So what if you use a GPL library? You cannot lock down the Universe.
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 6 years ago.
Improve this question
What is the best OCR algorithm used to extract text from an image taken with a mobile camera?
That depends on your application requirements.
Usually OCR engine can only return characters, font, word, line or region information. You need add many other modules and tune them to get the best results.
First, image preprocessing is necessary for camera OCR application. Background, noise removal, binarization, resize ... should be added to clean image as possible as you can.
Secondly, you need locate the text region. The algorithm not only depends on image features but also on your OCR objective. For example, if you need to OCR plate number, you can use the plate number's length, width or height for more accurate location.
After OCR, you can add some post processing to correct some OCR errors. Common OCR engines such as Abyy, ExperVision, Omnipage, GOCR, Tesseract are all trained according to common documents, magazine or office paper. If your documents are special, you can establish your high-level data extraction or analysis logic over OCR layer.
You can try the OCR API at http://www.wisetrend.com/wisetrend_ocr_cloud.shtml - it's a REST API that should be very simple to use from any mobile platform, and it's based on the ABBYY OCR engine which is great for low-quality images such as those from mobile phone cameras. Disclaimer: WiseTrend is my company's customer.