InterviewSolution
Saved Bookmarks
InterviewSolution
| 1. |
Solve : what languge?? |
|
Answer» Hi guys Hi guysWhat you a seeking may be beyond l your skill. Your question implies you do not have a basic training in computer languages and how t hey are used. Making a machine., a computer, read like a human requires a thing called AI. Here is an canticle about that. http://en.wikipedia.org/wiki/Artificial_intelligence Quote Artificial intelligence (AI) is the intelligence exhibited by machines or software, and the branch of computer science that develops machines and software with intelligence. Major AI researchers and textbooks define the field as "the study and design of intelligent agents",[1] where an intelligent agent is a system that perceives its environment and takes actions that maximize its chances of success.[2] John McCarthy, who coined the term in 1955,[3] defines it as "the science and engineering of making intelligent machines".[4]Maybe somebody said that you can do anything with computers. Wello, not really everything. But a lot of advancement has been make. Another thing you want to look at is OCR. Optical character recognition http://en.wikipedia.org/wiki/Optical_character_recognition Quote Optical Character Recognition, usually abbreviated to OCR, is the mechanical or electronic conversion of scanned or photoed images of typewritten or printed text into machine-encoded/computer-readable text. It is widely used as a form of data entry from some sort of original paper data source, whether passport documents, invoices, bank statement, receipts, business card, mail, or any number of printed records. It is a common method of digitizing printed texts so that they can be electronically edited, searched, stored more compactly, displayed on-line, and used in machine processes such as machine translation, text-to-speech, key data extraction and text mining. OCR is a field of research in pattern recognition, artificial intelligence and computer vision.For more, follow the links given above. Are you going to write your own OCR ENGINE? If you are clever enough to do that, you would surely already have a pretty good idea what language would be appropriate. If you are going to use a scripting language to string together various tools e.g. Tesseract, then a lot of people use Python for batch processing of images. You would STILL have the problem of processing a video stream but again there are scriptable solutions. If you are a beginner at programming, then isn't a number plate recognition system a bit ambitious? Good idea! Quote Tesseract is probably the most accurate open source OCR engine available. Combined with the Leptonica Image Processing Library it can read a wide variety of image formats and convert them to text in over 60 languages. It was one of the top 3 engines in the 1995 UNLV Accuracy test. Between 1995 and 2006 it had little work done on it, but since then it has been improved extensively by Google. It is released under the Apache License 2.0.https://code.google.com/p/tesseract-ocr/ As far as I know, Tesseract is mostly for doing OCR on non-skewed, black-on-white printed stuff, like scanned images of printed documents. To recognise a vehicle number/license plate in a video still, you NEED some artificial intelligence to find out which part of the image (if any) is a license plate, and whether that part needs de-skewing and other processing. This is not a trivial task. Usually a team of programmers would work for months on something like that. Right, pastern recognition of skewed image is herd to do. But the police are doing sit. Here is an article from USA today from last year. You can't hide from cops with license-plate scanners Watch your speed! Quote from: Geek-9pm on February 06, 2014, 08:48:41 PM Right, pastern recognition of skewed image is herd to do.Considering speech recognition is a form of pattern recognition I think this provides it's own example.Fonts of his 20. Yes indeed, speech recognition is also a form of pattern recognition. This product I'm using is made by a company called nuance. They also have OCR product for sale. However, I don't believe they have anything as sophisticated as what the police departments are now using in some areas. This version of Dragon NaturallySpeaking is an older version that I bought some time back and it doesn't have all the bells and whistles of the newer VERSIONS. This version is adjusted just for my voice and it has a limited vocabulary. Before I could use it I had to train it and I had a look at all my text files I had created so it could build a vocabulary based on things that I normally write about. However, reading numbers shouldn't be as hard to do if you have only numbers to deal with. But if you include alphanumeric characters, then it becomes much more difficult. For example, the B off looks like the number eight and then this issue about the number one and the letter I and the number zero and the letter O. So yes, speech recognition still has its limitations. And obviously, reading a license plate also would be a serious problem. Quite possibly they might come up with a new font for use on license plates that would make it easier for optical recognition. Okay, I am going to post this without any editing. Have a good laugh. |
|