9

This can be solved fairly straightforwardly with simple template matching. I don't know exactly how you have it set up, so I'll just describe the algorithm generally and use illustrations. Observe that the verse numbers have a distinctive border that can easily be used to detect the start and end of a verse. So create a binarized template for that pattern ...


7

As far as i know there are no native opensource Java OCR SDKs. There are Java APIs which wrap calls for native interfaces, for example, for one of the most popular opensource OCR engines - Tesseract (http://groups.google.com/group/tesseract-ocr/) - there are some Java wrappers like tesjeract (http://code.google.com/p/tesjeract/) or Tess4J (http://tess4j.sf....


5

I don't think you can completely get rid of histogram or threshold-based binarization, since the former is to achieve line segmentation, while the latter is to extract the letters. The Radon horizontal projection is used for line segmentation, and the center line can be used to approximate the baseline of each segment. Yet this is somehow equivalent to the ...


3

Stationarity over time just means that if you come back and look at the traffic sometime later it will look pretty much the same as it did when you first saw it. Sure there will be different cars but even the new cars will look similar to the first ones. The cars might be in different positions but their random arrangement will have the same properties as ...


2

'Frequency' for a sequence of values is the measure of how sharp the values in that sequence change. For example, the sequence $x_1(n)=[\begin{array}[cccccccc]&\cdots &1, &1, &1, &1, &\cdots\end{array}]$ has a frequency 0 but the $x_2(n)=[\begin{array}[cccccccc] &\cdots &1 &1 &7 &1 &\cdots\end{array}]$ is a ...


2

As with all ocr, you need to segment each individual character. Assuming this step is already done (and maybe some post processing to One easy way is to take the number and reduce the resolution. Similar to a lcd character display. You can then do a simple correlation between the reduced resolution number from the image, and a template. Since the numbers ...


1

You can obtain pretty good results by just thresholding the image at a high intensity (since your text appears always to be white) and do a closing operation to close the gaps: # convert to grayscale img = cv2.imread('OCR.jpg') gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # threshhold ret,bin = cv2.threshold(gray,245,255,cv2.THRESH_BINARY) # closing ...


1

Without seeing the coins it's not easy to give a unique solution. A possibility would be: Use the Hough transform to detect circles (the coin). Then do some open/close operations to get blocks of text, maybe apply Hough transform again to detect straight lines and finally, do the OCR. Another possibility is to do template matching. If you have pictures of ...


1

A short answer to your question is "NO". To my best knowledge, there is no such a smart end-to-end OCR system that can handle various OCR tasks. However, there are OCR products could reasonably handle some tasks under controlled environments. You seem to be confused of different OCR related tasks and you erroneously believe these tasks are quite similar ( ...


1

Aha, this is a quite funny story that I've heard about CV. Are you a bio guy? Any way, here are my suggestions. If you are a bio guy and just want to finish this project ( I mean successfully identify each insect in a video frame ), go for barcode, QR etc. They are labels though their contents are not directly readable by eyes. However, you will have a ...


Only top voted, non community-wiki answers of a minimum length are eligible