I have to recognize set of digits on something like scoreboard, calculator and similiar devices display.
I tried that image in most popular ocr's, but with no success.
How can i preprocess this image to get it work with ocr frameworks? How to get that digits from there?
First,Based on edge detection, determine the position of the digits. Then, convert the image to a two-value image (white foreground and black background). Last, put it to OCR...
Related
So me and my friends play a game and they recently changed there images from white background and black letters to black background and colorful letters. and the old ocr that we was created years ago by someone is pretty useless now as the accuracy is very low if not 0% (it just took the old ocr ~250 attempts). So my question would i be able to to extract the text from the following picture
I have never used IronOCR and i tried using the default code to get text from image but the results were weird.
Thanks in advance!
You can try to segment the image first by color (a histogram analysis will tell you colors on the image). Then you can convert the images to b/w and run OCR. You'll get better accuracy.
We are currently doing out thesis work about OCR or optical character recognition. Just want to ask something about diving a single image into multiple images or templates.
What we are trying to achieve is that we want to segment or divide each characters (total of 16) from a single image into multiple (16) image, for further recognition. Below is the image of the proposed segmented characters.
Character Segmentation
The solution we thought was to find contours or outlines of each characters. From these contours, we would draw a square boundary around the characters to distinguish them from the background. This square boundaries will then be the basis of division into multiple images.
The question is how can we do that in terms of coding? Is that solution possible?
I have a question regarding achieving better recognition results with tesseract. I am using tesseract to recognize serial numbers. The serial numbes consist of only one font-type, characters A-Z, 0-9 and occur in different sizes and lengths.
At the moment I am able to recognize about 40% of the serial number images correct. Images are taken via mobile phone camera. Therefore the image quality isn't the best.
Special problem characters are 8/B, 5/6. Since I am recognizing only serial numbers, I am not using any dictionary improvements and every character is recognized independently.
My question is: Does someone has already experience in achieving better recognition results with training tesseract? How many images would be needed to be able to get good results.
For training tesseract should I use printed and afterwards photographed serial numbers, or should I use original digital serial numbers, without printing and photographing?
Maybe somebody has already experience in that kind of area.
Regarding training tesseract: I have already trained tesseract with some images. Therefore I have printed all characters in different sizes, photographed and labeled them correctly. Example training photo of the character 5
Is this a good/bad training example? Since I only want to recognize single characters without any dependency, I though I don't have to use words for training.
Actual I only have trained with 3 of these images for the characters B 8 6 5 which doesn't result in a better recognition in comparison with the original english (eng) tesseract database.
best regards,
Christoph
I am currently working on a Sikuli application using Tesseract to read text (Strings and numbers) from screenshots. I found that the best way to achieve accuracy was to process the screenshot before performing the OCR on it. However, most of the text I am reading is green text-on black background, making this my preferred solution. I used Scalr's method within BufferedImage to increase the size of the image:
BufferedImage bufImg = Scalr.resize(...)
which instantly yielded more accurate results with black text on gray background. I then used BufferedImage's options BufferedImage.TYPE_BYTE_GRAY and BufferedImage.TYPE_BYTE_BINARY when creating a new BufferedImage to process the Image to grayscale and black/white, respectively.
Following these steps brought Tesseract's accuracy from a 30% to around an 85% when dealing with green text on black background, and a really-close-to-100% accuracy when dealing with normal black text on white background. (sometimes letters within a word are mistaken by numbers i.e. hel10)
I hope this helps!
I am exporting my web images from PSD by 'Save For Web' option along with using its Quality and Format controls as per the standards but when I check my image size they are heavy than the expectation. I see the image sizes on other web. Their GIF images are too small. i.e a bullet arrow GIF image (12px X 48px) is near around 90 bytes but when I create the same image in PSD and export as GIF my size goes upto 1 KB. I just wanted to know that is their any other way to export or create images for web to gain lower size?
You can check how many colors are you using.
If you create a GIF with less colors you get a smaller GIF.
The size also depends on how many colors are in the image, maybe the 90 bytes gif is pure black and white and yours have more colors.
When you Save For Web in Photoshop, there are a few variables you can play to gain lower size, that you already use. I tried to explain some for other users who find this question,in case you already know how them works:
Lossy: Lossy compression lets you compress more bytes out. Higher value produces low image quality and less weight.
Colors: More number of colors used in the image causes higher size image, as aleixventa says in his answer.
Web Snap: That's the option to convert the color of the image to web safe colors. More web safe colors results in a smaller image.
Combobox "No Dither": Dithering mixes pixels of the gradients to simulate the missing colors. You could retrieve more specific info about this feature here. BTW, less percentaje of difussion dittering results in higher image.
With all these variables in mind, you can see the total weight while playing with them:
This may not be a programming related but possibly programmers would be in the best position to answer it.
For camera calibration I have a 8 x 8 square pattern printed on sheet of paper. I have to manually enter these co-ordinates into a text file. The software would then pick it up from there and compute the calibration parameters.
Is there a script or some software that I can run on these images and get the pixel co-ordinates of the 4 corners of each of the 64 squares?
You can do this with a traditional chessboard pattern (i.e. black and white squares with no gaps) using cvFindChessboardCorners(). You can read more about the function in the OpenCV API Reference and see some sample code in O'Reilly's OpenCV Book or elsewhere online. As an added bonus, OpenCV has built-in functions that calculate the intrinsic parameters of the camera and an array of extrinsic parameters for the multiple views of a planar calibration object.
I would:
apply threshold and get binarized image.
apply SobelX filter to image. You get an image with the vertical lines. This belong to the sides of the squares that are almost vertical. Keep this as image1.
apply SobelY filter to image. You get an image with the horizontal lines. This belong to the sides of the squares that are almost horizontal. Keep this as image2.
make (image1 xor image2). You get a black image with white pixels indicating the corner positions.
Hope it helps.
I'm sure there are many computer vision libraries with varying capabilities and licenses out there, but one that I can remember off the top of my head is ARToolKit, which should be able to recognize this pattern. And if that's not possible, it comes with a set of very good patterns that are tailored so that they can be recognized even if they're partially obscured.
I don't know ARToolKit (although i've heard a lot about it) but with OpenCV this processing is trivial.