How to get do change to text perspective for OCR to detect?
Ori image:
After some pre processing, i got the below image.
I have this picture, and try to correct the perspective by using Bounding Box technical, i reference from others post, i tried to use morphnology to connect the text and use minAreaRect to get the area
Then draw the line, but the perspective is incorrect.
How can i get the persective as below?
After this, i will use getPerspectiveTransform and warpPerspective to correct it. Thanks
Related
I am trying to build a document scanner using openCV. I am trying to auto crop an uploaded image. I have few use cases where there is a gap in the border when the document is out of frame(captured image).
Ex image
Below is the canny edge detection of the given image.
The borders are missing here and findContours does not return me proper results due to this.
How can I handle such images.
Both automatic canny edge detection as well as dilate does not work in such cases because it can join only small edges.
Also few documents might have only 2 sides or 3 sides captured using camera and how can we crop the other areas which is not required.
Example Image:
Is there any specific technique for handling such documents?
Please suggest few ideas.
Your problem is unusual. One way to solve this problem which comes to my mind is to:
Add white borders around image.
https://docs.opencv.org/3.4/dc/da3/tutorial_copyMakeBorder.html
Find lines in edges
http://www.robindavid.fr/opencv-tutorial/chapter5-line-edge-and-contours-detection.html
https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_imgproc/py_houghlines/py_houghlines.html
Make Probablistic HoughLines
Crop image by these lines. It will for sure work for image like 1st one.
For image like 2nd one you can use perpendicular and parallel lines.
For sure your algorithm must be pretty complex to works good. The easiest way is to take a picture of whole document if it is possible.
Good luck!
I am making a program that recognizes horizontal/vertically straight lines from an image file and creates a bunch of line data for other purpose.
However I got a problem that when I take pictures from diagonally sideways(or up/downwards), that picture shouldn't have horizontally/vertically straight lines so I cannot use that picture.
So I have to make image pre-processing method to invert perspective warping. To do so, I must find current projection value of the image first.
Unfortunately I couldn't find a way with OpenCV, unless I add precalculating camera matrix progress before taking picture.
I assume that most of lines in input images should be horizontal/vertically straight. Is there any methods to solve my problem in OpenCV?
For example:
This image is Perspectively warped. I wanna make it image like this :
I was watching this talk from pycon http://youtu.be/B1d9dpqBDVA?t=15m34s around the 15:33 mark the speaker talks about extracting lines from an image (receipt) and then feeding that to the OCR engine so that text can be extracted in a better way.
I have a similar need where I'm passing images to the OCR engine. However, I don't quite understand what he means by extracting lines from an image. What are some open source tools that I can use to extract lines from an image?
Take a look at the technique used to detect the skew angle of a text.
Groups are lines are used to isolate text on an image (this is the interesting part).
From this result you can easily detect the upper/lower limits of each line of text. The text itself will be located inside them. I've faced a similar problem before, the code might be useful to you:
All you need to do from here is crop each pair of lines and feed that as an image to Tesseract.
i can tell u a simple technique to feed the images to OCR.. just perform some operations to get the ROI (Region of Interest) of ur image, and localize the area where the image after binarizing it.. then you may find contours, and by keeping the threasholding value, and setting the required contour area, you can feed the resulting image to OCR :) ..
(sorry for bad way of explaination)
Direct answer: you extract lines from an image with Hough Transform.
You can find an analytical guide here.
Text lines can be detected as well. Karlphillip's answer is based on Hough Transform too.
I am looking for an efficient way to detect the small boxes around the numbers (see images)?
I already tried to use hough transformation with no success. Any ideas? I need some hints! I am using opencv...
For inspiration, you can have a look at the
Matlab video sudoku solver demo and explanation
Sudoku Grab, an Iphone App, whose author explains the computer vision part on his blog
Alternatively, if you are always hunting for the same grid you could deploy something like this:
Make a perfect artificial template of the grid and detect or save all coordinates from all corners.
In the target image, do the same thing, for example with Harris points. Be creative, you might also be able to use the distinct triangles that can be found in your images.
Using the coordinates from the template and the found harris points, determine the affine transformation x = Ax' between the template and the target image. That transformation can then be used to map the template grid onto the target image. At the very least this will give you some prior information to help guide further segmentation.
The gist of the idea and examples of the estimation of affine matrix A can be found on the site of Zissermans book Multiple View Geometry in Computer Vision and Peter Kovesi
I'd start by trying to detect the rectangular boundary of the overall sheet, then applying a perspective transform to make it truly rectangular. Crop that portion of the image out. If possible, then try to make the alternating white and grey sub-rectangles have an equal background brightness - maybe try adaptive histogram equalization.
Then the Hough transform might perform better. Alternatively, you could then take an approach that's broadly similar to this demonstration by Robert Bemis on MATLAB Central (it's analysing a DNA microarray image rather than Lotto cards, but it's essentially finding bounding boxes of items arranged in a grid). At a high level, the approach is to calculate the autocorrelation along columns and rows of pixels to detect the periodicity of the items in the grid, and use that to impose a bounding box on each item.
Sorry the above advice is mostly MATLAB-based; I'm afraid I'm not an opencv user, but hopefully it will give you some ideas at least.
I want to make an apps detect an square/rectangle in my webcam using EMGU CV (an OPENCV wrapper). The square/rectangle will have a solid color.
if it's posible I would like to obtain the width and heigth of the square/rectangle
In this video you can see what I would like to do.
http://www.youtube.com/watch?v=ytvO2dijZ7A&NR=1
I'm working with C#
If you already know the color of the desired object then you can segment the image based on that color. (Which may be why the rectangle disapears when the guy movies the direction to and away from the camera [differences in lighting]. Once you have the object segmented out of the image you can do region calculations on the image. [In matlab think regionprops]
Once you have the blob you can attempt to do model fitting to get a good approximation of the object being represented.
In the video link provided what is probably being done is Surf feature detection. Take a look at the SURFFeture example that ships with EMGU. Rather than drawing lines in this case however the four corner points are detected and a shape drawn on top. Similar examples which will help you are ShapeDetection and TrafficSignRecognition both in the EMGU.CV.Examples folder. ShapeDetection will teach you how to classify the square and the StopSignDetector.cs class will show you another example of how to apply a surf feature detection algorithm.
It will require a little reconfiguration but if you get stuck feel free to ask another question.
Cheers
Chris