As an exercise, I'm attempting to break the following CAPTCHA:
It doesn't seem like it would be too difficult to break as the edges seems to fairly solid and noise should be relatively easy to remove. Problem is, I have very little experience with image manipulation. Currently I'm using Python with the Pillow library to manipulate the CAPTCHA image, after which it will be passed into Tesseract for OCR.
In the following code I attempt to bring out the edges by sharpening the image and the convert the image to black and white
from PIL import Image, ImageFilter
try:
img = Image.open("Captcha.jpg")
except:
print("Can't load captcha.")
exit()
# Bring out the edges by sharpening.
out = img.filter(ImageFilter.SHARPEN)
out = out.convert("L")
out = out.point(lambda x: 0 if x<136 else 255, "1")
width, height = out.size
out = out.resize((width*5, height*5), Image.NEAREST)
out.save("captcha_modified.png")
At this point I see the following:
However, Tesseract is still unable to read the characters. As an experiment, I used good ol' mspaint to manually modify the image to a point to where it could be read by Tesseract:
So if can get the image to that point, I think Tesseract will do a fairly good job at detecting characters. So my current thoughts are that I need to enhance the edges and reduce the noise the image. Also, I imagine it would be easier for Tesseract to detect the letters if the letters will filled in rather than outlined, but I have not idea how I'd do this.
Any suggestions on how to go about this? Is there a better way to process the images?
I am short on time so this answer may not be incredibly useful but goes over my own 2 algorithms exactly. There isn't much code but a few method reccomendations. It is a good idea to use code rather than MS Paint.With code its actually really easy to break a captcha and achieve above 50% success rate. Behavioral recognition may be a better security mechanism or may be an additional one.
A. Edge Detection Method you use:
Edge detection really isn't necessary. In this case, just use the getpixel((x,y)) function and fill in the area between the bounding lines, recognizing to fill at lines 1,3,5;etc. and turn off the fill after intersection 2,4,6;etc. Luckilly, you chose an easy Captcha so edge detection is a decent solution without decluttering,rotating, and re-alignment.
B. Manipulation Method:
Another method I use utilizes OpenCV and pillow as well. I am really busy but am posting a blog article on this later at druid5.wordpress.com/ which will contain code examples of this method. Since it isn't illegal to get through them, at least I am told, I use the method I will post to collect data all the time. Mostly, contrast and detail from pillow, some basic clutter removal with stats, re-alignment with a basic dfs, and rotation (performable with opencv or easily with a kernal). Tesseract is a good choice for open source but it isn't too hard to create an OCR with opencv either.
This exercies is a decent introduction to OpenCV, PIL (pillow), image manipulation with math, and some other things that help with everything from robotics to AI.
Using flow control to find the failed conditions and try different routes may be necessary but the aim should always be a generic solution.
Related
Forgive me but I'm new in OpenCV.
I would like to delete the common background in 3 images, where there is a landscape and a man.
I tried some subtraction codes but I can't solve the problem.
I would like output each image only with the man and without landscape
Are there in OpenCV Algorithms what do this do? (then without any manual operation so no markers or other)
I tried this python code CV - Extract differences between two images
but not works because in my case i don't have an image with only background (without man).
I thinks that good solution should to Compare all the images and save those "points" that are the same at least in an image.
In this way I can extrapolate a background (which we call "Result.jpg") and finally analyze each image and cut those portions that are also present in "Result.jpg".
You say it's a good idea? Do you have other simplest ideas?
Without semantic segmentation, you can't do that.
Because all you can compute is where two images differ, and this does not give you the silhouette of the person, but an overlapping of two silhouettes. You'll never know the exact outline.
My goal is to blur the picture a bit using a bilinear debayer.
This is to embody the dirty image of the VHS days.
As a graphic major, I tried to reproduce it with various graphic tools, but did not get the desired quality result.
I want that subtle feeling of faded haze when scanned with a scanner.
I decided to emulate a camera sensor.
The process I envisioned is this:
I convert the tiff,targa.png.jpg format image I made into a bayer format image. I want to restore the original image by debayering it again with a bilinear algorithm.
The reason for the bilinear method is that it degrades most gently and strongly.
The link below is the image change according to the algorithm.
https://www.dpreview.com/forums/post/63514167
I'm not a programmer at all, but I've tried something on my own to get what I want.
https://codegolf.stackexchange.com/questions/86410/reverse-bayer-filter-of-an-image
I succeeded in making an image of the Bayer pattern using the coding here.
And I tried debayering by running the debayer source code downloaded from other places, but it failed because the extension was not supported.
So you can change demoasic(debayer) in various ways
I got a program called darkable and raw therapy and tried to convert it, but these programs could only recognize raw files.
Even the algorithms provided by both programs were so good that it was hard to get the impression that the image was degraded.
How do I make what I want?
What can I look for? I really want to make this.
Please let me know which way I should go.
I am having to solve the problem where I have to detect the tire dot code in a given tire image and recognize the characters in the tire.
Sample :-
https://www.tirerack.com/images/tires/tiretech/determining_age/Post_2000_Full_Dot.jpg
I am using OPENCV to perform this task and referred the following link for reference https://github.com/schollz/python-ocr.
I have also used a Canny Edge and SWT detection to perform the task, but it has also not helped. I used the libpillowfight library for the same.
This approach is able to contrast the image but not able to extract the characters efficiently.
Can anyone suggest a better way to achieve this. Help appreciated.
fig:Shoe in the red circle is to be detected
I am trying to create a python script using cv2 that can recognize the shoe of the baller and determine whether the shoe is beyond, on or before the white line(refer to the image).
I have no idea about any kind of approach to use, what kind of algorithms might be helpful. Need some guideline, please help!
(Image is attached)
I realize this would work better as a comment because it isn't a full answer, but I don't have enough rep yet to leave comments, haha.
You may be interested in OpenCV's Canny Edge detection algorithm:
http://docs.opencv.org/trunk/da/d22/tutorial_py_canny.html
This will allow you to find shapes within your image.
Also, you can find similarly colored blobs using SimpleBlobDetector:
https://www.learnopencv.com/blob-detection-using-opencv-python-c/
This should make it fairly easy to detect the white line.
In order to detect a more complex object like the shoe, you'll probably have to make something like a object detection cascade file and use a CascadeClassifier to find it:
http://docs.opencv.org/2.4/doc/tutorials/objdetect/cascade_classifier/cascade_classifier.html#cascade-classifier
http://johnallen.github.io/opencv-object-detection-tutorial/
Basically, you take a bunch of pictures to "teach" what the object looks like, and output that info to a file that a CascadeClassifier can use to detect objects in input images. It may be hard to distinguish between different brands of shoe though, if you need it to be that specific. Also, you may need to adjust the input images (saturation, brightness, etc) before trying to detect objects in order to get good results.
I've been trying to identify ellipses in these pictures for a long time now for a project I'm working on. At the moment I'm trying a new method with a bit of success. I blur the image then subtract the original from it. After that I threshold that image which is how I get this: http://imgur.com/gIkv30A
I've been trying a few methods but have had pretty much no success with any of them. I can't get any more of the noise removed without compromising the quality of the ellipses I have found, but the ellipses I want to find seem to be decently defined.
If anyone has an idea on where I can go now I'd love to hear it.
Thanks,
Andy
edit:
Original Image: http://imgur.com/3ttIFiz
The main method I've tried so far using an adaptive threshold on the image then fitting an ellipse around each of the contours I find after that. It works quite well in one set of images, but performs very poorly in this set. I can see my current method working well in both I get it right.
How well it works with old images: http://imgur.com/eUYiYNa
How well it works with the new (more relevant to the program) images: http://imgur.com/1UXxXAp