CAPTCHA solving

1
CAPTCHA solving

• Tianhui Cai
• Period 3

2
CAPTCHAs

• Completely Automated Public Turing tests to tell
  Computers and Humans Apart
• Determines whether a user is a human or a
  computer to prevent spam, etc
• Found on lots of website registration pages
• Audio and visual
• Visual contains noise, distortions
• rotation
• translation
• scaling
• noise
• warp

3
Goal

• Solve a CAPTCHA, pretend to be a human
• Read the image figure out what it says
• This has been done before.
• Show weaknesses of visual CAPTCHAs

4
Procedure?

• Acquire image (from internet)?
• Remove background clutter
• Segmentation (separating letters)?
• Letter identification

5
Implementation

• JAVA / ruby
• Acquire images captchas.net
• formula to get actual text from image
• Remove background clutter median filter, etc
• Segmentation flood fill
• Letter identification neural network

6
First quarter

• Three layer backpropagation neural network
• Neural network good for classification
• Used often for image recognition
• Artificial neurons
• convert input to output
• Backpropagation
• used to let the neural network learn

7
Second quarter

• Image processing Java ImageIO
• Noise removal
• Segmentation

8
Third quarter

• Neural network made save / load
• saved into a text file
• a neural network can be trained multiple times
• Downloaded necessary images (ruby)?
• captchas.net
• filename is what the image says
• Analyzed image outputs from images
• Cropped and centered segmented letters
• uniform letter size
• centered around center of mass
• uniformity is good for training

9
Fourth quarter goals

• Train and test
• pretty much everything else is set up
• Gather data / analyze
• Possible future goal segment letters that stick
  together (flood fill wont work there)?
• Possible obstacles images that are fed into net
  are 30x30, which may be too big