Captcha Recognition using Neural Networks
2 likes1,729 views
Machine learning methods like neural networks and self-organizing maps can recognize CAPTCHAs with high accuracy using minimal preprocessing of images. Experiments showed neural networks outperformed self-organizing maps on CAPTCHAs with 4 or more letters. Accuracy decreased as the number of letters increased due to worse segmentation. Improving segmentation quality is key to maintaining high true positive rates. Future work involves better segmentation techniques and applying these methods to other problems like handwriting recognition.
Captcha Recognition using Neural Networks
- 1. Machine Learning Methods for CAPTCHA Recognition Rachel Shadoan Zachery Tidwell, II Constantine Priemski Navya Chandana and Shakeeb
- 2. CAPTCHA Completely Automated Public Turing Test to tell Computers and Humans Apart Why are they interesting? o Harder than normal text recognition On par with handwriting recognition, reading damaged text o Techniques translate well to other problems Facial recognition (Gonzaga, 2002) Weed identification (Yang, 2000) o Near infinite data sets Easier to avoid over-fitting
- 3. Hypothesis CAPTCHA recognition can be accomplished to a high degree of accuracy using machine learning methods with minimal preprocessing of inputs.
- 4. Methods Learning Methods o Feed-forward Neural Nets o Self-Organizing Maps o K-Means o Cluster Classification Segmentation Methods o Overlapping o Whitespace o K-Means Tools o JCaptcha o Image Processing
- 5. JCaptcha o Open-source CAPTCHA generation software o Highly configurable Can produce CAPTCHAs of many levels of difficulty o Check it out at: http://jcaptcha.sourceforge.net
- 6. Image Processing Sparse Image Represents Images as unbounded set of pixels Each pixel is a value between 0 and 1 and a coordinate pair Center each image before turning into a matrix of 0s and 1s Original After Transformation
- 7. As covered in class Feed-Forward Neural Nets
- 10. Overlapping Segmentation • Divide image into fixed number of overlapping tiles of the same size • In our case, 20 x 20 pixels with a 50% overlap • Discard chunks under a certain size and chunks that are all white Note: This is a B with part of it cut off, not an E. Therein lies the rub.
- 11. • Iterate through the image from left to right—segment when a full column of whitespace is encountered • Works perfectly for well-spaced text Whitespace Segmentation
- 12. K-Means Segmentation • Performs better than heuristic segmentation on closely-packed inputs
- 14. Experiment 1 Machine Learning Method: Self-Organizing Map Topology 200 buckets, initialized randomly Inputs: 3 letter CATPCHAs Random fonts Letters A-G “Chunked” using overlapping segmentation
- 15. Experiment 1 Results Buckets fell into three primary categories: Distinguishable letters Chunks with halves of two letters Indistinguishable noise
- 17. Experiment 2 ML Method: Neural Net Topology: Fully connected 400 inputs 50 node hidden layer 7 outputs Inputs: Single letter CATPCHAs Random fonts Letters A-G 400 Nodes 50 Nodes 7 Nodes Contains … ? A: 0 or 1 B : 0 or 1 C: 0 or 1 D: 0 or 1 E: 0 or 1 F: 0 or 1 G: 0 or 1
- 19. Experiment 2 Results Neural Net Accuracy vs. Size of Hidden Layer Past a certain number of nodes in the hidden layer, the topology ceases to have a huge impact on accuracy.
- 20. Experiment 3 ML Method: Neural Net Topology: Fully connected 400 inputs 1000 node hidden layer 7 outputs ML Method: SOM Topology: 500 buckets Inputs: 4 letter CATPCHAs Fandom fonts Letters A-G
- 22. Experiment 4 ML Method: Neural Net Topology: Fully connected 400 inputs 1000 node hidden layer 7 outputs ML Method: SOM Topology: 500 buckets Inputs: 4 letter CATPCHAs Fandom fonts Letters A-Z
- 24. Experiment 5 ML Method: Neural Net Topology: Fully connected 400 inputs 1000 node hidden layer 7 outputs ML Method: SOM Topology: 500 buckets Inputs: 5 letter CATPCHAs Fandom fonts Letters A-Z
- 25. Experiment 5 Neural Net vs. SOM on CAPTCHAs Length 5, Letters A-Z
- 26. What it all means • Increasing number of characters dramatically decreases total accuracy because segmentation quality decreases • True positive rate goes down when segmentation quality decreases • Hence, better segmentation is the key
- 27. Future Work Improved Segmentation o Wirescreen segmentation o Ensemble techniques Improved True Positive Rates with Current System o Ensemble techniques New problems o Handwriting recognition o Bot net of doom
- 28. Questions?