Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
Context:
I'm trying learning machine-learning using python3. My intended goal is to create a CNN program that can guess simple 4 letters 72*24 pixels CAPTCHA image as below:
CAPTCHA Image Displaying VDF5. This challenge was inspired by https://medium.com/#ageitgey/how-to-break-a-captcha-system-in-15-minutes-with-machine-learning-dbebb035a710, which I thought would be a great challenge for me to learn k-means clustering and CNN.
Edit---
I see I was being too "build me this guy". Now that I found scikit, I'll try to learn it and apply that instead. Sorry for annoying you all.
It seems as if you are looking to build a machine learning algorithm for educational purposes. If so, import TensorFlow and get to it! However, seeing as your question seems to be "create this for me" you might be better off simply using existing implementations from the scikit learn package. Simply import scikit learn, make an instance of the KNearestNeighborClassifier train it, and boom you've cracked this problem.
Related
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 11 months ago.
Improve this question
I'm trying to clean the line noises from this captcha, so I can implement an algorithm to read them. However, I'm finding some difficulties to make it readable to an AI using some techniques, such as Open CV threshold combined with some resources from pil.Image. I also tried an algorithm to "chop" the image, which gave me a better results, but stil far from the expected. I want to know if there is an alternative to remove noises from captchas like this one effectively.
(I'm using python)
Initially, the Captcha looks like this:
Once processed using OpenCV + Pillow, I've got this:
Later, using the "chop method" this what we have:
However, I need a better final image, but I think this methods combination is not appropriate. Is there a better alternative?
I think you could try minisom: https://github.com/JustGlowing/minisom
SOM (Self organizes maps) are a type of neural networks that group clusters of points in data, with an appropiate threshold it could help you removing those lines that are not surrounding the numbers/letters, combining that with chop method could do the job.
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 1 year ago.
Improve this question
I came across this research paper-http://www.cs.sjsu.edu/~pollett/papers/neural_net_plain.pdf.
These researchers have come up with a way to break character-based CAPTCHAs and it seems they have succeeded as they have used 13 million captchas for training the CNN they made and got accuracies higher than 95%.
How can we make a CAPTCHA secure so that it isn't bypassed by a deep learning model?
First of all, captchas are meant to stop automated users/bots. Yes, if you have the actual captcha generator, and you train a deep learning model on that distribution, chances are it will perform well.
Captchas are getting harder, they can be made even harder. But, it takes resources to generate the captchas, actual computational resources (unless they are random images and not synthetic). If it is needed to make a really bot-proof website, it can be made.
By bot, it usually means web scraping tools/automated users, who try to do things like human users, but very fast. Now, if you also integrate, deep learning models to it, it's possible to bypass the captchas (in most cases), but it may be an overkill (depending on your needs).
Saving websites from bots is less important than facial recognition, self-driving cars (relative statement).
Closed. This question needs debugging details. It is not currently accepting answers.
Edit the question to include desired behavior, a specific problem or error, and the shortest code necessary to reproduce the problem. This will help others answer the question.
Closed 1 year ago.
Improve this question
It's my first time using python and I have created a basic csv file. I want to know how would you create a predictive model using Naive Bayes to classify if the words are informative or uninformative ?
Python has a very extensive machine learning library scikit-learn.
As you are new to AI with python, you should consider learning from the basics. If you have already, DataCamp's Naive Bayes guide would be a good resource you can follow to achieve the classification model you want.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 2 years ago.
Improve this question
I'm very new to learning manim and well python. However, I'm trying to learn it to make nice videos for my students. I'm attempting to create some tree diagrams in manim, but I can't seem to find much help. I tried getting manim to use tikz, but I'm having trouble with that as well. Is there a nice way to make tree diagrams straight in manim?
The best way is that you create a class yourself to generate the trees, it is not complicated if you know how to order elements with VGroup and program the unions between each Node, since it is a personal project you will have to develop it on your own, you can also check Manim's Discord to request help from the community, the link is in the official Manim repository.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 6 years ago.
Improve this question
It would be really helpful if someone can explain and give an example of how to apply machine learning algorithms using scikit-learn and python to images,sound or videos. I know how to apply it to csv file just want to learn how it can be extended for multimedia files.
Thankyou
There's a section in the sklearn documentation on feature extracting that focuses on working with images. There's also a section of the docs that talk about working with images, video and audio. I suggest you spend some time going through these sections and the rest of the documentation.
The MNIST dataset is a standard dataset of images of hand written digits that is used in a lot of examples so if you're searching google for examples "MNIST sklearn" will probably be helpful.