Logo recognition in images [closed]

by

You could try to use local features like SIFT here:
http://en.wikipedia.org/wiki/Scale-invariant_feature_transform

It should work because logo shape is usually constant, so extracted features shall match well.

The workflow will be like this:

  1. Detect corners (e.g. Harris corner detector) – for Nike logo they are two sharp ends.

  2. Compute descriptors (like SIFT – 128D integer vector)

  3. On training stage remember them; on matching stage find nearest neighbours for every feature in the database obtained during training. Finally, you have a set of matches (some of them are probably wrong).

  4. Seed out wrong matches using RANSAC. Thus you’ll get the matrix that describes transform from ideal logo image to one where you find the logo. Depending on the settings, you could allow different kinds of transforms (just translation; translation and rotation; affine transform).

Szeliski’s book has a chapter (4.1) on local features.
http://research.microsoft.com/en-us/um/people/szeliski/Book/

P.S.

  1. I assumed you wanna find logos in photos, for example find all Pepsi billboards, so they could be distorted. If you need to find a TV channel logo on the screen (so that it is not rotated and scaled), you could do it easier (pattern matching or something).

  2. Conventional SIFT does not consider color information. Since logos usually have constant colors (though the exact color depends on lightning and camera) you might want to consider color information somehow.

More Related Contents:

  1. Is there anyone that can help me in finding an accurate dataset?
  2. Fine Tuning of GoogLeNet Model
  3. Machine Learning Two class classification [closed]
  4. Artificial Neural Network Toplogy
  5. how to get a single feature vector from SIFT descriptor [closed]
  6. What function defines accuracy in Keras when the loss is mean squared error (MSE)?
  7. A guide to convert_imageset.cpp
  8. Clarification on a Neural Net that plays Snake
  9. Common causes of nans during training of neural networks
  10. How to interpret MSE in Keras Regressor
  11. Intuitive understanding of 1D, 2D, and 3D convolutions in convolutional neural networks [closed]
  12. Epoch vs Iteration when training neural networks [closed]
  13. Why does one hot encoding improve machine learning performance? [closed]
  14. How to calculate optimal batch size
  15. Unable to approximate the sine function using a neural network
  16. ResNet: 100% accuracy during training, but 33% prediction accuracy with the same data
  17. Is deep learning bad at fitting simple non linear functions outside training scope (extrapolating)?
  18. How to interpret loss and accuracy for a machine learning model [closed]
  19. How to put more weight on certain features in machine learning?
  20. Pattern recognition in time series [closed]
  21. TimeDistributed(Dense) vs Dense in Keras – Same number of parameters
  22. How to create caffe.deploy from train.prototxt
  23. How to reduce a fully-connected (`”InnerProduct”`) layer using truncated SVD
  24. What is the difference between supervised learning and unsupervised learning? [closed]
  25. Which machine learning classifier to choose, in general? [closed]
  26. What is `lr_policy` in Caffe?
  27. Early stopping with Keras and sklearn GridSearchCV cross-validation
  28. Using pre-trained word2vec with LSTM for word generation
  29. How can I get biases from a trained model in Keras?
  30. Under what parameters are SVC and LinearSVC in scikit-learn equivalent?

Leave a Comment