Develop traffic sign recognition modules

ANN (Artifical Neural Network) technologies have been developed for a long time since its birth and so there are a number of open source packages for the research purposes. Within those two packages are compared considering its learning speed and computing times. Our first experiment will be focused on the OCR case and later we will extend the selected ANN module for the traffic sign recognition.

Traffic sign feature extraction

Please see Traffic sign feature extraction

Selecting a proper ANN module

Please see Selecting a proper ANN module

Extension for the traffic sign recognition

Please see Extension for the traffic sign recognition

Traffic sign pattern recognition

Traffic sign pattern ANN training algorithm

Please see Traffic sign pattern ANN training algorithm

Traffic sign pattern recognition algorithm

Please see Traffic sign pattern recognition algorithm

Experiment

Please see Traffic sign recognition test

Source Codes

  • FANN codes that we downloaded from their CVS storage. This version is more improved that the version that they published at their home page. Media:fann.zip
  • TSPR recognition module that Pilho developed for the test. This version is just for the test. Media:tspr_neural.zip

Both above codes are compiled with Visual Studio 6 (05/25/2006) using OpenCV libraries.