Traffic Signs Preprocessed
- by user1
- 04 March, 2022
Different techniques for preprocessing
LicenseOther (specified in description)
Tagsimage data, classification, deep learning, cnn, multiclass classification
📰 Related Papers
- Sichkar V. N. Real time detection and classification of traffic signs based on YOLO version 3 algorithm. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2020, vol. 20, no. 3, pp. 418–424. DOI: 10.17586/2226-1494-2020-20-3-418-424 (Full-text available on ResearchGate here: Real time detection and classification of traffic signs based on YOLO version 3 algorithm
- Sichkar V. N. Effect of various dimension convolutional layer filters on traffic sign classification accuracy. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2019, vol. 19, no. 3, pp. 546–552. DOI: 10.17586/2226-1494-2019-19-3-546-552 (Full-text available on ResearchGate here: Effect of various dimension convolutional layer filters on traffic sign classification accuracy
🎓 Related course for classification tasks
Design, Train & Test deep CNN for Image Classification. Join the course & enjoy new opportunities to get deep learning skills:
https://www.udemy.com/course/convolutional-neural-networks-for-image-classification/
🗺️ Concept Map of the Course
👉 Join the Course
Related Dataset for Detection Tasks
Explore one more dataset used for detection tasks here: https://www.kaggle.com/valentynsichkar/traffic-signs-dataset-in-yolo-format
About this Dataset for Classification Tasks
This is ready to use preprocessed data for Traffic Signs saved into the nine pickle files.
Original datasets are in the following files:
– train.pickle
– valid.pickle
– test.pickle
Code with detailed description on how datasets were preprocessed is in datasets_preparing.py
Before preprocessing training dataset was equalized making examples in the classes equal as it is shown on the figure below. Histogram of 43 classes for training dataset with their number of examples for Traffic Signs Classification before and after equalization by adding transformated images (brightness and rotation) from original dataset. After equalization, training dataset has increased up to 86989 examples.
Resulted preprocessed nine files are as follows:
– data0.pickle – Shuffling
– data1.pickle – Shuffling, /255.0 Normalization
– data2.pickle – Shuffling, /255.0 + Mean Normalization
– data3.pickle – Shuffling, /255.0 + Mean + STD Normalization
– data4.pickle – Grayscale, Shuffling
– data5.pickle – Grayscale, Shuffling, Local Histogram Equalization
– data6.pickle – Grayscale, Shuffling, Local Histogram Equalization, /255.0 Normalization
– data7.pickle – Grayscale, Shuffling, Local Histogram Equalization, /255.0 + Mean Normalization
– data8.pickle – Grayscale, Shuffling, Local Histogram Equalization, /255.0 + Mean + STD Normalization
Datasets data0 – data3 have RGB images and datasets data4 – data8 have Gray images.
Shapes of data0 – data3 are as following (RGB):
– xtrain: (86989, 3, 32, 32)
– ytrain: (86989,)
– xvalidation: (4410, 3, 32, 32)
– yvalidation: (4410,)
– xtest: (12630, 3, 32, 32)
– ytest: (12630,)
Shapes of data4 – data8 are as following (Gray):
– xtrain: (86989, 1, 32, 32)
– ytrain: (86989,)
– xvalidation: (4410, 1, 32, 32)
– yvalidation: (4410,)
– xtest: (12630, 1, 32, 32)
– ytest: (12630,)
mean image and standard deviation were calculated from train dataset and applied to validation and testing datasets for appropriate datasets. When using user’s image for classification, it has to be preprocessed firstly in the same way and in the same order according to the chosen dataset among nine.
Test online
Experiment online with custom Traffic Sign here: https://valentynsichkar.name/traffic_signs.html
Acknowledgements
Initial data is German Traffic Sign Recognition Benchmarks (GTSRB).
Size: 4366298 KB Price: Free Author: Valentyn Sichkar Data source: kaggle.com