Local texture patterns for traffic sign recognition using higher order spectra

Gudigar, Anjan; Shreesha, C; Raghavendra, U.; Acharya, U. Rajendra

doi:10.1016/j.patrec.2017.02.016

Cited by 39 publications

(13 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method 99.84 Ensemble CNNs [25] 99.65 HOGv+KELM [15] 99.56 Committee of CNNs [23] 99.46 CNN+ELM [26] 99.40 Human (best individual) [33] 98.84 Complementary Features [17] 98.65 Multi-Scale CNN [24] 98.31 SHOG5-SBRP2 [16] 98.17 HOS-LDA [18] 97.84…”

Section: Methods Accuracymentioning

confidence: 99%

“…The experiment results revealed that the combination possessed good complementariness. In 2017, Gudigar et al coupled the order spectra with texture based features to represent the shape and content of traffic signs, and the features processed by linear discriminant analysis (LDA) is effective for traffic sign recognition [18].…”

Section: Related Workmentioning

confidence: 99%

“…HOS-LDA [18]: It extracts the features by HOS-based entropies and textures, and maximizes between class covariance and minimizes within class covariance through LDA.…”

mentioning

confidence: 99%

See 2 more Smart Citations

A Shallow Network with Combined Pooling for Fast Traffic Sign Recognition

Zhang

Huang

et al. 2017

Information

View full text Add to dashboard Cite

Traffic sign recognition plays an important role in intelligent transportation systems. Motivated by the recent success of deep learning in the application of traffic sign recognition, we present a shallow network architecture based on convolutional neural networks (CNNs). The network consists of only three convolutional layers for feature extraction, and it learns in a backward optimization way. We propose the method of combining different pooling operations to improve sign recognition performance. In view of real-time performance, we use the activation function ReLU to improve computational efficiency. In addition, a linear layer with softmax-loss is taken as the classifier. We use the German traffic sign recognition benchmark (GTSRB) to evaluate the network on CPU, without expensive GPU acceleration hardware, under real-world recognition conditions. The experiment results indicate that the proposed method is effective and fast, and it achieves the highest recognition rate compared with other state-of-the-art algorithms.

show abstract

Section: Methods Accuracymentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Shallow Network with Combined Pooling for Fast Traffic Sign Recognition

Zhang

Huang

et al. 2017

Information

View full text Add to dashboard Cite

show abstract

“…On GTSRB, they reach 98.53% of accuracy merging grayscale values of tra c sign images and Histogram of Oriented Gradients (HOG) based features, reducing the dimensionality through Iterative Nearest Neighbours-based Linear Projections (INNLP) and classifying with Iterative Nearest Neighbours (Timofte & Van Gool, 2015) (INNC). Although Support Vector Machines (SVM) (Salti et al, 2015), Random Forests (Zaklouta et al, 2011) and Nearest Neighbours (Gudigar et al, 2017) classifiers have been used to recognise tra c sign images, Convolutional Neural Networks (Lecun et al, 1998), also known as ConvNets or CNNs, showed particularly high classification accuracies in the competition. Cireşan et al (2012) won the GTSRB contest (Stallkamp et al, 2012) with a 99.46% accuracy thanks to a committee of 25 CNN by using data augmentation and jittering.…”

Section: Related Workmentioning

confidence: 99%

Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods

2018

View full text Add to dashboard Cite

This paper presents a Deep Learning approach for traffic sign recognition systems. Several classification experiments are conducted over publicly available traffic sign datasets from Germany and Belgium using a Deep Neural Network which comprises Convolutional layers and Spatial Transformer Networks. Such trials are built to measure the impact of diverse factors with the end goal of designing a Convolutional Neural Network that can improve the state-of-the-art of traffic sign classification task. First, different adaptive and non-adaptive stochastic gradient descent optimisation algorithms such as SGD, SGD-Nesterov, RMSprop and Adam are evaluated. Subsequently, multiple combinations of Spatial Transformer Networks placed at distinct positions within the main neural network are analysed. The recognition rate of the proposed Convolutional Neural Network reports an accuracy of 99.71% in the German Traffic Sign Recognition Benchmark, outperforming previous state-of-the-art methods and also being more efficient in terms of memory requirements.

show abstract

“…In the medical field, it was successfully applied in breast ultrasound and mammography image enhancement [11,12], in cell image segmentation [13,14], in retinal vessel image processing [15,16], and in enhancement of bone fracture images [17]. Beyond medical field, CLAHE was applied to enhance underwater images [18,19], to perform fruit segmentation in agricultural systems [20,21], and to assist driving systems to improve vehicle detection [22], traffic sign detection [23], and pedestrian detection [24].…”

Section: Introductionmentioning

confidence: 99%

Machine learning hyperparameter selection for Contrast Limited Adaptive Histogram Equalization

Campos

Mastelini

Aguiar

et al. 2019

J Image Video Proc.

View full text Add to dashboard Cite

Contrast enhancement algorithms have been evolved through last decades to meet the requirement of its objectives. Actually, there are two main objectives while enhancing the contrast of an image: (i) improve its appearance for visual interpretation and (ii) facilitate/increase the performance of subsequent tasks (e.g., image analysis, object detection, and image segmentation). Most of the contrast enhancement techniques are based on histogram modifications, which can be performed globally or locally. The Contrast Limited Adaptive Histogram Equalization (CLAHE) is a method which can overcome the limitations of global approaches by performing local contrast enhancement. However, this method relies on two essential hyperparameters: the number of tiles and the clip limit. An improper hyperparameter selection may heavily decrease the image quality toward its degradation. Considering the lack of methods to efficiently determine these hyperparameters, this article presents a learning-based hyperparameter selection method for the CLAHE technique. The proposed supervised method was built and evaluated using contrast distortions from well-known image quality assessment datasets. Also, we introduce a more challenging dataset containing over 6200 images with a large range of contrast and intensity variations. The results show the efficiency of the proposed approach in predicting CLAHE hyperparameters with up to 0.014 RMSE and 0.935 R 2 values. Also, our method overcomes both experimented baselines by enhancing image contrast while keeping its natural aspect.

show abstract

Local texture patterns for traffic sign recognition using higher order spectra

Cited by 39 publications

References 42 publications

A Shallow Network with Combined Pooling for Fast Traffic Sign Recognition

A Shallow Network with Combined Pooling for Fast Traffic Sign Recognition

Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods

Machine learning hyperparameter selection for Contrast Limited Adaptive Histogram Equalization

Contact Info

Product

Resources

About