A Model for Classification of Traffic Signs Using Improved Convolutional Neural Network and Image Enhancement

Loukmane, Attoumane; Graña, Manuel; Mestari, Mohammed

doi:10.1109/icds50568.2020.9268761

Cited by 6 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, the German Traffic Sign Recognition Benchmark (GTSRB) dataset, with 43 classes containing 39,208 unique images of real traffic signs in Germany. It has been widely used in DL research ( Castanyer, Martínez-Fernández & Franch, 2021a ; Stallkamp et al, 2012 ; Loukmane, Graña & Mestari, 2020 ). This type of images are characterized by large changes of visual appearance for different causes ( e.g ., weather conditions).…”

Section: Methodsmentioning

confidence: 99%

Guiding the retraining of convolutional neural networks against adversarial inputs

Durán

Martínez‐Fernández

Felderer

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

Background When using deep learning models, one of the most critical vulnerabilities is their exposure to adversarial inputs, which can cause wrong decisions (e.g., incorrect classification of an image) with minor perturbations. To address this vulnerability, it becomes necessary to retrain the affected model against adversarial inputs as part of the software testing process. In order to make this process energy efficient, data scientists need support on which are the best guidance metrics for reducing the adversarial inputs to create and use during testing, as well as optimal dataset configurations. Aim We examined six guidance metrics for retraining deep learning models, specifically with convolutional neural network architecture, and three retraining configurations. Our goal is to improve the convolutional neural networks against the attack of adversarial inputs with regard to the accuracy, resource utilization and execution time from the point of view of a data scientist in the context of image classification. Method We conducted an empirical study using five datasets for image classification. We explore: (a) the accuracy, resource utilization, and execution time of retraining convolutional neural networks with the guidance of six different guidance metrics (neuron coverage, likelihood-based surprise adequacy, distance-based surprise adequacy, DeepGini, softmax entropy and random), (b) the accuracy and resource utilization of retraining convolutional neural networks with three different configurations (one-step adversarial retraining, adversarial retraining and adversarial fine-tuning). Results We reveal that adversarial retraining from original model weights, and by ordering with uncertainty metrics, gives the best model w.r.t. accuracy, resource utilization, and execution time. Conclusions Although more studies are necessary, we recommend data scientists use the above configuration and metrics to deal with the vulnerability to adversarial inputs of deep learning models, as they can improve their models against adversarial inputs without using many inputs and without creating numerous adversarial inputs. We also show that dataset size has an important impact on the results.

show abstract

Section: Methodsmentioning

confidence: 99%

Guiding the retraining of convolutional neural networks against adversarial inputs

Durán

Martínez‐Fernández

Felderer

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…First, the German Traffic Sign Recognition Benchmark (GTSRB), with 43 classes containing 39.208 unique images of real traffic signs in Germany. It has been widely used in DL research [6,22,36]. This type of images are characterized by large changes of visual appearance for different causes (e.g., weather conditions).…”

Section: Data Collection and Preprocessing: Datasetsmentioning

confidence: 99%

Guiding the retraining of convolutional neural networks againstadversarial inputs: best guidance metrics and configurations

2022

View full text Add to dashboard Cite

Background: When using deep learning models, there are many possible vulnerabilities and some of the most worrying are the adversarial inputs, which can cause wrong decisions (e.g., wrongly classifying an image) with minor perturbations. Therefore, it becomes necessary to retrain these models against adversarial inputs, as part of the software testing process addressing the vulnerability to adversarial inputs. Furthermore, for an energy efficient testing and retraining process, data scientists need support on which are the best guidance metrics for reducing the adversarial inputs to use as well as optimal dataset configurations.Aims: We examined four guidance metrics for retraining deep learning models, specifically with convolutional neural network architecture, and three retraining configurations. Our goal is to improve the convolutional neural networks against adversarial inputs with regard to accuracy, resource utilization and time from the point of view of a data scientist in the context of image classification.Method: We conduced an empirical study in two datasets for image classification. We explore: (a) the accuracy, resource utilization and time of retraining convolutional neural networks by ordering new training set by four different guidance metrics (neuron coverage, likelihood-based surprise adequacy, distance-based surprise adequacy and random), (b) the accuracy and resource utilization of retraining convolutional neural networks with three different configurations (from scratch and augmented dataset, using weights and augmented dataset, and using weights and only adversarial inputs).Results: We reveal that retraining with adversarial inputs from original model weights and by ordering with surprise adequacy metrics gives the best model w.r.t. accuracy, resource utilization and time.Conclusions: Although more studies are necessary, we recommend data scientists to use the above configuration and metrics to deal with the vulnerability to adversarial inputs of deep learning models, as they can improve their models against adversarial inputs without using many inputs. We also show that dataset size has an important impact on the results. CCS Concepts• Computing methodologies → Machine learning; Artificial intelligence; • Software and its engineering → Software creation and management.

show abstract

“…Contrarily, recognizing traffic signs is more crucial for accuracy than labeling [5,6] . Convolutional Neural Networks (CNN) [7] are a type of deep neural network that is comparable to the visual processing of human vision [8,4] and can learn more discriminative characteristics. In traffic sign identification algorithms, CNN performs better than the current top methods [9] .…”

Section: Introductionmentioning

confidence: 99%

An Efficient Traffic Sign Classification and Recognition with Deep Convolutional Neural Networks

2023

ijcih

View full text Add to dashboard Cite

Driver safety assisted driving, and autonomous driving all depend on automated traffic sign recognition. The most popular deep learning method for recognizing traffic signs is convolutional neural networks. (CNNs). This paper presents a useful technique for automatically detecting images of traffic signs. When employing the two common traffic sign photo datasets GTSRB, our method makes use of our CNN model architecture and performs the best. It aids the driver in safely operating the motor vehicle. The amount of time and effort drivers spend manually evaluating and recognizing traffic signs is excessive. This work provides an autonomous traffic sign identification using a convolutional neural network. Our work here introduces a unique CNN architecture with an Adam optimizer and a batch size of 128 to improve the efficiency of traffic sign recognition. Results based on a complex network were more accurately produced by a convolutional neural network (CNN). With 99.81% precision and a minimum of losses, our system learns from the GTSRB dataset, which contains 43 traffic classes, to identify the correct class of an anonymous traffic sign. The results, however, are better than those of the prior research, which examined this approach's accuracy and efficiency in recognizing traffic signs despite poor weather and hazy image circumstances.

show abstract

A Model for Classification of Traffic Signs Using Improved Convolutional Neural Network and Image Enhancement

Cited by 6 publications

References 20 publications

Guiding the retraining of convolutional neural networks against adversarial inputs

Guiding the retraining of convolutional neural networks against adversarial inputs

Guiding the retraining of convolutional neural networks againstadversarial inputs: best guidance metrics and configurations

An Efficient Traffic Sign Classification and Recognition with Deep Convolutional Neural Networks

Contact Info

Product

Resources

About