Efficient Traffic Sign Recognition Using CLAHE-Based Image Enhancement and ResNet CNN Architectures

Dubey, Utkarsh; Chaurasiya, Rahul Kumar

doi:10.4018/ijcini.295811

Cited by 6 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike the normal histogram equalizer in the adaptive method there are some histograms that are calculated on different parts of the image. and these histograms are used to redistribute the brightness values of the image [14]. Before applying the CLAHE process, the crop and unsharp masking techniques will be implemented [15].…”

Section: Preprocessing Clahementioning

confidence: 99%

Analysis of Pneumonia on Chest X-Ray Images Using Convolutional Neural Network Model iResNet-RS

Chandranegara,

Vitanti,

Suharso

et al. 2024

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Pneumonia, a prevalent inflammatory condition affecting lung tissue, poses a significant health threat across all age groups and remains a leading cause of infectious mortality among children worldwide. Early diagnosis is critical in preventing severe complications and potential fatality. Chest X-rays are a valuable diagnostic tool for pneumonia; however, their interpretation can be challenging due to unclear images, overlapping diagnoses, and various abnormalities. Consequently, expedient, and accurate analysis of medical images using computer-aided methods has become crucial. This research proposes a Convolutional Neural Network (CNN) model, specifically the ResNet-RS Model, to automate pneumonia identification. The Contrast Limited Adaptive Histogram Equalization (CLAHE) technique enhances image contrast and highlights abnormalities in pneumonia images. Additionally, data augmentation techniques are applied to expand the image dataset while preserving the intrinsic characteristics of the original images. The proposed methodology is evaluated through three testing scenarios, employing chest X-ray images and pneumonia dataset. The third testing scenario, which incorporates the ResNet-RS model, CLAHE preprocessing, and data augmentation, achieves superior performance among these scenarios. The results show an accuracy of 92% and a training loss of 0.0526. Moreover, this approach effectively mitigates overfitting, a common challenge in deep learning models. By leveraging the power of the ResNet-RS model, along with CLAHE preprocessing and data augmentation techniques, this research demonstrates a promising methodology for accurately detecting pneumonia in chest X-ray images. Such advancements contribute to the early diagnosis and timely treatment of pneumonia, ultimately improving patient outcomes and reducing mortality rates.

show abstract

Section: Preprocessing Clahementioning

confidence: 99%

Analysis of Pneumonia on Chest X-Ray Images Using Convolutional Neural Network Model iResNet-RS

Chandranegara,

Vitanti,

Suharso

et al. 2024

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

show abstract

“…In the same year, Shen et al [9] proposed an effective multi-scale attention module, which aggregates features of different scales, suppresses clutter information in the background, and constructs an information feature pyramid for detecting traffic signs of different sizes. In 2022, Dubey et al [10] proposed a two-step TSR method, which uses a convolutional neural network as a multi-class classifier. Compared with other similar methods, this method has better classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

Research on a Traffic Sign Recognition Method under Small Sample Conditions

Zhang

2023

Sensors

View full text Add to dashboard Cite

Traffic signs are updated quickly, and there image acquisition and labeling work requires a lot of manpower and material resources, so it is difficult to provide a large number of training samples for high-precision recognition. Aiming at this problem, a traffic sign recognition method based on FSOD (few-shot object learning) is proposed. This method adjusts the backbone network of the original model and introduces dropout, which improves the detection accuracy and reduces the risk of overfitting. Secondly, an RPN (region proposal network) with improved attention mechanism is proposed to generate more accurate target candidate boxes by selectively enhancing some features. Finally, the FPN (feature pyramid network) is introduced for multi-scale feature extraction, and the feature map with higher semantic information but lower resolution is merged with the feature map with higher resolution but weaker semantic information, which further improves the detection accuracy. Compared with the baseline model, the improved algorithm improves the 5-way 3-shot and 5-way 5-shot tasks by 4.27% and 1.64%, respectively. We apply the model structure to the PASCAL VOC dataset. The results show that this method is superior to some current few-shot object detection algorithms.

show abstract

“…In the same year, Shen et al [15] proposed the GMSA module, which achieved good results on various traffic sign datasets. In 2022, Dubey et al [16] proposed a two-step TSR method, which achieved good classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

Traffic sign detection algorithm based on improved YOLOv7

Zhang

2023

International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023)

View full text Add to dashboard Cite

Aiming at the problems of low detection accuracy and slow detection speed of existing deep learning-based traffic sign detection methods, this paper proposes an improved YOLOv7 traffic sign detection method CN-YOLOv7. First, based on the idea of ConvNeXt network, this paper introduces ConvNeXt_block with integrated attention in the feature extraction network to reduce the loss of small target traffic sign feature information during downsampling, improve the accuracy of traffic sign detection and reduce the number of network floating point operations; in the detection head part, in order to improve the detection ability for tiny targets, this paper adds a small target detection head. On this basis, in order to speed up the network calculation, this paper adjusts the maximum pooling layer arrangement of the SPPCSPC module based on the detection layer structure to obtain the SPPFCSPC module, which replaces the SPPCSPC module and reduces the number of network parameters under the same feeling field. In addition, this paper uses K-means++ clustering algorithm to obtain predefined anchor frames to make them more suitable for the dataset, which improves the robustness and detection accuracy of the algorithm. The comparison experiments on the homemade dataset and CCTSDB dataset show that compared with the YOLOv7 algorithm, the CN-YOLOv7 algorithm improves the mAP by 4.1% and the inference speed reaches 61.7 FPS. Compared with SSD, Faster R-CNN, YOLOv5, YOLOv7 and other methods, the CN-YOLOv7 ensures the detection speed At the same time, it can effectively improve the detection accuracy, and the detection effect is better than the original network model and the traditional classical target detection network model.

show abstract

Efficient Traffic Sign Recognition Using CLAHE-Based Image Enhancement and ResNet CNN Architectures

Cited by 6 publications

References 23 publications

Analysis of Pneumonia on Chest X-Ray Images Using Convolutional Neural Network Model iResNet-RS

Analysis of Pneumonia on Chest X-Ray Images Using Convolutional Neural Network Model iResNet-RS

Research on a Traffic Sign Recognition Method under Small Sample Conditions

Traffic sign detection algorithm based on improved YOLOv7

Contact Info

Product

Resources

About