An image denoising method based on multiscale wavelet thresholding and bilateral filtering

Shi, Wenxuan; Li, Jie; Wu, Mingxi

doi:10.1007/s11859-010-0212-y

Cited by 24 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image processing approaches in surface defect inspection involve techniques like thresholding [4][5][6], image denoising and enhancement [7][8][9], to improve visibility and identify surface patterns for defect detection and classification. Improved Otsu's methods [4], [5] and global adaptive percentile thresholding [6] have been utilized for detecting steel surface defects.…”

Section: ) Image Processing-based Methodsmentioning

confidence: 99%

“…Improved Otsu's methods [4], [5] and global adaptive percentile thresholding [6] have been utilized for detecting steel surface defects. Morphological processing [7] and bilateral filtering [8] techniques have been employed to reduce noise and preserve edges. A joint-prior-based uneven illumination enhancement (JPUIE) method [9] has been used to eliminate uneven illumination in images for surface defect detection.…”

Section: ) Image Processing-based Methodsmentioning

confidence: 99%

“…In recent years, advances in image processing [4][5][6][7][8][9], machine learning [10][11][12][13][14][15], and deep learning [16][17][18][19][20] techniques have revolutionized surface inspection, enabling more accurate, efficient, and automated inspection processes. Image processing and machine learning approaches offer valuable tools for surface inspection, but they have limitations regarding feature selection and generalization.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Enhancing Metal Surface Defect Recognition Through Image Patching and Synthetic Defect Generation

Mustafaev,

Kim,

Kim

2023

IEEE Access

View full text Add to dashboard Cite

Preventing surface defects of metal products during the production process is challenging due to manufacturing complexity, material properties and environmental factors. Relying on human inspectors for quality control can introduce human error, which increases the risk of delivering defective products to customers. To address these challenges, we propose an Inception-CNN model specifically designed for surface defect recognition in servo motor housings (SMHs). The model incorporates an inception module between convolutional layers to effectively capture multi-scale local information and extract complex and abstract features. Additionally, we introduce an image patching technique that enhances defect recognition for small defects by reducing image complexity while maintaining defect visibility. Moreover, we propose a surface defect generation GAN (SDG-GAN) method, a novel approach that addresses the data imbalance problem and improves the accuracy and robustness of the classification model through generating diverse and high-quality synthetic defect images. The original data was collected using a line scan camera installed in the SMHSI system. We ensured model generalization through 10-fold cross-validation using the SMHSD-P-GAN dataset. Evaluation results indicate that our classification model outperformed other CNN models and achieved strong generalization, with 99.40% accuracy in cross-validation and 99.23% on the original test data. This represents a substantial 32.31% improvement over a baseline CNN model trained on the SMHSD-O-TA dataset, underscoring the effectiveness of our proposed approaches in enhancing classification performance Our method efficiently processes 12 images per second, making it ideal for real-time defect inspection in SMHs. Its successful integration into the SMHSI system confirms its practicality and effectiveness in real-world industrial applications.

show abstract

Section: ) Image Processing-based Methodsmentioning

confidence: 99%

Section: ) Image Processing-based Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Metal Surface Defect Recognition Through Image Patching and Synthetic Defect Generation

Mustafaev,

Kim,

Kim

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, the experimental results show that the noise is sharpened while the image is sharpened. In [8], Shi K Q et al adaptively adjust the gray level standard deviation in the bilateral filter according to the noise standard deviation in the filter window, but the calculation method has defects, resulting in poor image edge preservation effect. C. Xiong et al propose a parameter adaptive bilateral filtering algorithm [9], and it also removes the pseudo-edges of the image, which is better than that achieved by traditional Canny edge detection algorithm [10][11].…”

Section: Introductionmentioning

confidence: 99%

Adaptive block level bilateral filtering algorithm

Zhang

2023

ACE

View full text Add to dashboard Cite

During the acquisition or transmission process, video images are subject to random signal interference and generate noise, which can hinder people's understanding of the image and subsequent processing work. Therefore, it is necessary to study video image denoising and filtering algorithms. Bilateral filter is one of many typical video image filtering algorithms. However, the traditional bilateral filter algorithm does not consider the differences in the contents of different regions of the image. It is difficult to obtain the optimal filtering effect by using a fixed filtering weight to filter the entire image, which leads to problems such as blurred image edges and inadequate details processing. This paper studies the influence of different filter block sizes on the bilateral filter effect, and proposes an algorithm to adaptively update the bilateral filter weight according to the block's variance. The experimental result shows that the performance of adaptive bilateral filter with different block sizes is expected to be better than that of traditional algorithms with fixed filter weights.

show abstract

“…In recent years, another effective image denoising method called bilateral filtering (BF) was proposed [6]. Based on multiscale wavelet transform (WT) and BF, Shi et al [7] proposed an image denoising method. This method applies BF to the approximation subbands and WT to the detail subbands in all wavelet decomposition scales.…”

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of Image Denoising Methods Based on Wavelet Transform and Threshold Functions

Lin

2017

IJE

View full text Add to dashboard Cite

There are many unavoidable noise interferences in image capturing and transmission. In order to make it better for subsequent processing, the noise in the image should be removed in advance. There are many kinds of image noises, mainly including salt & pepper noise and Gaussian noise. This paper focuses on the research of the Gaussian noise removal. It introduces many wavelet threshold denoising algorithms which include global threshold denoising, Maxmin threshold denoising, and BayesShrink threshold denoising. Besides, we make a comparative analysis for these denoising methods. The experimental result shows that the wavelet images denoising algorithm based on Gaussian mixture model has the best performance than other threshold denoising methods in both subjectivity and objectivity.

show abstract

An image denoising method based on multiscale wavelet thresholding and bilateral filtering

Cited by 24 publications

References 14 publications

Enhancing Metal Surface Defect Recognition Through Image Patching and Synthetic Defect Generation

Enhancing Metal Surface Defect Recognition Through Image Patching and Synthetic Defect Generation

Adaptive block level bilateral filtering algorithm

Comparative Analysis of Image Denoising Methods Based on Wavelet Transform and Threshold Functions

Contact Info

Product

Resources

About