An Improved Adaptive Weighted Mean Filtering Approach for Metallographic Image Processing

Shao, Chonglei; Kaur, Preet; Kumar, Rajeev

doi:10.1515/jisys-2020-0080

Cited by 10 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This technique replaces the pixel values with an average of all the current values [9][10][11]. Table 2 provides a sample of 3x3 pixels and the equation to calculate them (2):…”

Section: Mean Filteringmentioning

confidence: 99%

“…Since the Mean Filtering method effectively reduces picture noise and sharpens images by replacing pixel values with the average of all previous values, it was chosen [9][10][11]. Several criteria are employed in a confusion matrix to test the accuracy of this procedure, namely True Positive (TP), True Negative (TN), False Positive (FP), and False Negative (FN) making it easier during the calculation process [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Median and Mean Filtering Methods for Optimizing Face Detection in Digital Photo

Sunardi¹,

Yudhana²,

Wijaya³

2023

RIA

View full text Add to dashboard Cite

Locating the facial region is the aim of face detection in digital images. Face detection issues frequently arise because of digital image noise levels. This study uses median and means filtering techniques to reduce noise in digital photographs. A confusion matrix is used to quantify the median and means filtering methods' accuracy, while the parameters Mean Square Error (MSE) and Peak Noise to Signal Ratio (PNSR) are used to assess these approaches' performance. For this experiment, Viola-Jones was chosen as the face detection method since it is one of the face detection methods with the best accuracy and computational power. According to the outcomes of comparing the median and mean filtering techniques using MSE and PNSR on 50 image samples, the median filtering approach produced the lowest average MSE results, with a value of 19.43, and the median filtering procedure yielded a 13.74 value for the highest PNSR score. The fastest average time was obtained from the mean filtering method with a time of 3.18 seconds. As for the accuracy based on the confusion matrix, these two methods get a good accuracy of 90%. These findings indicate that the Median Filtering approach is superior to the Mean Filtering method in terms of error.

show abstract

“…This technique replaces the pixel values with an average of all the current values [9][10][11]. Table 2 provides a sample of 3x3 pixels and the equation to calculate them (2):…”

Section: Mean Filteringmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of Median and Mean Filtering Methods for Optimizing Face Detection in Digital Photo

Sunardi¹,

Yudhana²,

Wijaya³

2023

RIA

View full text Add to dashboard Cite

show abstract

“…Mean Filtering Method. It uses the average brightness value or weighted value of all pixels in the neighborhood of gray jump points to replace the original jump pixel value, remove abnormal pixels, and realize image smoothing, so as to eliminate noise [11,12]. e mathematical form of mean filtering is as follows:…”

Section: Computer Virtual Image Technologymentioning

confidence: 99%

“…It uses the average brightness value or weighted value of all pixels in the neighborhood of gray jump points to replace the original jump pixel value, remove abnormal pixels, and realize image smoothing, so as to eliminate noise [ 11 , 12 ]. The mathematical form of mean filtering is as follows:

where d i is the neighboring pixel value of the jumping pixel g ( x , y ), e i is the weighting coefficient of the neighboring pixel, that is, the template coefficient, and mn is the number of weighting coefficients, that is, the template size.…”

Section: Computer Virtual Image Technologymentioning

confidence: 99%

Concrete Application of Computer Virtual Image Technology in Modern Sports Training

Chi

Li²

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The efficiency of basketball shooting training has always been an urgent problem to be solved in basketball sports. Applying computer virtual image technology to basketball sports training is the key to improve basketball shooting ability and improve the effect of basketball sports training. Therefore, based on the design of basketball shooting automatic recognition system based on the background difference method, this study puts forward the specific application of computer virtual image technology in modern sports training. By analyzing the techniques of image denoising, image detection, and image calibration, a goal detection algorithm for modern sports basketball shooting training is designed. Firstly, the camera is used for image capture, the RGB image is converted into gray image, and the median filter is used to suppress the noise in the image. Then, the background difference method is used to detect the moving region, and the background modeling is combined with the mean method. After obtaining the background reference model, the image is differentiated, the gray image after image difference is binarized, and then the binary image is postprocessed by morphological middle closure operation. Finally, the image calibration technology is used to extract the basketball feature information. Through the region segmentation algorithm, the basketball shooting part is segmented and judged, so as to realize the basketball shooting training goal detection. The experimental results show that the proposed method has a good effect on basketball shooting training goal detection and can effectively improve the detection accuracy and efficiency.

show abstract

“…[7][8][9][10] High-density FICS digital images are acquired through a metallographic microscope platform, exhibiting diverse grain shapes, significant noise interference, and large variations in grayscale. 11,12 During defect detection, the texture structure of FICS images may resemble certain defects, thereby interfering with defect detection. Additionally, it is challenging to simultaneously eliminate noise and small defects during denoising processes.…”

Section: Introductionmentioning

confidence: 99%

A differential geometry-based method for detecting etching defects in high-density interconnect IC substrates

Yu,

Huang,

Zhou

et al. 2023

First Advanced Imaging and Information Processing Conference (AIIP 2023)

View full text Add to dashboard Cite

An Improved Adaptive Weighted Mean Filtering Approach for Metallographic Image Processing

Cited by 10 publications

References 15 publications

Application of Median and Mean Filtering Methods for Optimizing Face Detection in Digital Photo

Application of Median and Mean Filtering Methods for Optimizing Face Detection in Digital Photo

Concrete Application of Computer Virtual Image Technology in Modern Sports Training

A differential geometry-based method for detecting etching defects in high-density interconnect IC substrates

Contact Info

Product

Resources

About