Multi-scale Filtering Method Research Articles

A coupling enhancement algorithm for ZrO2 ceramic bearing ball surface defect detection based on cartoon-texture decomposition model and multi-scale filtering method

To improve the detection accuracy of surface defects of ZrO2 ceramic bearing balls, a detection method for surface defects of ZrO2 ceramic bearing balls based on cartoon texture decomposition model is proposed. By building a surface defect detection system for ZrO2 ceramic bearing balls, the Gaussian curvature model is used to decompose the surface defect images of ZrO2 ceramic bearing balls, and the decomposed image layers are filtered by winner filtering and wavelet value domain filtering, and fused into clear and damage-free images The surface defect image of ZrO2 ceramic bearing ball and its detection. The experimental results shown the PSNR of image is 34.1 dB, the SSIM is 0.9476, the detection accuracy is 95.8 %, and the detection speed of a single defect image is 191 ms/img. The method can remove images noise, retain its details. It improves the efficiency and accuracy of ZrO2 ceramic bearing ball surface defect detection.

Automated Visual Inspection of Glass Bottle Bottom With Saliency Detection and Template Matching

Glass bottles are widely used as containers in the food and beverage industry, especially for beer and carbonated beverages. As the key part of a glass bottle, the bottle bottom and its quality are closely related to product safety. Therefore, the bottle bottom must be inspected before the bottle is used for packaging. In this paper, an apparatus based on machine vision is designed for real-time bottle bottom inspection, and a framework for the defect detection mainly using saliency detection and template matching is presented. Following a brief description of the apparatus, our emphasis is on the image analysis. First, we locate the bottom by combining Hough circle detection with the size prior, and we divide the region of interest into three measurement regions: central panel region, annular panel region, and annular texture region. Then, a saliency detection method is proposed for finding defective areas inside the central panel region. A multiscale filtering method is adopted to search for defects in the annular panel region. For the annular texture region, we combine template matching with multiscale filtering to detect defects. Finally, the defect detection results of the three measurement regions are fused to distinguish the quality of the tested bottle bottom. The proposed defect detection framework is evaluated on bottle bottom images acquired by our designed apparatus. The experimental results demonstrate that the proposed methods achieve the best performance in comparison with many conventional methods.

Assessing the usability of digital images of human placenta with multi-scale filtering methods

Objectives: Quantitative 3D Doppler (3DPD) has shown its great potential for utero-placental (UP) vascularization evaluation as well as for pregnancy severe complications’ prediction such as preeclampsia and intrauterine growth restriction. The diffusion of this technique, however, remains limited due to its lack of reproducibility when different machine settings are used, as previously proven by in vitro and animal models studies. Our objective was to evaluate how the machine settings affect the UP 3DPD indices in pregnant women.

The Impact Mechanism of Fractal Noise on PN Code Detection System

Taking the pseudo-random phase modulated CW radar for example, this paper studies the impact mechanism of a class of non-stationary fractal noise on PN code detection system, especially signal mixing and matching filter. The cross correlation function, power spectrum function and average power of pseudo-random signal and fractal noise are deduced, compared with the impact of white noise on the pseudo code detection system. We analyze the impact mechanism of three kinds of sea clutter model, namely fractal Brownian model (FBM), the multifractal (MF) model and the non-stationary random fractal model (e.g., infinitely divisible cascades, IDC), on the pseudo-random code detection system, and demonstrate the reason why the multi-scale filtering method in wavelet domain and the MF methods fail to eliminate the effect of sea clutter. Based on the natural sea clutter data, we simulate and analyze the influence of white noise and fractal noise comparatively on detection system, which indicates that the effect of fractal noise cannot be inhibited effectively by the traditional correlation detection and MF analysis, and finally we put forward possible solutions.

Using Multi-Scale Filtering to Initialize a Background Extraction Model

Problem statement: Probability-based methods which usually work based on the saved history of each pixel are utilized severally in extracting a background image for moving detection systems. Probability-based methods suffer from a lack of information when the system first begins to work. The model should be initialized using an alternative accurate method. Approach: The use of a nonparametric filtering to calculate the most probable value for each pixel in the initialization phase can be useful. In this study a complete system to extract an adaptable gray scale background image is presented. It is a probability-based system and especially suitable for outdoor applications. The proposed method is initialized using a multi-scale filtering method. Results: The results of the experiments certify that not only the quality of the final extracted background is about 10% more accurate in comparison to four recent re-implemented methods, but also the time consumption of the extraction are acceptable. Conclusion: Using multi-scale filtering to initialize the background model and to extract the background using a probability-based method proposes an accurate and adaptable background extraction method which is able to handle sudden and large illumination changes.