The Influence of the Choice of a Gaussian Filter on the Determination of Areal Surface Texture Parameters

Current vision-based roughness measurement methods are classified into two main types: index design and deep learning. Among them, the computation procedure for constructing a roughness correlation index based on image data is relatively difficult, and the imaging environment criteria are stringent and not universally applicable. The roughness measurement method based on deep learning takes a long time to train the model, which is not conducive to achieving rapid online roughness measurement. To tackle with the problems mentioned above, a visual measurement method for surface roughness of milling workpieces based on broad learning system was proposed in this paper. The process began by capturing photos of the milling workpiece using a CCD camera in a normal lighting setting. Then, the train set was augmented with additional data to lower the quantity of data required by the model. Finally, the broad learning system was utilized to achieve the classification prediction of roughness. The experimental results showed that the roughness measurement method in this paper not only had a training speed incomparable to deep learning models, but also could automatically extract features and exhibited high recognition accuracy.

Section: Resultsmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Classification and inspection of milling surface roughness based on a broad learning system

Fang

Wang

et al. 2022

“…The measurable goal was to obtain a periodic mesa-shaped pixel structure with perpendicular, smooth sidewalls and rectangular corners. According to the definition given in [16], the surface roughness was assessed in our work, not the profile roughness. The paper describes in detail the inductively coupled plasma -reactive ion etching (ICP-RIE) processes of InAs/GaSb type II SL heterostructures and examines the effect of ICP/RIE etching time on etch rate, mesa sidewall slope, and the surface morphology between the pixels.…”

Section: Introductionmentioning

confidence: 99%

The use of one-component plasma in the icp-rie etching process of periodic structures for applications in photodetector arrays

Różycka,

Jasik,

Kozłowski

et al. 2023

The paper presents the effect of ICP-RIE etching time using one-component plasma on various parameters of an InAs/GaSb type II superlattice matrix. In the studies, two samples used at different BCl3 gas flow rates were compared and it was found that using a lower flow rate of 7 sccm results in obtaining a smoother sidewall morphology. Next, five periodic mesa-shaped structures were etched under identical conditions, but using a different time. The results indicated that the ICP-RIE method using a BCl3 flow rate of 7 sccm, ICP:RIE power ratio of 300W:270W allowed the ICP:RIE formation of a periodic mesa-shaped structure with smooth and perpendicular sidewalls.

“…However, in practical measurement, various factors influence determination of areal parameters and uncertainties for optical measurement. For example, the possible factors may be metrology characteristics of the measuring instrument [5], vibration [6], temperature fluctuations [7,8], the application of filtering [9,10], noise [11], non-measured points (NMPs) [12] and outliers [13].…”

Section: Introductionmentioning

confidence: 99%

Experimental study of non-measured points on surface measurement using structured illumination microscopy

Li,

Gröger

2022

Non-measured points (NMPs) are one of vital problems in optical measurement. The number and location of NMPs affect the obtained surface texture parameters. Therefore, systematic studying of the NMP is meaningful in understanding the instrument performance and optimizing measurement strategies. This paper investigates the influence of measurement settings on the non-measured points ratio (NMPR) using structured illumination microscopy. It is found that using a low magnification lens, high exposure time, high dynamic range (HDR) lighting levels, and low vertical scanning interval may help reduce the NMPR. In addition, an improved approach is proposed to analyze the influence of NMP on areal surface texture parameters. The analysis indicates that the influence of NMP on some parameters cannot be ignored, especially for extreme height parameters and feature parameters.