【導(dǎo)讀】行量化處理，并進(jìn)行回歸分析。隨后，原始圖像通過立方卷積插值技術(shù)和改進(jìn)的線性邊緣算法進(jìn)行放大處。最后，對(duì)放大參數(shù)Ga和表面粗糙度之間的關(guān)系進(jìn)行了比較。由于工業(yè)自動(dòng)化在制造業(yè)與日益增的需求，機(jī)器視覺中起著重要作用的質(zhì)量檢驗(yàn)和過程監(jiān)控。糙度檢查是一項(xiàng)重要的質(zhì)量控制過程，以確保制造部分符合指定的標(biāo)準(zhǔn)。這種檢查通常是通過使用觸控筆。類文書實(shí)現(xiàn)，其中相關(guān)的議案鉆石核彈頭的筆向粗糙度表面正在調(diào)查中。主要不利的始使用觸控筆等測(cè)量。是它需要直接的身體接觸，這限制了測(cè)量速度。此外，在該儀器讀數(shù)的基礎(chǔ)上數(shù)量有限的路線抽樣，這可。能并不代表真正的物體的表面。這種偏差可能會(huì)導(dǎo)致嚴(yán)重的錯(cuò)誤在表面質(zhì)量的評(píng)估，尤其是當(dāng)表面輪廓是。由于這些缺點(diǎn)，接觸式文書，不適合用于高速自動(dòng)檢查。以前的研究人員使用的機(jī)器視覺技術(shù)。每單位長(zhǎng)度的掃描線，在灰色水平形象，估計(jì)表面粗糙度。反映和總事件的強(qiáng)度，這是當(dāng)時(shí)的用于計(jì)算表面粗糙度。

　　

【正文】 the workpiece. The arithmetic average of the grey level Gacan be expressed as X _. GaZ 240。j g1K gmjCjg2K gmjC/CjgnKgmj222。 n where g1,g2,g3,.,gnare the gray level values of a surface image along one line and gmis the mean of the grey values and this can be determined as X _. gmZ 240。g 1C g2C/C gn222。 n The grey level average (Ga) has been calculated for all the surfaces after the images of the surface were captured. These Gavalues have been calibrated with the respective Ra values measured using a stylus pro?lometer. Multiple linear Table 1 R. Kumar et al. / International Journal of Machine Tools amp。 Manufacture 45 (2020) 228–234 Table 3 231 Machining parameters used for grinding and the roughness values Machining parameters used for shaping and the roughness values Speed (rpm) 1801 2204 2593 1809 1501 2020 1800 2202 2593 Depth of cut (doc) (mm) 50 50 50 30 30 30 80 80 80 Ga, optical parameter Ra(mm), stylus parameter Speed (rpm) 12 18 24 18 24 18 18 12 18 24 12 Feed (mm/stroke) Depth of cut (mm) 1 1 1 1 Ga, optical parameter Ra(mm), stylus parameter regression equations have been developed for each of the machining processes based upon the data presented in Tables 1–3. They are as follows: 24 24 1 1 (a) Grinding: RaZ 0:52K240。1:9!10K5222。speedK240。0:00044222。 doc C240。0:003322222。 Ga (b) Milling: RaZK0:97 C240。0:0003222。 speed K240。0:00694222。 feed C240。0:415222。 docC240。0:1985222。 Ga (c) Shaping RaZ 7:182C240。0:0683222。 speedC240。11:44222。 feed C240。5:61222。 docC240。0:328222。 Ga 6. Magni?cation and surface roughness Earlier research work [18] carried out on roughness evaluation of surfaces using machine vision involved Table 2 Machining parameters used for milling and the roughness values correlating the spectra of such surfaces to the roughness values and these have been shown to follow power law behavior. Pro?le of such surfaces were shown to be self af?ned which implies that when magni?ed, increasing details of roughness emerge and appear similar to the original pro?le. In this paper an attempt has been made to correlate the grey level average (Ga) values obtained from the images with their respective surface roughness and study the behavior of such a correlation at various degrees of image magni?cation for the three machining operations. Consequently, images of workpieces captured by machine vision were magni?ed by factors 2, 5, 10 and 20 using the magni?cation technique mentioned in Section 3 and improved by Linear Edge Crispening algorithm. The feature of the image under study, Ga, was extracted and a correlation between Gaand surface roughness Rawas established on the basis of data given in Tables 4–6 (for three machining processes). Based on the values of correlation coef?cient so obtained, plots have been drawn between the magni?cation factor and correlation coef?cient from the data and are shown in Fig. 1 for three machining processes. 7. Results and discussion Based on the cubic convolution algorithm, the digital Speed (rpm) 125 250 90 90 Feed (mm/min) 45 Depth of cut (mm) Ga, optical parameter Ra(mm), sty lus parameter images of machined work pieces have been magni?ed for Table 4 Variation of Gawith varying magni?cation factors for ground surfaces Ga(1!)Ga(2!) Ga(5!) Ga(10!) Ga(20!) Ra(mm) 125 180 90 125 63 63 90 125 45 45 45 45 45 1 1 1 1 1 1 232 Table 5 R. Kumar et al. / International Journal of Machine Tools amp。 Manufacture 45 (2020) 228–234 Basically the accuracy of the interpolation technique to Variation of Gawith varying magni?cation factors for milled surfaces Ga(1!)Ga(2!) Ga(5!) Ga(10!) Ga(20!) Ra(mm) provide image magni?cation depends on its convergence rate. Cubic convolution [13] offers a O(h3) convergence rate Table 6 whereas cubic spline has a fourth order convergence rate, . O(h4). It means removing or altering the conditions on interpolation kernel to achieve a higher convergence rate, which in turn demands higher putational effort to derive interpolation coef?cients. So there is a trade off between accuracy offered by an interpolation technique and ef?ciency in terms of putational effort it requires. Moreover, it is implemented quite easily by modern digital puters and image processors. Although the present algorithm is the optimal choice, it Variation of Gawith varying magni?cation factors for shaped surfaces Ga(1!) Ga(2!) Ga(5!) Ga(10!) Ga(20!) Ra(mm) cannot prevent the perceptible degradation of edges fully. a wide range of magni?cation index ranging from 2! to 20! going in steps, suitable for future task of determining surface roughness and also to assess the effectiveness of improvement scheme once applied to them. Cubic convolu tion remains as one of the best methods for magni?cation of digital images in terms of preserving edge details when pared to other methods, the blurring of edges has been found to be reduced substantially [13].