Abstract: Machine vision measurement (MVM) is an essential approach that measures the area or length of a target efficiently and non-destructively for product quality control. The result of MVM is determined by its configuration, especially the lighting scheme design in image acquisition and the algorithmic parameter optimization in image processing. In a traditional workflow, engineers constantly adjust and verify the configuration for an acceptable result, which is time-consuming and significantly depends on expertise. To address these challenges, we propose a target-independent approach, visual interactive image clustering, which facilitates configuration optimization by grouping images into different clusters to suggest lighting schemes with common parameters. Our approach has four steps: data preparation, data sampling, data processing, and visual analysis with our visualization system. During preparation, engineers design several candidate lighting schemes to acquire images and develop an algorithm to process images. Our approach samples engineer-defined parameters for each image and obtains results by executing the algorithm. The core of data processing is the explainable measurement of the relationships among images using the algorithmic parameters. Based on the image relationships, we develop VMExplorer, a visual analytics system that assists engineers in grouping images into clusters and exploring parameters. Finally, engineers can determine an appropriate lighting scheme with robust parameter combinations. To demonstrate the effectiveness and usability of our approach, we conduct a case study with engineers and obtain feedback from expert interviews.

可视交互式图像聚类：一种机器视觉测量中目标无关的配置优化方法

[1]Afzal S, Maciejewski R, Ebert DS, 2011. Visual analytics decision support environment for epidemic modeling and response evaluation. IEEE Conf on Visual Analytics Science and Technology, p.191-200.

[2]Albers A, Gladysz B, Pinner T, et al., 2016. Procedure for defining the system of objectives in the initial phase of an Industry 4.0 project focusing on intelligent quality control systems. Proc CIRP, 52:262-267.

[3]Alonso V, Dacal-Nieto A, Barreto L, et al., 2019. Industry 4.0 implications in machine vision metrology: an overview. Proc Manuf, 41:359-366.

[4]Alsallakh B, Ren L, 2017. PowerSet: a comprehensive visualization of set intersections. IEEE Trans Visual Comput Graph, 23(1):361-370.

[5]Alsallakh B, Micallef L, Aigner W, et al., 2016. The state-of-the-art of set visualization. Comput Graph Forum, 35(1):234-260.

[6]Baron ME, 1969. A note on the historical development of logic diagrams: Leibniz, Euler and Venn. Math Gaz, 53(384):113-125.

[7]Bergner S, Sedlmair M, Moller T, et al., 2013. ParaGlide: interactive parameter space partitioning for computer simulations. IEEE Trans Visual Comput Graph, 19(9):1499-1512.

[8]Bruckner S, Möller T, 2010. Result-driven exploration of simulation parameter spaces for visual effects design. IEEE Trans Visual Comput Graph, 16(6):1468-1476.

[9]Coffey D, Lin CL, Erdman AG, et al., 2013. Design by dragging: an interface for creative forward and inverse design with simulation ensembles. IEEE Trans Visual Comput Graph, 19(12):2783-2791.

[10]Comer ML, Delp EJIII, 1999. Morphological operations for color image processing. J Electron Imag, 8(3):279-289.

[11]Eades P, 1984. A heuristic for graph drawing. Congre Numer, 42:149-160.

[12]Gleicher M, 2018. Considerations for visualizing comparison. IEEE Trans Visual Comput Graph, 24(1):413-423.

[13]Godina R, Matias JCO, 2019. Quality control in the context of Industry 4.0. Int Joint Conf on Industrial Engineering and Operations Management, p.177-187.

[14]Golnabi H, Asadpour A, 2007. Design and application of industrial machine vision systems. Robot Comput-Integr Manuf, 23(6):630-637.

[15]Kopparapu SK, 2006. Lighting design for machine vision application. Image Vis Comput, 24(7):720-726.

[16]Lex A, Gehlenborg N, Strobelt H, et al., 2014. UpSet: visualization of intersecting sets. IEEE Trans Visual Comput Graph, 20(12):1983-1992.

[17]Luk F, Huynh V, North W, 1989. Measurement of surface roughness by a machine vision system. J Phys E Sci Instrum, 22(12):977-980.

[18]Martin D, 2007. A Practical Guide to Machine Vision Lighting. Advanced Illumination, Vermont, USA, p.1-21.

[19]Munzner T, 2014. Visualization Analysis and Design. CRC Press, New York, USA.

[20]Ngo NV, Hsu QC, Hsiao WL, et al., 2017. Development of a simple three-dimensional machine-vision measurement system for in-process mechanical parts. Adv Mech Eng, 9(10):1-11.

[21]Pretorius AJ, Bray MA, Carpenter AE, et al., 2011. Visualization of parameter space for image analysis. IEEE Trans Visual Comput Graph, 17(12):2402-2411.

[22]Pretorius AJ, Zhou Y, Ruddle R, 2015. Visual parameter optimisation for biomedical image processing. BMC Bioinform, 16(S11):S9.

[23]Sadana R, Major T, Dove A, et al., 2014. OnSet: a visualization technique for large-scale binary set data. IEEE Trans Visual Comput Graph, 20(12):1993-2002.

[24]Sahoo PK, Soltani S, Wong AKC, 1988. A survey of thresholding techniques. Comput Vis Graph Image Process, 41(2):233-260.

[25]Sedlmair M, Heinzl C, Bruckner S, et al., 2014. Visual parameter space analysis: a conceptual framework. IEEE Trans Visual Comput Graph, 20(12):2161-2170.

[26]Torsney-Weir T, Saad A, Moller T, et al., 2011. Tuner: principled parameter finding for image segmentation algorithms using visual response surface exploration. IEEE Trans Visual Comput Graph, 17(12):1892-1901.

[27]Wang WC, Guan FN, Ma SY, et al., 2015. Measurement system of gear parameters based on machine vision. Meas Contr, 48(8):242-248.

[28]Weng L, Preneel B, 2011. A secure perceptual hash algorithm for image content authentication. IFIP Int Conf on Communications and Multimedia Security, p.108-121.

[29]Wu KL, Yang MS, 2007. Mean shift-based clustering. Patt Recogn, 40(11):3035-3052.

[30]Xia JZ, Ye FJ, Chen W, et al., 2018. LDSScanner: exploratory analysis of low-dimensional structures in high-dimensional datasets. IEEE Trans Visual Comput Graph, 24(1):236-245.

[31]Xia JZ, Chen TX, Zhang L, et al., 2020. SMAP: a joint dimensionality reduction scheme for secure multi-party visualization. IEEE Conf on Visual Analytics Science and Technology, p.107-118.

[32]Xia JZ, Zhang YC, Song J, et al., 2022. Revisiting dimensionality reduction techniques for visual cluster analysis: an empirical study. IEEE Trans Visual Comput Graph, 28(1):529-539.

[33]Xia JZ, Huang LQ, Lin WX, et al., 2023. Interactive visual cluster analysis by contrastive dimensionality reduction. IEEE Trans Visual Comput Graph, 29(1):734-744.

[34]Yalcin MA, Elmqvist N, Bederson BB, 2016. AggreSet: rich and scalable set exploration using visualizations of element aggregations. IEEE Trans Visual Comput Graph, 22(1):688-697.

[35]Yuan J, Chen CJ, Yang WK, et al., 2021. A survey of visual analytics techniques for machine learning. Comput Visual Med, 7(1):3-36.

[36]Yuan QM, Zhang H, 2022. Research on the characteristics of light sources in machine vision. Acad J Sci Technol, 3(1):1-6.

[37]Zhu ZH, Shen Y, Zhu SJ, et al., 2022. Towards better pattern enhancement in temporal evolving set visualization. J Vis, early access.

[38]Zorcolo A, Escobar-Palafox G, Gault R, et al., 2011. Study of lighting solutions in machine vision applications for automated assembly operations. IOP Conf Ser Mater Sci Eng, 26(1):012019.