Classifier-based analysis of visual inspection: Gender differences in decision-making

Among manufacturing companies there is a wide-spread consensus that women are better suited to perform visual quality inspection, having higher endurance and making decisions with better reproducibility. Up to now gender-differences in visual inspection decision making have not been thoroughly investigated. We propose a machine learning approach to model male and female decisions with classifiers and base the analysis of gender-differences on the identified model parameters. A study with 50 male and 50 female subjects on a visual inspection task of stylized die-cast parts revealed significant gender-differences in the miss rate (p = 0.002), while differences in overall accuracy are not significant (p = 0.34). On a more detailed level, the application of classifier models shows gender differences are most prominent in the judgment of scratch lengths (p = 0.005). Our results suggest, that gender-differences in visual inspection are significant and that classifier-based modeling is a promising approach for analysis of these tasks.

[1]  Jacob Cohen.  Statistical Power Analysis for the Behavioral Sciences , 1969, The SAGE Encyclopedia of Research Design.

[2]  Colin G. Drury,et al.  Task Complexity in Visual Inspection , 1986 .

[3]  Winfrid G. Schneeweiss.  Stochastic Theory of Boolean Functions , 1989 .

[4]  Edwin Lughofer,et al.  Assessment of the influence of adaptive components in trainable surface inspection systems , 2010, Machine Vision and Applications.

[5]  Anand K. Gramopadhye,et al.  The effects of per-lot and per-item pacing on inspection performance , 2001 .

[6]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[7]  Douglas H. Harris,et al.  Human factors in quality assurance , 1969 .

[8]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[9]  Anand K. Gramopadhye,et al.  Noise, feedback training, and visual inspection performance , 1997 .

[10]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[11]  Edwin Lughofer,et al.  Human–Machine Interaction Issues in Quality Control Based on Online Image Classification , 2009, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[12]  A. Floren,et al.  ' " ' " ' " . " ' " " " " " ' " ' " " " " " : ' " 1 , 2001 .

[13]  Colin G. Drury,et al.  Training Programs for Inspection , 1981 .

[14]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[15]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[16]  Colin G. Drury.  Integrating Human Factors Models into Statistical Quality Control , 1976 .

[17]  J. Hyde,et al.  The Gender Similarities Hypothesis , 2005 .

[18]  P. Lachenbruch.  Statistical Power Analysis for the Behavioral Sciences (2nd ed.) , 1989 .

[19]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[20]  Steven J. Landry,et al.  Introduction to Human Factors and Ergonomics for Engineers , 2007 .