Automatic determination of text readability over textured backgrounds for augmented reality systems

This paper describes a pattern recognition approach to determine readability of text labels in augmented reality systems. In many augmented reality applications, one of the ways in which information is presented to the user is to place a text label over the area of interest. However, if this information is placed over very busy and textured backgrounds, this can affect the readability of the text. The goal of this work was to identify methods of quantitatively describing conditions under which such text would be readable or unreadable. We used texture properties and other visual features to determine if a text placed on a particular background would be readable or not. Based on these features, a supervised classifier was built that was trained using data collected front human subjects' judgment of text readability. Using a rather small training set of about 400 human evaluations over 50 heterogeneous textures the system is able to achieve a correct classification rate of over 85%.

[1]  Carl Gutwin,et al.  Multiblending: displaying overlapping windows simultaneously without the drawbacks of alpha blending , 2004, CHI.

[2]  Gordon E. Legge,et al.  Psychophysics of reading—II. Low vision , 1985, Vision Research.

[3]  J A Solomon,et al.  Texture interactions determine perceived contrast , 1989, Proceedings of the National Academy of Sciences of the United States of America.

[4]  David E. Breen,et al.  Annotating Real-World Objects Using Augmented Reality , 1995, Computer Graphics.

[5]  Anil K. Jain,et al.  Texture Analysis , 2018, Handbook of Image Processing and Computer Vision.

[6]  Nicolai Petkov,et al.  Suppression of contour perception by band-limited noise and its relation to nonclassical receptive field inhibition , 2003, Biological cybernetics.

[7]  B. Julesz.  Textons, the elements of texture perception, and their interactions , 1981, Nature.

[8]  G. Legge,et al.  Psychophysics of reading—I. Normal vision , 1985, Vision Research.

[9]  Gordon E Legge,et al.  Psychophysics of reading XX. Linking letter recognition to reading speed in central and peripheral vision , 2001, Vision Research.

[10]  Steven K. Feiner,et al.  View management for virtual and augmented reality , 2001, UIST '01.

[11]  Ronald Azuma,et al.  Evaluating label placement for augmented reality view management , 2003, The Second IEEE and ACM International Symposium on Mixed and Augmented Reality, 2003. Proceedings..

[12]  P Perona,et al.  Preattentive texture discrimination with early vision mechanisms. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[13]  A. Ahumada,et al.  Discriminability measures for predicting readability of text on textured backgrounds. , 2000, Optics express.

[14]  Denis G. Pelli,et al.  The visual filter mediating letter identification , 1994, Nature.

[15]  Lauren F. V. Scharff,et al.  Discriminability measures for predicting readability , 1999, Electronic Imaging.

[16]  Anil K. Jain,et al.  Unsupervised texture segmentation using Gabor filters , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.

[17]  Wilson S. Geisler,et al.  Texture segmentation using Gabor modulation/demodulation , 1987, Pattern Recognit. Lett..