Automated functional verification of digital television systems using camera

This paper presents an approach to automated verification of digital television systems. Camera is used to capture the content on the TV screen. An algorithm was developed for detecting the TV screen content and comparing it with the expected content. The TV screen content is extracted in two steps. The first step is the TV screen edge detection, performed with Scharr edge detection and detection of long lines and TV screen rectangle. The second step is the extraction of the TV screen content between the detected edges and its scaling to the dimensions of the referent image. The images are compared using the normalized cross-correlation method. The test suite includes the random images, selected patterns and TV menus shown on the screen. The system is planned to be used as a part of the Black Box Testing system.

[1]  Sergey Ablameyko,et al.  Fast Line and Rectangle Detection by Clustering and Grouping , 1997, CAIP.

[2]  Anthony Hoogs,et al.  Image Comparison by Compound Disjoint Information , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[3]  David W. Jacobs,et al.  Surface Dependent Representations for Illumination Insensitive Image Comparison , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Hanno Scharr,et al.  Optimal operators in digital image processing , 2000 .

[5]  Vukota Pekovic,et al.  TV Screen Content Extraction and Recognition Algorithm for the Verification of Digital Television Systems , 2010, 2010 17th IEEE International Conference and Workshops on Engineering of Computer Based Systems.

[6]  E. R. Davies,et al.  Machine vision - theory, algorithms, practicalities , 2004 .

[7]  Vukota Pekovic,et al.  On the Effectiveness of the System Validation Based on the Black Box Testing Methodology , 2009, 2009 IEEE Circuits and Systems International Conference on Testing and Diagnosis.