engleski

Extraction of Scene Text in HSI Color Space using K-means Clustering with Chromatic and Intensity Distance

Text extraction is important step that strongly influences on the final recognition performance. This task is especially challenging in case of scene text which is characterized with wide set of degradations like complex backgrounds, uneven illumination, viewing angle, etc. In this paper we evaluated text extraction based on K-means clustering in HSI color space with chromatic distance and intensity distance. Obtained results are analyzed with respect to their complementarity in order to show potential for performance improvement. Comparison is also made with approach using cylin drical distance in K-means clustering of HSI image.

scene text extraction; K - means; chromatic distance; intensity distance

nije evidentirano