Title :
Text detection in video sequence using 1-D DCT
Author :
Do Kyoung Shin ; Jong Min Lee ; Yong Min Kim ; Young Shik Moon ; Ki Tae Park
Author_Institution :
Dept. of Radiat. Oncology, Case Western Reserve Univ., Cleveland, OH, USA
Abstract :
In this paper, a new method of detecting text regions from video sequences, without prior knowledge such as font, color, size of characters is proposed. By analyzing the characteristics of text regions in video sequences, we found that text regions include both horizontal and vertical edges simultaneously, while background regions do not. Therefore, In order to detect text regions accurately, the detection of candidate object regions through 1D-DCT and an adaptive thresholding technique are proposed. Experimental results have shown that the proposed method successfully detects text regions regardless of environmental conditions such as low contrast, complex texture, and various colors and sizes.
Keywords :
character recognition; discrete cosine transforms; edge detection; image colour analysis; image sequences; text detection; video signal processing; 1D DCT; adaptive thresholding technique; background region; candidate object region detection; character color; character font; character size; horizontal edge; text region characteristics; text region detection; vertical edge; video sequence; Discrete cosine transforms; Educational institutions; Filtering; Image color analysis; Image edge detection; Video sequences; Discrete cosine transform; Horizontal and vertical edge maps; Text detection;
Conference_Titel :
Consumer Electronics (ISCE 2014), The 18th IEEE International Symposium on
Conference_Location :
JeJu Island
DOI :
10.1109/ISCE.2014.6884528