Chia-Jen Wang

Learn More
In this paper we present a scene-based video watermarking scheme using support vector machines (SVMs). In a given scene, the algorithm uses the first h′ frames to train an embedding SVM, and uses this SVM to watermark the rest of frames. In the extracting phrase, the detector uses center h frames of the first h′ frames to train an extracting SVM. The final(More)
This paper presents a method for improving the quality of degraded documents by noise removal and text enhancing. Histogram of a degraded document is analyzed to find out the approximate ranges of gray-value for text-, graph-, (i.e. photographs), and background-pixels. After the graph-pixels are identified, they are replaced by the background pixels.(More)
A novel scheme is proposed to extract characters from dated postcards. The illustrations of the postcards appear in various languages and colors embedded in different backgrounds. Due to reproduction and uneven illumination, these characters suffer a severely degradation and hence extracting characters using conventional methods becomes difficult. A(More)
  • 1