Hsiao-Wei Chang

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 multiple frames integration based approach to detect and localize static caption texts on news videos. Utilizing the temporal information of videos, the algorithm includes robust text features and the non-text line deletion technique, and yields precise and tight localization for detected text regions. The Canny edge detector is first(More)
This paper proposes an exemplar-based modified priority belief propagation (MP-BP) method to complete a stitched panorama. The result is an image with a rectangular boundary in which the missing area is filled by a visually plausible background that copies the appearance of the source region. Global optimization is usually preferable to greedy algorithms(More)
This paper proposes an image e®ect creation system that can create various types of e®ects for images, to satisfy di®erent needs of users for speci¯c design goals. Some operations needed for creating image e®ects, such as °ow-based bilateral ¯lter, °ow-based Gaussian ¯lter, curve-shaped ¯lters, line drawing, pencil texture generator, and modi¯ed shock(More)
Feature points' matching is a popular method in dealing with object recognition and image matching problems. However, variations of images, such as shift, rotation, and scaling, influence the matching correctness. Therefore, a feature point matching system with a distinctive and invariant feature point detector as well as robust description mechanism(More)
  • 1