1,720,968 research outputs found
DEVELOPMENT OF ARTIFICIAL INTELLIGENCE SYSTEM FOR THE FIGHTING GAMES USING LENGTH TECHNIQUE
No full textSecurity in CAI Materials by Embedding Digital Watermarks
No full textComputer-based instruction assistance (CAI) plays very important role in e-leaming system. Distancelearning students can remotely access this kind of course materials. However, being an electronic form has created a growing need to protect them against illegal manipulation and duplication. Therefore, the more robust techniques are needed. Digital watermarking has been proposed as a solution to the problem of copyright protection of multimedia for many decades. This technique can also be applied to the educational frameworks. In this paper, before the CAI will be distributed, double watermarks have been embedded into all still images in the CAI materials. Firstly, the visible watermark, e.g., university’s logo, is inserted directly on image pixel’s intensity to exhibit an ownership of the CAI. The fragile invisible watermark is then embedded again on these watermarked images. Because of the special characteristic of the latter if there is any attempt to change or remove the visible logo, it can be clearly detected. We also proposed the extracting method to reveal secret information using for verifying our right on the materials. The experiments using different kinds of attacks on the materials are also conducted. Finally, the discussion of the experimental results and conclusion of the paper are also given.</jats:p
Image Preprocessing and Trajectory Feature Extraction based on Hidden Markov Models for Sign Language Recognition
No full textAnalyzing Motion Parameters Using Unsupervised Fuzzy C-Prototypes
No full textMotion-based segmentation plays an important role in dynamic scene analysis of video sequence. This technique should not only cluster the feature vectors but also extract the optimum number of clusters that correspond to the moving objects. The motion features of moving objects in a video sequence have to be extracted so that segmentation can be performed based on this information. In this paper, we present a scheme for extracting moving objects. First, the dense optical flow fields are calculated to extract motion vectors. Surface fitting is performed over the parametric motion model. Then, an unsupervised robust fuzzy C-Prototypes clustering technique is applied to motion-based segmentation in the parameter space. Finally, the individual moving object and background can be represented in layers. Experimental results showing the significance of ths proposed method are provided. 1 Introduction Recent technology in digital video processing has moved to "content-based" storage and retr..
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Traffic Sign Recognition by Color Filtering and Particle Swarm Optimization
No full textAbstract. In this paper a comprehensive approach to traffic sign detection and recognition is proposed. An RGB roadside image is acquired. Color filtering and segmentation is used to detect the boundary of traffic sign in binary mode. At the feature extraction stage, the RGB traffic sign region is cropped. The image is resized to 100x100 pixels. Finally, particle swarm optimization is used to identify the traffic sign. Experimental results show that our system can give a high recognition rate for all types of traffic signs used in Thailand: namely, prohibitory signs (red or blue), general warning signs (yellow) and construction area warning signs (amber)
- …
