Yen-Shou Lai

Robust lossless image watermarking based on α-trimmed mean algorithm and support vector machine

This paper presents a robust lossless watermarking technique, based on @a-trimmed mean algorithm and support vector machine (SVM), for image authentication. SVM is trained to memorize relationship between the watermark and the image-dependent watermark other than embedding watermark into the host image. While needing to authenticate the ownership of the image, the trained SVM is used to recover the watermark and then the recovered watermark is compared with the original watermark to determine the ownership. Meanwhile, the robustness can be enhanced using @a-trimmed mean operator against attacks. Experimental results demonstrate that the technique not only possesses the robustness to resist on image-manipulation attacks under consideration but also, in average, is superior to other existing methods being considered in the paper.

A zero-watermark scheme with geometrical invariants using SVM and PSO against geometrical attacks for image protection

Highlights? A zero-watermark scheme is proposed using RST invariant features, the SVM and the PSO algorithm against RST attacks for image authentication. ? The SVM-based zero-watermark scheme makes no changes to original images after embedding the owner signature of images. ? The SVM-based zero-watermark scheme requires no original image while retrieving watermarks. ? The particle swarm optimization algorithm is employed to search for a set of nearly optimal parameters of the SVM. ? In average, the SVM-based zero-watermark scheme outperforms other existing methods against RST attacks. This paper proposes a zero-watermark scheme with geometrical invariants using support vector machine (SVM) classifier against geometrical attacks for image authentication. Here geometrical attacks merely address rotation, scale, and translation (RST) operations on images. The proposed scheme is called the SVM-based zero-watermark (SZW) scheme hereafter. The SZW method makes no changes to original images while embedding the owner signature of images so as to achieve high transparency. Moreover, in order to promote the robustness to RST operations, it integrates the discrete Fourier transform (DFT) with the log-polar mapping (LPM) for finding out RST invariants of images. The SZW method then generates the secret key for a host image via performing a logical operation exclusive disjunction, an exclusive-or (XOR) operation, on the original watermark and a set of the characteristics of the RST invariants of the host image. Subsequently, a trained SVM (TSVM) is regarded as a mapping so that it can memorize the relationships between the set of characteristics of RST invariants and the secret key. During the watermark-extraction process of the SZW method, the TSVM is first fed with the set of characteristics of RST invariants of the watermarked image to get the estimated secret key. The SZW method then extracts the estimated watermark by performing the XOR operation on the set of characteristics of RST invariants and the estimated secret key. Consequently, the SZW method requires no original image while retrieving watermarks. In the paper, the particle swarm optimization (PSO) algorithm is also employed to search for a set of nearly optimal parameters of the SVM. Finally, the experimental results show that, in average, the SZW method outperforms other existing methods against RST attacks under consideration here.

Using SVM to design facial expression recognition for shape and texture features

This paper presents a novel facial emotion recognition (FER) technique, based on support vector machine (SVM), to recognize the facial emotion expression. Here it is called the FERS technique. First, a face detection method, which combines the Haar-like features (HFs) method with the self quotient image (SQI) filter, is used in the FERS technique to accurately locate the face region of an image. It can improve the detection rate due to the use of the SQI filter to overcome the insufficient light and shade light. Subsequently, angular radial transform (ART), discrete cosine transform (DCT) and Gabor filter (GF) are employed in the procedure of facial expression feature extraction. An SVM is trained and then utilized to recognize the facial expression for a queried face image. Finally, experimental results show that the recognition performance of the FERS technique can be better than that of other existing methods.

Using the RFIDs to Construct the Ubiquitous Self-Learning Environment for Understanding the Plants in the Schoolyard

This paper uses the radio frequency identification (RFID) to construct a smart ubiquitous learning environment. In the ubiquitous computing environment, learners can get the right learning contents to achieve self-learning at the right place and the right time through non-contact RFID identification. The learning system is composed of three layers, the portable learning object, the mobile device, and the system modules for learning management and manipulation. A total of twenty-eight students recruited from fifth grade elementary school are participating in the quasi-experimental study. After three weeks of investigated subject learning, the results showed that the average scores of attitude for the experimental group are higher than the control one. There was statistical difference for learning attitude between them.

A Multimedia Learning System Using HMMs to Improve Phonemic Awareness for English Pronunciation

Phonetic awareness is a critical and often neglected component in the learning of the English language. It is submitted that good pronunciation can improve upon spelling and reading abilities of children. This paper describes a multimedia (ML) learning system that is directed at children with the aim of enhancing their English pronunciation. The system uses hidden Markov models (HMMs) to analyze phonetic structures, identify and capture pronunciation errors. It provides children with targeted advice in pronunciation, intonation, rhythm and volume that is equivalent to four years of instruction. The system was tested in an informal experiment that involved thirty two elementary students that were divided into two groups: sixteen high and sixteen low achievers. It helped the low achieving group to significantly improve not only their English pronunciation but their spelling and reading abilities.

Development trend analysis of augmented reality system in educational applications

With the rapid development of information technology, computer-assisted learning and instruction integrated with information technology, these technologies have been widely used in the traditional classroom. The concept of augmented reality is to place computer graphics on the real environment. It provides an interactive and intuitional interface to help users for observing the three-dimensional virtual objects in the real world. Currently, most of augmented reality (AR) applications focus on the research issues, such as military, medicine, and game. This study investigates the educational development and application of AR system in recent years. This study also analyzes the acceptance and effectiveness of augmented reality as well as the trend in education.

A multimedia instructional environment for english learning

The paper explores the effects on learning of English as a first foreign language by utilizing the multimedia equipments, including personal computer (PC), digital video recorder (DVR), projector, and dual integrated viewer (DIV), to present the recording/recorded learning activities as learning materials in a classroom environment. An experiment was applied to two groups of third-grade students in the elementary school in Taiwan. The singular and plural forms of English vocabularies were presented as the learning content. Learning environment of the conventional group was in a traditional classroom setting with whiteboard teaching. The second group was in a multimedia learning environment with projector to display the computer slides on the screen and an extra digital video recorder to capture the students mouth shape. The result showed that the experiment group performed better than the conventional group on learning effects. Consequently, the finding supports the use of multimedia equipments in classroom learning environment.

Robust lossless watermarking using alpha-trimmed mean and SVM

This paper presents a robust lossless watermarking technique using alpha-trimmed mean and support vector machine (SVM), which is called the RLW method hereafter. It does not damage the contents of original images during watermark embedding, because it uses trained SVMs to memorize the watermark or owner signature and then exploits the trained SVMs to estimate the watermark. Meanwhile, its robustness can be enhanced using alpha-trimmed mean operator against attacks. Experimental results demonstrate that the RLW method not only possesses the robust ability to resist on image-manipulation attacks under consideration but also, in average, is superior to other existing methods being considered in the paper.

Constructing a Multi-Monitor Displays System for Learning

This paper proposes a Multi-monitor Displays (MMD) System for assisting primary school students with their learning performance in music learning. The progress of computer technology has enabled an explosion in the visual ways of teaching presentation. In recent years, most educators present their instructional materials by using projectors primarily rather than chalkboards. Multimedia instruction is a good approach for learners to construct meaningful knowledge and to make referential connections between mental representations. This paper proposes a multi-monitor approach for constructing a multimedia aided learning system supported by some popular tools such as Microsoft PowerPoint, Microsoft Word, Microsoft Excel, and Adobe Acrobat Reader. Based on the Cognitive Theory of Multimedia Learning, this aided system is realized to combine and support verbal and pictorial forms. As a result, teachers can easily develop their teaching materials and present reference materials on two different monitors or screens. Our experiment reveals that by using the MMD system to simultaneously present musical notations and a listening map the results using multimedia presentation are superior to those of the conventional instruction methods when it comes to learning achievement and creative ability.

Tutorial 2: Search Engines in Indian Languages

This paper presents a distributed network diagnosis (DND) algorithm for an arbitrary network topology where every node needs to record the status of every other nodes and links assuming the nodes and links are subjected to crash and value faults in a dynamic fault environment (the nodes or links status may change during execution of algorithm). The algorithm operates correctly in each connected component if the network is partitioned due to a set of faulty links or faulty nodes. The worst-case bounds for diagnostic latency is at most O(td) rounds where t is the number of dissemination trees and d is the diameter of the network. The proposed approach uses non-broadcasting method of message dissemination that has similar diagnostic latency with flooding [4] and similar message complexity with Chinese Agent [14] method of message dissemination respectively.