Yuan-Kai Wang

Context awareness and adaptation in mobile learning

This study investigates the importance of context-awareness and adaptation in mobile learning. Context-aware mobile learning that senses mobile environment and reacts to changing context during learning process has four interaction modes with three mobile entities of different mobility. Contexts in mobile learning are categorized into six dimensions that form a context space. Several mobile learning systems are examined according to the definition of context-aware mobile learning. Challenging issues of context awareness and adaptation are explored.

Genetic-based search for error-correcting graph isomorphism

Error-correcting graph isomorphism has been found useful in numerous pattern recognition applications. This paper presents a genetic-based search approach that adopts genetic algorithms as the searching criteria to solve the problem of error-correcting graph isomorphism. By applying genetic algorithms, some local search strategies are amalgamated to improve convergence speed. Besides, a selection operator is proposed to prevent premature convergence. The proposed approach has been implemented to verify its validity. Experimental results reveal the superiority of this new technique than several other well-known algorithms.

Remarks on space-time codes including a new lower bound and an improved code

This article presents a new asymptotically exact lower bound on pairwise error probability of a space-time code as well as an example code that outperforms the comparable orthogonal-design-based space-time (ODST) code. Also contained in the article are an exact expression for pairwise error probability (PEP), signal design guidelines, and some observations relating to the reception of ODST codes.

Marginal noise removal of document images

Marginal noise is a common phenomenon in document analysis which results from the scanning of thick documents or skew documents. It usually appears in the front of a large and dark region around the margin of document images. Marginal noise might cover meaningful document objects, such as text, graphics and forms. The overlapping of marginal noise with meaningful objects makes it difficult to perform the task of segmentation and recognition of document objects. This paper proposes a novel approach to remove marginal noise. The proposed approach consists of two steps which are marginal noise detection and marginal noise deletion. Marginal noise detection will reduce an original document image into a smaller image, and then find marginal noise regions according to the shape length and location of the split blocks. After the detection of marginal noise regions, different removal methods are performed. A local thresholding method is proposed for the removal of marginal noise in gray-scale document images, whereas a region growing method is devised for binary document images. Experimenting with a wide variety of test samples reveals the feasibility and effectiveness of our proposed approach in removing marginal noises.

Single image defogging by multiscale depth fusion.

Restoration of fog images is important for the deweathering issue in computer vision. The problem is ill-posed and can be regularized within a Bayesian context using a probabilistic fusion model. This paper presents a multiscale depth fusion (MDF) method for defog from a single image. A linear model representing the stochastic residual of nonlinear filtering is first proposed. Multiscale filtering results are probabilistically blended into a fused depth map based on the model. The fusion is formulated as an energy minimization problem that incorporates spatial Markov dependence. An inhomogeneous Laplacian–Markov random field for the multiscale fusion regularized with smoothing and edge-preserving constraints is developed. A nonconvex potential, adaptive truncated Laplacian, is devised to account for spatially variant characteristics such as edge and depth discontinuity. Defog is solved by an alternate optimization algorithm searching for solutions of depth map by minimizing the nonconvex potential in the random field. The MDF method is experimentally verified by real-world fog images including cluttered-depth scene that is challenging for defogging at finer details. The fog-free images are restored with improving contrast and vivid colors but without over-saturation. Quantitative assessment of image quality is applied to compare various defog methods. Experimental results demonstrate that the accurate estimation of depth map by the proposed edge-preserved multiscale fusion should recover high-quality images with sharp details.

Fabric Classification Based on Recognition Using a Neural Network and Dimensionality Reduction

Fabric classification plays an important role in the textile industry. In this paper, two fabric classification methods, the neural network and dimensionality reduction, are proposed to automatically classify fabrics based on measured hand properties. The methods are independent and reinforce each other. The first method adopts a neural network to recognize the category of an unknown fabric. In the second method, a dimensionality reduction technique is applied to reduce the dimensionality of the mea sured properties of input fabrics from sixteen dimensions to two. The reduced features are then plotted in a two-dimensional coordinate system to visualize and verify the classification results of the neural network. In experiments conducted to verify the validity of our proposed approach, fabric data are expressed in the form of hand prop erties extracted from the KES-FB system (Kawabatas evaluation system for fabrics). These experiments confirm the feasibility and efficiency of our approach with a wide variety of fabrics.

A genetic sparse distributed memory approach to the application of handwritten character recognition

Kanervas Sparse Distributed Memory (SDM) is one of the self-organizing neural networks that mimic closely the psychological behavior of the human brain. In this paper, a Genetic Sparse Distributed Memory (GSDM) model that combines SDM with genetic algorithms is proposed. The proposed GSDM model not only maintains the advantages of both SDM and genetic algorithms, but also has higher memory utilization to improve the recognition rate. Its effective performance is also verified by application to Optical Character Recognition (OCR). Experimental results reveal the feasibility and validity of the proposed model.

Applying genetic algorithms on pattern recognition: an analysis and survey

In this paper, a concise mode is proposed to model a fundamental pattern recognition problem. From this concise mode, three optimization subproblems of pattern recognition are discussed. The reason why genetic algorithms are appropriate for solving pattern recognition problems are explained by comparing the advantages and disadvantages of various kinds of approaches. The status of applying genetic algorithms on pattern recognition is surveyed in this paper.

A robust vehicle detection approach

Vehicle detection plays an important role in the intelligent transportation system. In this paper, we propose a novel approach which performs a spatio-temporal wavelet transform on videos to obtain motion information of vehicles. Different kinds of motion information extracted in sub-bands are combined to form an additive motion image. The additive motion image is then processed by adaptive thresholding, connected components labeling to segment moving region. The moving region is not accurate since the wavelet transform references many consecutive frames along temporal domain. We present a location calibration method to obtain precise moving regions of vehicles. The proposed approach is tolerant to cast shadow and camera vibration. Experimental videos are captured from roadway and expressway. Experimental results show high precision and recall rates.

Real-time camera anomaly detection for real-world video surveillance

This paper proposes an automatic event detection technique for camera anomaly by image analysis, in order to confirm good image quality and correct field of view of surveillance videos. The technique first extracts reduced-reference features from multiple regions in the surveillance image, and then detects anomaly events by analyzing variation of features when image quality decreases and field of view changes. Event detection is achieved by statistically calculating accumulated variations along temporal domain. False alarms occurred due to noise are further reduced by an online Kalman filter that can recursively smooth the features. Experiments are conducted on a set of recorded videos simulating various challenging situations. Compared with an existing method, experimental results demonstrate that our method has high precision and low false alarm rate with low time complexity.