认知语义学述评

认知语义学是对传统意义观的诸多不足之处的一种反思。认知语义学强调人类在认知过程中与周围世界的相互作用，认为基本类概念和图像一图式是人类建立复杂认知模式的根本。概念的建立与人自身的躯体经验关系密切。认知语义学的证据主要来源于两个方面：一是成功地分析和解释了一些语义现象，二是心理语言学研究为认知语义学提供了实验证据。认知语义学是一门正在发展与完善的语义理论，有很多问题尚待研究。

EFFECTIVE IMAGE SEGMENTATION FRAMEWORK FOR GAUSSIAN MIXTURE MODEL INCORPORATING LOCAL INFORMATION

A new two-step framework is proposed for image segmentation. In the first step, the gray-value distribution of the given image is reshaped to have larger inter-class variance and less intra-class variance. In the sec- ond step, the discriminant-based methods or clustering-based methods are performed on the reformed distribution. It is focused on the typical clustering methods-Gaussian mixture model （GMM） and its variant to demonstrate the feasibility of the framework. Due to the independence of the first step in its second step, it can be integrated into the pixel-based and the histogram-based methods to improve their segmentation quality. The experiments on artificial and real images show that the framework can achieve effective and robust segmentation results.

Turbo-Based DNW Algorithm for Compressed Video in VLC Domain

In order to improve the robustness of the differential number watermarking (DNW) algorithm proposed by us before, we proposed turbo-based DNW (T-DNW) in which the turbo code was employed in the DNW algorithm. The turbo code was used to encode the message prior to watermark embedding and decode the watermark posterior to watermark detection. From the analysis and experiments, the following conclusion could be drawn. The T-DNW algorithm has little higher computational complexity than DNW. And both algorithms have the same performance in terms of watermark visual quality impact. Furthermore, the T-DNW algorithm is much more robust against some common attack than DNW. Although the T-DNW algorithm sacrifices a half payload, we think the achievements are encouraging.

A color based face detection system using multiple templates

A color based system using multiple templates was developed and implem ented for detecting human faces in color images. The algorithm consists of three image processing steps. The first step is human skin color statistics. Then it separates skin regions from non-skin regions. After that, it locates the fronta l human face(s) within the skin regions. In the first step, 250 skin samples from persons of different ethnicities are used to determine the color distribution o f human skin in chromatic color space in order to get a chroma chart showing lik elihoods of skin colors. This chroma chart is used to generate, from the origina l color image, a gray scale image whose gray value at a pixel shows its likelih ood of representing the skin. The algorithm uses an adaptive thresholding proces s to achieve the optimal threshold value for dividing the gray scale image into separate skin regions from non skin regions. Finally, multiple face templates ma tching is used to determine if a given skin region represents a frontal human fa ce or not. Test of the system with more than 400 color images showed that the re sulting detection rate was 83%, which is better than most color-based face dete c tion systems. The average speed for face detection is 0.8 second/image (400×300 pixels) on a Pentium 3 (800MHz) PC.

A Skeleton Extraction Framework Based on Inner-Product and Border Gap

A novel algorithm for skeleton extraction is proposed in the paper. By numbering objeet＇s border dements on spatial position, the border gap （BG） of inner pixel of the object is calculated; an 8-connected medial-axis hierarchy is derived by the BG; a thinning method including slicing and counting is proposed to improve the processing speed; branches with minor importance are truncated by vector diversity Vd and length-width ratio （LWR） with support vector machine （SVM） classifier. Experiments demonstrate that the derived skeletons keep good connectivity, especially in long and narrow area.

Medical Image Dynamic Collaborative Processing on the Distributed Environment

A new trend in the development of medical image processing systems is to enhance the shar-ing of medical resources and the collaborative processing of medical specialists. This paper presents an architecture of medical image dynamic collaborative processing on the distributed environment by combining the JAVA, CORBA (Common Object Request and Broker Architecture) and the MAS (Multi-Agents System) collaborative mechanism. The architecture allows medical specialists or applications to share records and cornmunicate with each other on the web by overcoming the shortcut of traditional approach using Common Gateway Interface (CGI) and client/server architecture, and can support the remote heterogeneous systems collaboration. The new approach im-proves the collaborative processing of medical data and applications and is able to enhance the in-teroperation among heterogeneous system. Research on the system will help the collaboration and cooperation among medical application systems distributed on the web, thus supply high quality medical service such as diagnosis and therapy to practicing specialists regardless of their actual geo-graphic location.

AN LBP-BASED MULTI-SCALE ILLUMINATION PREPROCESSING METHOD FOR FACE RECOGNITION

It is one of the major challenges for face recognition to minimize the disadvantage of il- lumination variations of face images in different scenarios. Local Binary Pattern (LBP) has been proved to be successful for face recognition. However, it is still very rare to take LBP as an illumination preprocessing approach. In this paper, we propose a new LBP-based multi-scale illumination pre- processing method. This method mainly includes three aspects: threshold adjustment, multi-scale addition and symmetry restoration/neighborhood replacement. Our experiment results show that the proposed method performs better than the existing LBP-based methods at the point of illumination preprocessing. Moreover, compared with some face image preprocessing methods, such as histogram equalization, Gamma transformation, Retinex, and simplified LBP operator, our method can effectively improve the robustness for face recognition against illumination variation, and achieve higher recog- nition rate.

Online Sequential Extreme Multilayer Perception with Time Series Learning Machine Based Output Self Feedback for Prediction

This study presents a time series prediction model with output self feedback which is implemented based on online sequential extreme learning machine. The output variables derived from multilayer perception can feedback to the network input layer to create a temporal relation between the current node inputs and the lagged node outputs while overcoming the limitation of memory which is a vital port for any time-series prediction application. The model can overcome the static prediction problem with most time series prediction models and can effectively cope with the dynamic properties of time series data. A linear and a nonlinear forecasting algorithms based on online extreme learning machine are proposed to implement the output feedback forecasting model. They are both recursive estimator and have two distinct phases： Predict and Update. The proposed model was tested against different kinds of time series data and the results indicate that the model outperforms the original static model without feedback.