Fuzzy rule-based models are widely used in many fields. The existing performance indexes for the models are mainly numeric, which ignore the characteristic of fuzzy sets in the models. Aiming at the problem, a new method of evaluating the performance of fuzzy rule-based models was proposed, to effectively evaluate the non-numeric (granular) nature of results formed by the fuzzy models. In this method, different from the commonly used numeric performance indexes (such as Mean Squared Error (MSE)), the characteristics of information granules were used to represent the quality of granular results output by the model and this proposed index was applied for the performance optimization of the fuzzy model. The performance of information granule was quantified by two basic indexes, coverage rate (of data) and specificity (of information granule itself), and the maximization of the output quality of granularity (expressed as the product of coverage rate and specificity) was realized with the use of particle swarm optimization. Moreover, the distribution of information granules formed through fuzzy clustering was optimized. The experimental results show the effectiveness of the proposed method on the performance evaluation of fuzzy rule-based models

Moving object detection is the essential process of object recognition, marking and tracking in video sequences, the background subtraction algorithm is widely used in moving object detection. Concerning the problem that illumination changing, noise and local motion seriously affect the accuracy of moving object detection, a moving object detection algorithm based on background subtraction for video sequences was proposed. The background subtraction was combined with inter-frame difference to estimate the motion state of current frame pixels. The related pixels in the static and motion region were replaced and updated respectively. The Otsu method was used to extract moving object and the mathematical morphological operation was used to eliminate the noise and redundant information in the objects. The experimental results show that the proposed algorithm has good visual effect and high accuracy for detecting moving objects in video sequences, and it can overcome the shortcomings such as local movement and noise.

Current feature extraction methods are mainly based on global or local features. In order to fully utilize all the sample information, this paper presented Face Feature Extraction based on Graph (FFEG). At the training stage, the optimal projection was computed by learning the training samples, which guaranteed the samples within classes were close and between classes were far away. At the recognition stage, the test samples were successively mapped onto the optimal projection, and then the nearest neighbor classifier was used for classification and recognition. The experimental results on ORL dataset prove the effectiveness of the proposed method.

Disparity estimation is a key technology for stereo video compression. Considering the disadvantage of the epipolar correction algorithm, a fast disparity estimation algorithm based on the features of disparity vector was proposed. The algorithm analyzed the features of disparity vector in parallel camera and convergent camera systems respectively, and explained how to find the best matching block by a three-step search according to their features. The algorithm was tested in both 640×480 and 1280×720 resolution sequences. The experimental results show that compared to the original TZSearch algorithm in JMVC, the proposed algorithm can effectively shorten the encoding time and improve coding efficiency without decreasing the image quality and compression efficiency. Because there is not epipolar correction in the proposed algorithm, the disadvantage caused by epipolar correction will not appear.

The authors studied the clustering mechanism in Mobile Ad Hoc Network (MANET) and proposed a maximal weighted clustering algorithm based on connected dominating set, including clustering algorithm and clustering maintenance strategy. The comprehensive performance of nodes was quantized by the weighted amount of node mobility, minimum average emissive power, and the energy consumption rate. The improved algorithm for solving connected dominating set was used for clustering the nodes, which made the higher performance nodes be the cluster heads and reduced the number of clusters. The simulation results show that the proposed algorithm is beneficial to improving the load balancing ability and enhancing the robustness and stability of the network.

A skew angle detection approach using Hough transform was proposed for OMR images. The proposed method doesn’t need to identify exact position of locating marks and can bear high noise. In order to avoid heavy computing of Hough transform, a low-resolution image was created by sampling OMR image. Also, a fast iteration algorithm based on run-length center for written marks segmentation was presented. Experiment results show that the algorithm can achieve skew correction and segmentation of OMR image efficiently and accurately.