Yannan Zhao

An efficient method of license plate location

License plate location is an important stage in vehicle license plate recognition for automated transport system. This paper presents a real time and robust method of license plate location. License plate area contains rich edge and texture information. We first extract out the vertical edges of the car image using image enhancement and Sobel operator, then remove most of the background and noise edges by an effective algorithm, and finally search the plate region by a rectangle window in the residual edge image and segment the plate out from the original car image. Experimental results demonstrate the great robustness and efficiency of our method.

Non-flat function estimation with a multi-scale support vector regression

Abstract Estimating the non-flat function which comprises both the steep variations and the smooth variations is a hard problem. The results achieved by the common support vector methods like SVR, LPR and LS-SVM are often unsatisfactory, because they cannot avoid underfitting and overfitting simultaneously. This paper takes this problem as a linear regression in a combined feature space which is implicitly defined by a set of translation invariant kernels with different scales, and proposes a multi-scale support vector regression (MS-SVR) method. MS-SVR performs better than SVR, LPR and LS-SVM in the experiments tried.

Recognition of gray character using gabor filters

In this paper, a novel Gabor filter-based feature extraction method for low resolution gray character classification is proposed By applying Gabor filters to a character image, dominant orientation matrix is obtained and used to form feature vector for recognition. We compared our Gabor feature with other Gabor features. Experiments show that the proposed feature extraction method achieves high recognition accuracy and is also not sensitive to noise and other distortions. This method has been used in a Vehicle License Plate Character System.

A novel hybrid feature selection algorithm: using ReliefF estimation for GA-Wrapper search

A new feature selection method named ReliefF-GA-Wrapper is proposed to combine the advantages of filter and wrapper. In the ReliefF-GA-Wrapper method, the original features are evaluated by the ReliefF method, and the resulting estimation is embedded into the genetic algorithm applied to search optimal feature subset with the train accuracy of induction learning algorithm for the evaluation function. Experiments are carried on handwritten Chinese characters dataset, which is a large-scale dataset, and several other typical datasets with features more than 20. The results show ReliefF-GA-Wrapper has better performance then ReliefF and GA-Wrapper, indicating that the proposed ReliefF-GA-Wrapper algorithm is competitive and scales well to large datasets.

Self-adaptive design of hidden Markov models

Hidden Markov models (HMMs) are stochastic models widely used in speech and image processing in recent years. The number of states in a classical HMMs is usually predefined and fixed during training, and may be quite different from the real number of hidden states of the signal source. Moreover, in pattern recognition applications, different signal sources probably have different state numbers, thereby cannot be well modeled by HMMs with a fixed state number. This paper proposes a self-adaptive design method of HMMs to overcome this limitation. According to this design, an HMM automatically matches its state number to the real state number of the signal source being modeled. To realize a practicable training algorithm for the new HMM, this paper first introduces an entropic definition of the a priori probability of the model and accordingly a maximum a posteriori (MAP) training strategy, and then designs an MAP training algorithm in the case of fixed state number based on the deterministic annealing (DA) technique. Based on this MAP training, a complete training method named shrink algorithm is finally proposed for the new HMM. Experimental results indicate that self-adaptive HMMs can model stochastic signals more accurately and have better performance in pattern recognition than classical models.

Feature selection in recognition of handwritten Chinese characters

Recognition of handwritten Chinese characters is a large-scale pattern recognition task, which is difficult and time consuming to build the corresponding classifiers. In this paper, two feature selection methods are proposed to reduce the complexity and speed up the handwritten Chinese recognition: one is the ReliefF-Wrapper method which evaluates the original features with the ReliefF method, and then uses the wrapper method to decide the number of features to be selected; and the other is GA-Wrapper that uses genetic algorithm to search the optimal subset of features with high training accuracy. Experiments were performed on 800 most frequently used Chinese characters, with 80,000 handwritten samples. Results show that the ReliefF-Wrapper method has good interpretation and high speed and GA-Wrapper gains higher accuracy. Limitations of the both methods and future work are also discussed.

Adaptive parameter tuning for relevance feedback of information retrieval

Relevance feedback is an effective way to improve the performance of an information retrieval system. In practice, the parameters for feedback were usually determined manually without the consideration of the quality of the query. We propose a new concept (adaptiveness) to measure the quality of the query. We built two models to predict the adaptiveness of the query. The parameters for feedback were then determined by the quality of the query. Our experiments on TREC data showed that the performance was improved significantly when compared with blind relevance feedback.

Design and implementation of educational platform in RoboCup simulation games

RoboCup is an international game and academic activity which focuses on improving the education and research of distributed AI, intelligent robotics, machine learning and other related fields. To stimulate the students interests of AI research and introduce the RoboCup games to more students, we transplant the RoboCup to an educational platform for students to study and research. This paper shows the structure and design of the whole platform, the specific implementation of basic modules on the educational platform. The platform is divided into three parts: low-level module, libraries, and program scheme. Students should work in the programming scheme part, build the basic skill and top-level strategy layer. This paper describes the main theory of the basic skills such as dribble, kick, and shoot, including the distributed planning in realizing these skills. The top-level strategy part analyzes the realization of several basic strategies and machine learnings impact on the game. We also provide the method and framework for implementing the basic skills and top-level strategy, called the qsinghuAeolus program. Finally, we show the educational value of the platform in RoboCup simulation games.

Conceiving, analyzing, modeling, verifying and developing-the clews of modeling open software architectures of robot controllers

Openness is one of the features of modem robot controllers. Although many modeling technologies about how to model and develop open robot controllers have been discussed, the focus is always on some detail problems in some respects. While the relative complete modeling clews have never been discussed. In this paper, an initial modeling clew is presented. The corresponding contents including basic conceptions, modeling methods, requirement analysis, and testing strategies are discussed in detail.

Design and implementation of wafer transporting system for photo lithographer

Wafer transporting system is a vital part of IC manufacturing system. This paper presents the design and implementation of the wafer transporting system. Approaches in pre-aligning process and re-locating process are important to the performance of the system. In pre-aligning, Least Square Circle Fitting is adopted to locate the center of the wafer and the notch of the wafer. In re-locating, Section Linear Interpolation is used to calibrate the sensor and special locations of sensors are applied to calculate the wafer eccentricity relative to the fiducially position. The precision of the whole system is very high.