Hierarchical models for analysis and recognition of handwritten characters

Different hierarchical models in pattern analysis and recognition are proposed, based on occurrence probability of patterns. As an important application of recognizing handprinted characters, three typical kinds of hierarchical models such asM _89-89,M _89-36 andM _36-36 have been presented, accompanied by the computer algorithms for computing recognition rates of pattern parts. Moreover, a comparative study of their recognition rates has been conducted theoretically; and numerical experiments have been carried out to verify the analytical conclusions made. Various hierarchical models deliberated in this paper can provide users more or better choices of pattern models in practical application, and lead to a uniform computational scheme (or code). The recognition rates of parts can be improved remarkably by a suitable hierarchical model. For the modelM _89-36 in which case some of the Canadian standard handprinted characters have multiple occurrence probabilities, the total mean recognition rates of the given sample may reach 120% of that by the model proposed by Li et al., and 156% of that obtained from the subjective experiments reported by Suen.     

Large tree classifier with heuristic search and global training

In the tree classifier with top-down search, a global decision is made via a series of local decisions. Although this approach gains in classification efficiency, it also gives rise to error accumulation which can be very harmful when the number of classes is very large. To overcome this difficulty, a new tree classifier with the following characteristics is proposed: 1) fuzzy logic search is used to find all ``possible correct classes,' and some similarity measures are used to determine the ``most probable class'; 2) global training is applied to generate extended terminals in order to enhance the recognition rate; 3) both the training and search algorithms have been given a lot of flexibility, to provide tradeoffs between error and rejection rates, and between the recognition rate and speed. A computer simulation of the decision trees for the recognition of 3200 Chinese character categories yielded a very high recognition rate of 99.93 percent and a very high speed of 861 samples/s, when the program was written in a high level language and run on a large multiuser time-sharing computer.     

稀土含量对喷熔层组织及耐蚀性的影响

本文通过在镍基自熔合金粉末中加入不同含量的稀土，研究了稀土含量对喷熔层组织及耐蚀性的影响规律及其作用机制。结果表明，在喷熔材料中加入适量稀土，可使喷熔层组织细化、晶界净化，从而使腐蚀过程中的表面活性点减少，耐蚀性提高。     

TDE-85环氧树脂丙烯酸酯的合成及其UV固化特性的研究

本文研究了TDE-85环氧树脂丙烯酸酯的合成方法，讨论了合成条件（催化剂的种类与用量，反应温度及时间，投料比，反应类型及不饱和酸种类的选择等）对合成反应及合成产物性状的影响。另外，还考察了该合成产物的UV固化特性。     

Near-duplicate document image matching: A graphical perspective

A near-duplicate document image matching approach characterized by a graphical perspective is proposed in this paper. Document images are represented by graphs whose nodes correspond to the objects in the images. Consequently, the image matching problem is then converted to graph matching. To deal with the instability of object segmentation, a multi-granularity object tree is constructed for a document image. Each level in the tree corresponds to one possible object segmentation, while different levels are characterized by various object granularities. Some graphs can be generated from the tree and the objects associated with each graph may be of different granularities. Two graphs with the maximum similarity are found from the multi-granularity object trees of the two near-duplicate document images which are to be matched. The encouraging experimental results have demonstrated the effectiveness of the proposed approach.     

Improved activity and thermostability of Candida antarctica lipase B by DNA family shuffling

DNA family shuffling was used to create chimeric lipase B proteins with improved activity toward the hydrolysis of diethyl 3-(3',4'-dichlorophenyl)glutarate (DDG). Three homologous lipases from Candida antarctica ATCC 32657, Hyphozyma sp. CBS 648.91 and Crytococcus tsukubaensis ATCC 24555 were cloned and shuffled to generate a diverse gene library. A high-throughput screening assay was developed and used successfully to identify chimeric lipase B proteins having a 20-fold higher activity toward DDG than lipase B from C.antarctica ATCC 32657 and a 13-fold higher activity than the most active parent derived from C.tsukubaensis ATCC 24555. In addition, the stability characteristics of several highly active chimeric proteins were also improved as a result of family shuffling. For example, the half-life at 45 degrees C and melting point (T(m)) of one chimera exceeded those of lipase B from C.antarctica ATCC 32657 by 11-fold and 6.4 degrees C, respectively, which closely approached the stability characteristics of the most thermostable parent derived from Hyphozyma sp. CBS 648.91.     

Approximation of graph edit distance based on Hausdorff matching

Graph edit distance is a powerful and flexible method for error-tolerant graph matching. Yet it can only be calculated for small graphs in practice due to its exponential time complexity when considering unconstrained graphs. In this paper we propose a quadratic time approximation of graph edit distance based on Hausdorff matching. In a series of experiments we analyze the performance of the proposed Hausdorff edit distance in the context of graph classification and compare it with a cubic time algorithm based on the assignment problem. Investigated applications include nearest neighbor classification of graphs representing letter drawings, fingerprints, and molecular compounds as well as hidden Markov model classification of vector space embedded graphs representing handwriting. In many cases, a substantial speedup is achieved with only a minor loss in accuracy or, in one case, even with a gain in accuracy. Overall, the proposed Hausdorff edit distance shows a promising potential in terms of flexibility, efficiency, and accuracy.     

Application of a multilayer decision tree in computer recognition of chinese characters

A multistage classifier with general tree structure has been developed to recognize a large number of Chinese characters. A simple and efficient method of classifying the characters was achieved by choosing the best feature at each stage of the tree. The features used are Walsh coefficients obtained from two profiles of a character projected onto the X-Y orthogonal axes. Some algorithms for aligning the characters were compared and one of them was adopted in this recognition scheme. A high recognition rate of about 99.5 percent was obtained in an experiment with more than 3000 different Chinese characters.     

Application of neural network interval regression method for minimum zone straightness and flatness

The goal of this paper is to develop an accurate, efficient, and robust algorithm for the minimum zone (MZ) straightness and flatness. In this paper, we use an interval bias adaptive linear neural network (NN) structure together with least mean squares (LMS) learning algorithm, and an appropriate cost function to carry out the interval regression analysis. From the results, we can see that both the straightness and flatness results from the interval regression method by NN can converge closer to the definition of the MZ straightness and flatness, respectively, than that of the least-squares (LSQ) method. The interval regression method by NN developed in this paper is applicable in the linear regression analysis that has a complicated constraint, and where the LSQ method cannot be used.