A common viewpoint-free framework that fuses pose recovery and classification for action and gait recognition is presented in this paper. First, a markerless pose recovery method is adopted to automatically capture the 3-D human joint and pose parameter sequences from volume data. Second, multiple configuration features (combination of joints) and movement features (position, orientation, and height of the body) are extracted from the recovered 3-D human joint and pose parameter sequences. A hidden Markov model (HMM) and an exemplar-based HMM are then used to model the movement features and configuration features, respectively. Finally, actions are classified by a hierarchical classifier that fuses the movement features and the configuration features, and persons are recognized from their gait sequences with the configuration features. The effectiveness of the proposed approach is demonstrated with experiments on the Institut National de Recherche en Informatique et Automatique Xmas Motion Acquisition Sequences data set.

This paper presents a novel approach for marker-less 3D full body pose tracking using adaptive particle filter. Firstly, the search space decomposition strategy and body part segmentation method are used to reduce the calculation complexity due to the large degrees of freedom. Then an adaptive particle filter is adopted to track each body part. This new technique is a significant improvement over the standard particle filter with the advantage of adaptive particle number for each body part. Experimental results on tracking several challenging action sequences have shown that the proposed 3D full body tracker is able to effectively handle rapid no-linear movements, large changes of viewpoint, and different actors. The average errors of joint position are from 0.56 to 1.13 voxel in these action sequences.

In this paper, we present a novel method for human action recognition with the combined global movement feature and local configuration feature. The human action is represented as a sequence of joints in the 4D spatio-temporal space, and modeled by two HMMs, a conventional HMM for global movement feature and an exemplar-based HMM for configuration feature. Firstly, an adaptive particle filter is adopted to track the marker-less actor's 3D joints. Then, the combined features are extracted from the full body tracking results. Finally, the actions are classified by fusing two HMMs. The effectiveness of the proposed algorithm is demonstrated with experiments on 7 actions by 12 actors. The results prove robustness of the proposed method with respect to viewpoints and actors.

Classifier combination is an effective method to improve the recognition accuracy of a biometric system. It has been applied to many practical biometric systems and achieved excellent performance. However, there is little literature involving theoretical analysis on the effectiveness of classifier combination. In this paper, we investigate classifiers combined with the max and min rules. In particular, we compute the recognition performance of each combined classifier, and illustrate the condition in which the combined classifier outperforms the original unimodal classifier. We focus our study on personal verification, where the input pattern is classified into one of two categories, the genuine or the impostor. For simplicity, we further assume that the matching score produced by the original classifier follows a normal distribution and the outputs of different classifiers are independent and identically distributed. Randomly-generated data are employed to test our conclusion. The influence of finite samples is explored at the same time. Moreover, an iris recognition system, which adopts multiple snapshots to identify a subject, is introduced as a practical application of the above discussions.

Abstract Joint source–channel coding schemes have been proven to be very effective for reliable multimedia communications. In this paper, we develop a joint source–channel coding scheme that combines the hidden Markov source (HMS) estimation and the low‐density parity‐check (LDPC) codes with an iterative estimation/decoding scheme. With this innovative combination, multimedia source redundancy could be accurately extracted by the hidden Markov estimation without any a priori information about the source. Moreover, the interleaver that is usually used to separate the source coding and channel coding can be avoided by exploiting the randomizing property of the LDPC codes. Furthermore, the channel decoding procedure may be implemented in parallel, resulting in good performance with a fairly low decoding complexity and delay. Simulation results have shown that the proposed scheme can achieve much better performance than the standard coding scheme over the binary input additive white Gaussian noise (BIAWGN) channels. Copyright © 2002 John Wiley & Sons, Ltd.

A new connected component based segmentation algorithm which automatically extracts text regions from natural scene images is proposed in this paper. This approach utilizes a multichannel decomposition method to locate text blocks in complex backgrounds. Block alignment analysis and recognition confidence values are used in the combination and identification of the connected components. The algorithm is applied to a test image database and shows promising results.

Based on the properties of cyclic codes, a new decoding algorithm for burst-error-correction is proposed in this paper. This algorithm can effectively correct burst errors with length that approaches to n-k for (n,k) Reed-Solomon (RS) codes. Moreover, due to the use of error locations correlation within a burst, divisions are exempted from the decoding process, achieving a fast decoding algorithm with much less computational complexity compared with existing algorithms. It is shown that the proposed algorithm can be widely used in wireless communications, wireless digital broadcast systems, and so on.

A new algorithm for segmenting handwritten Chinese character strings is presented. This approach is based on a split-and-merge strategy by locating possible ligatures between Chinese characters and merging the over-split components. The strategy is proposed by considering the structural properties of Chinese character strings. To guarantee the accuracy of the above segmentation algorithm, a recognizer is involved in order to aid the segmentation process. A maximum a posteriori probability index is derived for joint optimization of the segmentation and recognition results, and a dynamic programming algorithm-a modified level-building algorithm-is used to optimize this index. The whole algorithm is applied to a Chinese bank check amount recognition task, and some promising experimental results are obtained.

This paper presents a novel spatio-temporal modeling method for on-line handwritten Chinese character recognition. In this method, a statistical structure model (SSM) is used to describe the structural feature of Chinese characters from a probabilistic aspect, and an improved hidden Markov model (PCHMM) is employed to capture temporal information contained in ink. These two models are combined closely leading to a powerful spatio-temporal unified model (STUM), which has shown strong description ability and resulted in superior performance in the experiments where traditional models such as HMM (Hidden Markov Model) and ARG (Attributed Relational Graph) are also introduced and compared.

Studies the question of H-MLP (multilayer perceptron with hardlimiting activation function) network size selection for any two-class classification problem with finite samples. Based on a concept called classification complexity (CC). Meaningful theoretical results are given. An information like criterion and an algorithm are proposed for estimating the degree of CC. This estimation process presents a constructive method to construct network structure, size, and weights configuration in each layer.

This paper addresses a hybrid neural networks system, "TsingNeu-1", for large scale printed Chinese character recognition. The system, which consists of three-level structure of neural networks with feedback error control, is a well designed unbalanced hierarchical tree structure with its functional parts working in a cooperative way according to their functions. Feedback error control based on output evaluation has been adopted for improving robustness of the system. Recognition features of the Chinese characters are extracted automatically and adaptively by self-organizing learning in every stage of the recognition processes. The implemented system can recognize 3755 categories of Chinese characters and some common used punctuations with various fonts and sizes. Experimental results show that the whole system is of reasonable size, easy to train and satisfactory performance.

This paper investigates the application of TAF (trainable activation function) neural network to handwritten digit recognition. A three-layer feedforward TAF neural network is used as digits recognizer. Each TAF neuron in the hidden layer acts as a two-class classifier which distinguishes the two pattern classes from each other. The output layer gives output for decision making. While many approaches have bean suggested for this application the proposed method is new and has the advantage of small network size and good recognition performance. Experiments performed on selected digits from NIST database demonstrated that about 99% correct recognition rate has been achieved.

A new method to extract crossing line features for off-line handwritten Chinese character recognition is proposed in this paper. Firstly, the input pattern is nonlinearly normalized in order to compensate for shape variations. Secondly, the normalized pattern is separated into four subpatterns according to the four kinds of elementary strokes. Thirdly, the four subpatterns are uniformly divided into M/spl times/M cells respectively. In every cell, the crossing lines are counted. Then a 4M/sup 2/-dimensional feature vector is generated. An off-line handwritten Chinese character recognition system is built based on this feature. Our experiments have demonstrated the effectiveness of the method proposed in this paper.

A novel unconstrained numeral recognition system using an MFNN (multilayered feedforward neural net)-based multi-expert combination strategy is proposed. Taking advantage of every method's confidence value as well as its output label, this strategy can improve the system's performance significantly with as few as two experts. Another novel feature of the system is that the multi-expert combination problem is converted into a new classification problem, and then the MFNNs are used to handle the combination adaptively. The proposed system has achieved promising results on the NIST database.

The paper presents a novel method for online handwritten Chinese character recognition. In our method, each category of character is described by a fuzzy attributed relational graph (FARG). A relaxation algorithm is developed to match the input pattern with every FARG. For decision making, a similarity measure is established via statistical technique to calculate the matching degree between the input pattern and referenced FARG, according to which the recognition result is determined. The principle of our method makes it very robust against stroke connection and stroke order variation as well as stroke shape deformation. A database of 22530 samples collected from 6 subjects is used to test our recognition system which can recognize 3755 categories of Chinese characters. The result shows that our method is very effective: a top 1 recognition rate of 98.8% and a top 10 of 99.7% are reached.

This paper focuses on the realization of a bilingual Chinese-English OCR system. First, the Twice-Segment Algorithm is used for segmentation of documents with Chinese and English characters mixed. Then the comprehensive recognition method is employed to improve the robustness of Chinese character recognition. A new measurement of robustness of OCR recognition performance is also put forward here. Finally, exciting experimental results are given.

In this paper we present a form description method, in which frame lines are used to constitute a so-called frame template, which reflects the structure of a form either topologically or geometrically. Relevant item traversal algorithm is then proposed to locate and label form's items. We have also developed a robust and fast frame line detection method to make this form description practical for form recognition. Experimental results show our approach provides an effective way to convert printed forms into computerized format or collect information for database from printed forms.

Motion estimation and compensation are important tasks in image sequence coding. In this paper, we present a motion estimation scheme with multiresolution tree structure and hierarchical motion vector search. Experiments and analysis show that this scheme is not only computation efficient, but also robust. The multiresolution tree structure is further utilized in a variable block size image sequence coding scheme that incorporates the visual spatio-temporal characteristics. Both DCT and quadtree approaches are used to encode the motion compensated prediction error. Although the signal-to-noise ratio of the quadtree coded image is a little lower, the subjective quality around sharp edges is much better. Comparing our extensive simulation results with the MPEG-1 standard, we have obtained quite promising results.

This paper presents a method for vectorizing line-structured engineering drawings based on window features extraction. A line-structured engineering drawing is composed of straight lines and curves (they may have different widths) as well as their ends, corners, and crosses (we call them feature points). In the paper we use 2-dimension black-run-length to trace and separate different lines. We present feature point extracting criteria to detect feature point. When any feature point is detected a small rectangle window is opened around the feature point. After an adaptive window enlarge algorithm is applied, a proper size and position of the window which is named as Window Feature is obtained. In this way, we can see whether it is really a feature point (end, corner, cross) or just a noise. We define 40 window features and with these window features, we can process and vectorize all the complicated cross points in mechanical drawings. Finally we give some experimental samples about vectorizing mechanical drawings.

The constraint graph is introduced as a general character representation framework for recognizing multifont, multiple-size Chinese characters. Each character class is described by a constraint graph model. Sampling points on a character skeleton are taken as nodes in the graph. Connection constraints and position constraints are taken as arcs in the graph. For patterns of the same character class, the model captures both the topological invariance and the geometrical invariance in a general and uniform way. Character recognition is then formulated as a constraint-based optimization problem. A cooperative relaxation matching algorithm that solves this optimization problem is developed. A practical optical character recognition (OCR) system that is able to recognize multifont, multiple-size Chinese characters with a satisfactory performance was implemented.>