A Survey of Computer Vision-Based Human Motion Capture

Recent developments in human motion analysis

A general and efficient design approach using a radial basis function (RBF) neural classifier to cope with small training sets of high dimension, which is a problem frequently encountered in face recognition, is presented. In order to avoid overfitting and reduce the computational burden, face features are first extracted by the principal component analysis (PCA) method. Then, the resulting features are further processed by the Fisher's linear discriminant (FLD) technique to acquire lower-dimensional discriminant patterns. A novel paradigm is proposed whereby data information is encapsulated in determining the structure and initial parameters of the RBF neural classifier before learning takes place. A hybrid learning algorithm is used to train the RBF neural networks so that the dimension of the search space is drastically reduced in the gradient paradigm. Simulation results conducted on the ORL database show that the system achieves excellent performance both in terms of error rates of classification and learning efficiency.

/pdf/face-recognition-with-radial-basis-function-rbf-neural-17p2mq3yfx.pdf

Face recognition with radial basis function (RBF) neural networks

An accurate and robust face recognition system was developed and tested. This system exploits the feature extraction capabilities of the discrete cosine transform (DCT) and invokes certain normalization techniques that increase its robustness to variations in facial geometry and illumination. The method was tested on a variety of available face databases, including one collected at McGill University. The system was shown to perform very well when compared to other approaches.

/pdf/face-recognition-using-the-discrete-cosine-transform-3kglttkuvl.pdf

Face Recognition Using the Discrete Cosine Transform

Online handwriting recognition is gaining renewed interest owing to the increase of pen computing applications and new pen input devices. The recognition of Chinese characters is different from western handwriting recognition and poses a special challenge. To provide an overview of the technical status and inspire future research, this paper reviews the advances in online Chinese character recognition (OLCCR), with emphasis on the research works from the 1990s. Compared to the research in the 1980s, the research efforts in the 1990s aimed to further relax the constraints of handwriting, namely, the adherence to standard stroke orders and stroke numbers and the restriction of recognition to isolated characters only. The target of recognition has shifted from regular script to fluent script in order to better meet the requirements of practical applications. The research works are reviewed in terms of pattern representation, character classification, learning/adaptation, and contextual processing. We compare important results and discuss possible directions of future research.

'Online recognition of Chinese characters: the state-of-the-art

Recognition of JPEG compressed face images based on statistical methods

This paper presents an advanced face recognition system that is based on the use of Pseudo 2-D HMMs and coefficients of the 2-D DCT as features. A major advantage of our approach is the fact that our face recognition system works directly with JPEG-compressed face images, i.e. it uses directly the DCT-features provided by the JPEG standard, without any necessity of completely decompressing the image before recognition. The recognition rates on the Olivetti Research Laboratory (ORL) face database are 100% for the original images and 99.5% for JPEG compressed domain recognition. A comparison with other face recognition systems evaluated on the ORL database, shows that these are the best recognition results on this database.

High quality face recognition in JPEG compressed images

A face recognition system based on 2-D DCT features and pseudo-2D Hidden Markov Models is presented. The system achieves a recognition rate of 99.5% on the Olivetti Research Laboratory (ORL) face database. This recognition rate is much better than the recognition rate of a previous pseudo 2-D HMM approach. Only one single face out of the 200 available test faces was not correctly recognized. The superiority of our approach against the previous approach is analyzed, and the recognition rates are compared to other face recognition systems evaluated on the ORL database.

High performance face recognition using pseudo 2-D hidden Markov models

This paper presents a novel approach to robust and flexible person tracking using an algorithm that combines two powerful stochastic modeling techniques: pseudo-2D hidden Markov models (P2DHMM) used for capturing the shape of a person within an image frame, and the well-known Kalman-filtering algorithm, that uses the output of the P2DHMM for tracking the person by estimation of a bounding box trajectory indicating the location of the person within the entire video sequence. Both algorithms cooperate together in an optimal way, and with this co-operative feedback, the proposed approach even makes the tracking of people possible in the presence of background motions caused by moving objects or by camera operations as, e.g., panning or zooming. Our results are confirmed by several tracking examples in real scenarios, shown at the end of the paper and provided on the Web server of our institute.

Person tracking in real-world scenarios using statistical methods

The paper describes the authors' image retrieval system, which enables the user to search a grey-scale image database intuitively by presenting simple sketches. The database contains 120 different isolated objects (mostly hand tools) with arbitrary orientation. Each of these images is represented by a hidden Markov model (HMM) which has been modified in order to obtain rotation and scale invariance. Thus, no labeling of the content or the relation angle of the object is needed when adding new images to the database. This is particularly important when using query by sketch due to the skew which occurs naturally in human handwriting and in drawings. The retrieved images can be ranked according to the similarity with the query sketch using the output probabilities of the HMMs. Furthermore, the use of HMMs allows efficient pruning and thus a fast retrieval even with large databases. Experiments with the demonstration system showed good retrieval results with several users.

Stefan Müller

Papers

Recognition of JPEG compressed face images based on statistical methods

High quality face recognition in JPEG compressed images

High performance face recognition using pseudo 2-D hidden Markov models

Person tracking in real-world scenarios using statistical methods

Image database retrieval of rotated objects by user sketch