In this paper we investigate the retrieval of semantic events that occur in broadcast sports footage. We do so by considering the spatio-temporal behaviour of an object in the footage as being the embodiment of a particular semantic event. Broadcast snooker footage is used as an example of the sports footage for the purpose of this research.

This report investigates the use of three dierent schemes to optimize the number of states of linear left-to-right Hidden Markov Models (HMM). As the rst method we describe the xed length modeling scheme where each character model is assigned the same number of states. The second method considered is the Bakis length modeling where the number of model states is set to a given fraction of the average number of observations of the corresponding character. In the third length modeling scheme the number of model states is set to a speci ed quantile of the corresponding character length histogram. This method is called quantile length modeling. A comparison of the dierent length modeling schemes has been carried out with a handwriting recognition system using o-line images of cursively handwritten English words from the IAM database. For the xed length modeling a recognition rate of 61% has been achieved. Using Bakis or quantile length modeling the word recognition rates could be improved to over 69%.

Hidden Markov Models have many applications in signal processing and pattern recognition, but their convergence-based training algorithms are known to suffer from over-sensitivity to the initial random model choice. This paper describes the boundary between regions in which ensemble learning is superior to Rabiner’s multiple-sequence Baum-Welch training method, and proposes techniques for determining the best method in any arbitrary situation. It also studies the suitability of the training methods using the condition number, a recently proposed diagnostic tool for test-ing the quality of the model. A new method for training Hidden Markov Models Correspondence to:

Online handwriting recognition of Arabic script is a difficult problem since it is naturally both cursive and unconstrained. The analysis of Arabic script is further complicated in comparison to Latin script due to obligatory dots/stokes that are placed above or below most letters. This paper introduces a Hidden Markov Model (HMM) based system to provide solutions for most of the difficulties inherent in recognizing Arabic script including: letter connectivity, position-dependent letter shaping, and delayed strokes. This is the first HMM-based solution to online Arabic handwriting recognition. We report successful results for writerdependent and writer-independent word recognition.

Abstract—The last two decades witnessed some advances in the development of an Arabic character recognition (CR) system. Arabic CR faces technical problems not encountered in any other language that make Arabic CR systems achieve relatively low accuracy and retards establishing them as market products. We propose the basic stages towards a system that attacks the problem of recognizing online Arabic cursive handwriting. Rule-based methods are used to perform simultaneous segmentation and recognition of word portions in an unconstrained cursively handwritten document using dynamic programming. The output of these stages is in the form of a ranked list of the possible decisions. A new technique for text line separation is also used. Keywords—Arabic handwriting, character recognition, cursive handwriting, on-line recognition.

To my family and friends ii This thesis investigates semantic analysis of broadcast sports footage. A domain depen-dent sports video model is proposed. Under this model, the game semantics can be derived according to their relationship with the sequence of dynamic events that occur in the sport and the evolution of the spatio-temporal behaviour of a relevant object. Snooker and tennis are targeted as typical broadcast sports footage for the purpose of this research. The prob-lem focus is to automatically extract semantically meaningful events and to convey a useful representation to the user. Access to semantics provides a more natural tool for a user to query a corpus of data than by low-level content based features alone. These semantics are however open to various interpretations by different viewers. Therefore, in order to create a successful semantic based retrieval system it is necessary to consider the user-context. Unconstrained sports footage is generally very complicated in structure, so restricting the domain being addressed enables

This paper is dedicated to data driven design method for a hybrid ANN / HMM based handwriting recognition system. On one hand, a data driven designed neural modelling of handwriting primitives is proposed. ANNs are firstly used as state models in a HMM primitive divider that associates each signal frame with an ANN by minimizing the accumulated prediction error. Then, the neural modelling is realized by training each network on its own frame set. Organizing these two steps in an EM algorithm, precise primitive models are obtained. On the other hand, a data driven systematic method is proposed for HMM topology inference task. All possible prototypes of a pattern class are firstly merged into several clusters by a Tabu search aided clustering algorithm. Then a multiple parallel-path HMM is constructed for the pattern class. Experiments prove an 8 % recognition improvement with a saving of 50 % of system resources, compared to an intuitively designed referential ANN / HMM system. 1.

this document.) Data points are collected as a time sequenced (x,y) points sampled along the stylus' trajectory. The program gathers these points and attempts to fit one of the two types of geometric primitives: (1) A straight line segment, or (2) An arc segment of a circle. We refer to this process as `segmentation '. Figure 5 shows an example. The figure on the left corresponds to the unprocessed ink as obtained directly from the digitizing tablet. The figure on the right shows the resulting symbol after segmentation

In this paper we investigate the retrieval of dynamic events that occur in broadcast sports footage. Dynamic events in sports are important in so far as they are related to the game syntax. Thus far, the temporal interleaving of camera views has been used to infer these types of events. We propose the use of the spatio-temporal behaviour of an object in the footage as an embodiment of a semantic event. This is accomplished by modeling the evolution of the position of the object with a Hidden Markov Model (HMM). Snooker is used as an example for the purpose of this research. The system firstly parses the video sequence based on the geometry of the content in the camera view and classifies the footage as a particular view type. Secondly, we consider the relative position of the white ball on the snooker table over the duration of a clip to embody semantic events. A colour based particle filter is employed to robustly track the snooker balls. The temporal behaviour of the white ball is modeled using a HMM where each model is representative of a particular semantic episode. Upon collision of the white ball with another coloured ball, a separate track is instantiated.

In this paper we discuss a data driven approach to select better phone model topologies, in particular to decide on the number of states for linear left-right continuous HMMs. The novel approach is based on a conditional probabilistic viterbi path estimation and operates on forward-backward trained multiple parallel-path HMMs consisting of two different topologies. We compare this conditional probabilistic viterbi path estimation with systematic, statistical and knowledge based designs of different monophone based continuous HMM topologies and evaluate them in a LVSRS system with speech data from the German Verbmobil corpus.