With the rapid development of image processing techniques, many unprecedented applications are emerging from all kinds of science branches, such as medicine, meteorology, astronomy, industrial control, etc. This dissertation presents an achievement of our research work related to the image processing field. Technically, the work consists of two parts. The first part concerns decomposition of morphological structuring elements while the second part explores the problems of human object segmentation in video/image data. In the first part, an integrated method, aiming to decompose a morphological structuring element into dilations of smaller ones, is proposed. By first formulating the decomposition problem into a set of linear constraints, the integer linear programming echnique is then applied to obtain an optimal decomposition. Compared to other existing approaches, the proposed method is more general and has several advantages. Firstly, it provides a systematic way of decomposing arbitrarily shaped structuring elements. Secondly, for convex images, factors can be of any size, not restricted to 3x3. Thirdly, the candidate set can be freely assigned by the user and finally the criteria of optimality can be flexible. In the second part, we present a three-stage system for segmentation of multiple human objects in a video stream. In the first stage, for a base frame to be segmented, we propose a hybrid self-clustering technique that incorporates the spatial concept as well as color attributes to reduce the number of small segments. In the second stage, the face shape modeled by the eight-directional convex polygons and the face features including two eyes and a mouth are extracted, parameterized, and fed to a trained neural network for detection of a human face. In the last stage, the size and orientation of the detected face region as well as the motion information among frames are used to roughly detect the corresponding body. To locate human objects more accurately, another neural network is constructed for recognizing the ambiguous regions.

Neuro-fuzzy modeling is an efficient computing paradigm for system modeling problems. It mainly integrates two well-known approaches, neural networks and fuzzy systems, and therefore possesses advantages of them, i.e., learning capability, robustness, human-like reasoning, and high understandability. Up to now, many approaches have been proposed for neuro-fuzzy modeling. However, it still exists many problems need to be solved. We propose in this thesis two self-constructing rule generation methods, i.e., similarity-based rule generation (SRG) and similarity-and-merge-based rule generation (SMRG), and one hybrid learning algorithm (HLA) for structure identification and parameter identification, respectively, of neuro-fuzzy modeling. SRG and SMRG group the input-output training data into a set of fuzzy clusters incrementally based on similarity tests on the input and output spaces. Membership functions associated with each cluster are defined according to statistical means and deviations of the data points included in the cluster. Additionally, SMRG employs a merging mechanism to merge similar clusters dynamically. Then a zero-order or first-order TSK-type fuzzy IF-THEN rule is extracted from each cluster to form an initial fuzzy rule-base which can be directly employed for fuzzy reasoning or be further refined in the next phase of parameter identification. Compared with other methods, both our SRG and SMRG have advantages of generating fuzzy rules quickly, matching membership functions closely with the real distribution of the training data points, and avoiding the generation of the whole set of clusters from the scratch when new training data are considered. Besides, SMRG supports a more reasonable and quick mechanism for cluster merging to alleviate the problems of data-input-order bias and redundant clusters, which are encountered in SRG and other incremental clustering approaches. To refine the fuzzy rules obtained in the structure identification phase, a zero-order or first-order TSK-type fuzzy neural network is constructed accordingly in the parameter identification phase. Then, we develop a HLA composed by a recursive SVD-based least squares estimator and the gradient descent method to train the network. Our HLA has the advantage of alleviating the local minimal problem. Besides, it learns faster, consumes less memory, and produces lower approximation errors than other methods. To verify the practicability of our approaches, we apply them to the applications of function approximation and classification. For function approximation, we apply our approaches to model several nonlinear functions and real cases from measured input-output datasets. For classification, our approaches are applied to a problem of human object segmentation. A fuzzy self-clustering algorithm is used to divide the base frame of a video stream into a set of segments which are then categorized as foreground or background based on a combination of multiple criteria. Then, human objects in the base frame and the remaining frames of the video stream are precisely located by a fuzzy neural network which is constructed with the fuzzy rules previously obtained and is trained by our proposed HLA. Experimental results show that our approaches can improve the accuracy of human object identification in video streams and work well even when the human object presents no significant motion in an image sequence.