Return to search

Decomposition of Morphological Structuring Elements and Segmentation of Human Objects in Video Sequences

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.

Identiferoai:union.ndltd.org:NSYSU/oai:NSYSU:etd-0911107-223003
Date11 September 2007
CreatorsYang, Hsin-Tai
ContributorsChungnan Lee, Shie-Jue Lee, Tsung-Chuan Huang, Chih-Hung Wu, C. H. Hsieh, Shing-Tai Pan, Chih-Chin Lai
PublisherNSYSU
Source SetsNSYSU Electronic Thesis and Dissertation Archive
LanguageEnglish
Detected LanguageEnglish
Typetext
Formatapplication/pdf
Sourcehttp://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0911107-223003
Rightsnot_available, Copyright information available at source archive

Page generated in 0.0021 seconds