The Research Of Characteristic Extraction Method For 2-D Skull Based On CT Image

With the emergence of biological recognition technology, the identification technology depending on biometric such as human face fingerprint iris are growing maturity, and applied broadly on access system security system and other occasion needing identity witnesses. In the identification process, a variety of biologic characteristic combining for purpose of identification is often required, normally single biometric identification accuracy is difficult to achieve authentication requirements. Therefore, multimode biometric authentication integration is the goal of many researchers to trace. It is significant for the biologic identification to exploit new basis. The main target of this research is skull, which characteristic will be extracted as a basis for the identification of different individuals, For the purpose of this we have a in-depth study for a number of key technologies and major algorithms in identification process, the main work includes the following:(1) On the basis of analysis and review in the relevant research and latest research result and progress, this paper has sum up the purpose and signification of skull study, the results of the analysis show, the research of skull is known in medical field, it is few taken as identification target.(2) The border shape of skull is taken as identification target, extract characteristic depend on different algorithms, analyze and compare the result of different experiments.(3) By using gray projection methods for positioning, the result of positioning is applied to template matching algorithm of skull identification, through extensive experiments some accurate positioning point can be found at projection curve.(4) Orthogonal function will be introduced in the skull identification; the article details the three orthogonal rule, make it possess the property of pattern recognition by its standardization transformation, and used it in the extraction of features of region.(5) It introduced the principles of equal difference function algorithm, and some other equal difference function derived from which on this basis, features of skull boundary and region are extracted by using those different descriptor, then based on experiment results the respective advantages and disadvantages are analyzed.In the identification process, we focus on the research of identification algorithm, on the...