| Summary: | 碩士 === 國立臺北教育大學 === 資訊科學系碩士班 === 98 === Because the advance of the technology and fast development of economy, the personal wealth and security privacy have become important issues. People use key and password for security in general, but these kinds of tool are inconvenient to carry and maybe have the problem of forgetfulness and loss. Therefore, the personal identification with the biological characteristics is researched by professionals.
The scholars employ voiceprint, palm print, facial, iris…etc to check characteristic of personal in the biological characteristics. Nevertheless, the Facial recognition can not conform to 「invariant」 because people may change their physique. Then the Iris recognition need to compute formula of complexity, and need large 「Hardware resources」, Consequently the Iris recognition was usually used in the Government departments. The 「cost」 and 「Equipment size」are important factors to the application of entrance or internet on general conditions, therefore scholars usually employ voiceprint and palm print to check characteristic of personal.
In the system of automated fingerprint identification, the fingerprint image can influence the discriminating result, so it must eliminate background in non-fingerprint area and doubt characteristic, enhance image identification, thinning…etc on first-step. The purpose of thesis is to propose the ways to strengthen the fingerprint identification on first-step, and then reinforce the execution speed of automated fingerprint identification system.
|
|---|
