Ranking Criteria of Enterprise Information Security Architecture Using Fuzzy Topsis

摘要

It is very simple and easier to recapture a high quality images from LCD screens with the development ofmultimedia technology and digital devices. In authentication, the use of such recaptured images can bevery dangerous. So, it is very important to recognize the recaptured images in order to increaseauthenticity. Even though, there are a number of features that have been proposed in various state-of-theartvisual recognition tasks, but it is still difficult to decide which feature or combination of features havemore significant impact on this task. In this paper an image recapture detection method based on set ofphysical based features including texture, HSV colour and blurriness is proposed. Also, this paperevaluates the performance of different distinctive featuresin the context of recognition of recapturedimages. Several experimental setups have been conducted in order to demonstrate the performance of theproposed method. In all these experimental results, the proposed method is efficient with good recognitionrate. Among the combination of low-level features, CS-LBP detection is to operator which is used to extractthe texture feature is the most robust feature.