Texture analysis of iris biometrics based on adaptive size neighborhood entropy and linear discriminant analysis
Апстракт
Novel method for personal identification, based on adaptive size neighborhood entropy of iris images, was proposed. Through the process of segmentation, iris was extracted from other regions of the human eye, geometrically transformed and normalized. Entropy calculations performed for different neighborhood sizes allows simultaneous distinguishing of fine and global iris texture. Described method also allows recognition of images which contain artifacts and their removal from further analysis after application of principal component analysis (PCA). In the last analytical step, linear discriminant analysis (LDA) with training vector set was applied, allowing rigorous classification. Described procedure is suitable for the application in security systems with small number of authorized persons and a high degree of safety.
Кључне речи:
biometric basedИзвор:
Sinteza 2014 - Impact of the Internet on Business Activities in Serbia and Worldwide, 2014Издавач:
- Univerzitet Singidunum, Beograd
Институција/група
Institut za multidisciplinarna istraživanjaTY - CONF AU - Adamović, Saša AU - Savić, Aleksandar AU - Milosavljević, Milan AU - Spasić, Slađana PY - 2014 UR - http://rimsi.imsi.bg.ac.rs/handle/123456789/2389 AB - Novel method for personal identification, based on adaptive size neighborhood entropy of iris images, was proposed. Through the process of segmentation, iris was extracted from other regions of the human eye, geometrically transformed and normalized. Entropy calculations performed for different neighborhood sizes allows simultaneous distinguishing of fine and global iris texture. Described method also allows recognition of images which contain artifacts and their removal from further analysis after application of principal component analysis (PCA). In the last analytical step, linear discriminant analysis (LDA) with training vector set was applied, allowing rigorous classification. Described procedure is suitable for the application in security systems with small number of authorized persons and a high degree of safety. PB - Univerzitet Singidunum, Beograd C3 - Sinteza 2014 - Impact of the Internet on Business Activities in Serbia and Worldwide T1 - Texture analysis of iris biometrics based on adaptive size neighborhood entropy and linear discriminant analysis DO - 10.15308/sinteza-2014-658-660 ER -
@conference{ author = "Adamović, Saša and Savić, Aleksandar and Milosavljević, Milan and Spasić, Slađana", year = "2014", abstract = "Novel method for personal identification, based on adaptive size neighborhood entropy of iris images, was proposed. Through the process of segmentation, iris was extracted from other regions of the human eye, geometrically transformed and normalized. Entropy calculations performed for different neighborhood sizes allows simultaneous distinguishing of fine and global iris texture. Described method also allows recognition of images which contain artifacts and their removal from further analysis after application of principal component analysis (PCA). In the last analytical step, linear discriminant analysis (LDA) with training vector set was applied, allowing rigorous classification. Described procedure is suitable for the application in security systems with small number of authorized persons and a high degree of safety.", publisher = "Univerzitet Singidunum, Beograd", journal = "Sinteza 2014 - Impact of the Internet on Business Activities in Serbia and Worldwide", title = "Texture analysis of iris biometrics based on adaptive size neighborhood entropy and linear discriminant analysis", doi = "10.15308/sinteza-2014-658-660" }
Adamović, S., Savić, A., Milosavljević, M.,& Spasić, S.. (2014). Texture analysis of iris biometrics based on adaptive size neighborhood entropy and linear discriminant analysis. in Sinteza 2014 - Impact of the Internet on Business Activities in Serbia and Worldwide Univerzitet Singidunum, Beograd.. https://doi.org/10.15308/sinteza-2014-658-660
Adamović S, Savić A, Milosavljević M, Spasić S. Texture analysis of iris biometrics based on adaptive size neighborhood entropy and linear discriminant analysis. in Sinteza 2014 - Impact of the Internet on Business Activities in Serbia and Worldwide. 2014;. doi:10.15308/sinteza-2014-658-660 .
Adamović, Saša, Savić, Aleksandar, Milosavljević, Milan, Spasić, Slađana, "Texture analysis of iris biometrics based on adaptive size neighborhood entropy and linear discriminant analysis" in Sinteza 2014 - Impact of the Internet on Business Activities in Serbia and Worldwide (2014), https://doi.org/10.15308/sinteza-2014-658-660 . .