Iris Feature Extraction Method Based on 1D Gabor Filter

The normalized iris image was divided into eight sub-bands, and every column of each sub-band was averaged by rows to generate eight 1D iris signals. Then the even symmetry item of 1D Gabor filter was used to describe local characteristic blocks in 1D iris signals, and the results were quantified by their polarities to generate iris codes. In order to estimate the performance of the presented method, an iris recognition platform was produced and the Hamming distance between two iris codes was computed to measure the dissimilarity of them. The experimental results in CASIA v1. 0 and Bath iris image databases show that the proposed iris feature extraction algorithm has a promising potential in iris recognition.

A Novel Location Method for Interline Power Flow Controllers Based on Entropy Theory

As one of the new generation flexible AC transmission systems(FACTS)devices,the interline power flow controller(IPFC)has the significant advantage of simultaneously regulating the power flow of multiple lines.Nevertheless,how to choose the appropriate location for the IPFC converters has not been discussed thoroughly.To solve this problem,this paper proposes a novel location method for IPFC using entropy theory.To clarify IPFC’s impact on system power flow,its operation mechanism and control strategies of different types of serial converters are discussed.Subsequently,to clarify the system power flow characteristic suitable for device location analysis,the entropy concept is introduced.In this process,the power flow distribution entropy index is used as an optimization index.Using this index as a foundation,the power flow transfer entropy index is also generated and proposed for the IPFC location determination study.Finally,electromechanical electromagnetic hybrid simulations based on ADPSS are implemented for validation.These are tested in a practical power grid with over 800 nodes.A modular multilevel converter(MMC)-based IPFC electromagnetic model is also established for precise verification.The results show that the proposed method can quickly and efficiently complete optimized IPFC location and support IPFC to determine an optimal adjustment in the N-1 fault cases.

An image segmentation based method for iris feature extraction

In this article, the local anomalistic blocks such as crypts, furrows, and so on in the iris are initially used directly as iris features. A novel image segmentation method based on intersecting cortical model （ICM） neural network was introduced to segment these anomalistic blocks. First, the normalized iris image was put into ICM neural network after enhancement. Second, the iris features were segmented out perfectly and were output in binary image type by the ICM neural network. Finally, the fourth output pulse image produced by ICM neural network was chosen as the iris code for the convenience of real time processing. To estimate the performance of the presented method, an iris recognition platform was produced and the Hamming Distance between two iris codes was computed to measure the dissimilarity between them. The experimental results in CASIA v1.0 and Bath iris image databases show that the proposed iris feature extraction algorithm has promising potential in iris recognition.