A Study on Fingerprint Hash Code Generation Using Euclidean Distance for Identifying a User

Biometrics innovation has ended up being a precise and proficient response to the security issue. Biometrics is a developing field of research as of late and has been dedicated to the distinguishing proof or authentication of people utilizing one or multiple inherent physical or behavioural characteristics. The unique fingerprint traits of a man are exceptionally exact and are special to a person. Authentication frameworks in light of unique fingerprints have demonstrated to create low false acceptance rate and false rejection rate, alongside other favourable circumstances like simple and easy usage strategy. But the modern study reveals that fingerprint is not so secured like secured passwords which consist of alphanumeric characters, number and special characters. Fingerprints are left at crime places, on materials or at the door which is usually class of latent fingerprints. We cannot keep fingerprint as secure like rigid passwords. In this paper, we discuss fingerprint image Hash code generation based on the Euclidean distance calculated on the binary image. Euclidean distance on a binary image is the distance from every pixel to the nearest neighbour pixel which is having bit value one. Hashcode alone not sufficient for Verification or Authentication purpose, but can work along with Multifactor security model or it is half secured. To implement Hash code generation we use MATLAB2015a. This study shows how fingerprints Hash code uniquely identifies a user or acts as index-key or identity-key.

Seleksi Citra Berdasarkan Ciri dengan Algoritma Threshold Mengunakan Fuzzy Kurva S dan Fungsi Min

Image retrieval process of fruits and flowers with CBIR concept was represented by the colors and shapes using adaptive histogram method for color, and invariant moment for shape. To measure the similarity between the query image and the basis data image Euclidean distance function was used, where the result is f(x). Calculations for f (y) through the process of ‘fuzzy-ing’-S curve, where the value of f(x) guides the sigmoid function. The value f(y) on each image than the threshold value based image query. Basically, the algorithm displays the image based on Threshold features, by comparing the threshold value with the value f(y). A high grade value (approaching 1) indicates that the feature of the sample (query) image is similar to the basis data image, and vice versa. The process was continued by comparing the value grades of the image representation of color and form using min operator in fuzzy logic, so that it only displayed several images that have some resemblances in accordance with the original image. The advantage of threshold algorithm and the fuzzy function - compared to other methods – lies in the simplicity method in the image retrieval, so that the performance of CBIR becomes more reliable and effective.