International Journal of Recent Development in Engineering and Technology Website: www.ijrdet.com (ISSN 2347-6435(Online) Volume 3, Issue 1, July 2014) 208 Fingerprint Recognition using Core Detection Technique Manisha Yadav 1 , Parveen Yadav 2 1 M. Tech Scholar, RPS, Mahendergarh, INDIA. 2 A.P. in CSE Dept, RPS, Mahendergarh, INDIA Abstract— a single biometric indicator used in biometric system that is uncomfortable with noisy data in user verification process. There are some kinds of restrictions on degree of freedom with some unacceptable error rates. With existing of these problems it’s very difficult for particular to improve the performance a biometric system. In biometric system finger recognition is very necessary process for safety and security purpose. In our thesis work we are going to improve performance of fingerprint recognition process using Core Detection Technique. Image of fingerprint is binarised in first step and apply thinning process to make it ready for further process of detection. There are many techniques available in market but as comparison on basis of result with the existing, core detection performs well. Core Detection Technique performs best at level for recognition of fingerprint in biometric system. Keywords— Fingerprint recognition, Minutiae, Core detection technique, Binarization. I. INTRODUCTION Fingerprint recognition or palm print identification is the process of comparing questioned and known friction skin ridge impressions from fingers or palms or even toes to determine if the impressions are from the same finger or palm. When friction between skin ridge is flexible then no two finger or palm prints are ever exactly alike (never identical in every detail). Fingerprint identification (also referred to as individualization) occurs when an expert (or an expert computer system operating under threshold scoring rules) determines that two friction ridge impressions originated from the same finger or palm (or toe, sole) to the exclusion of all others [2]. A known print is the intentional recording of the friction ridges, when ink of black printer rolled across a contrasting background of white color, as like a card of white color. Friction ridges can also be recorded digitally using a technique called Live-Scan. Latent prints are often fragmentary and may require any light source, or methods of chemical and powder, in order to be visualized. When friction ridges come in contact with a surface of any oil, grease or ink then transferred this on the item. There are numerous factors available that affect impressions of friction ridge, thereby requiring examiners to undergo extensive and objective study in order to be trained to competency. The development medium is just some of the various factors which can cause a latent print to appear differently from the known recording of the same friction ridges. Indeed, the conditions of friction ridge deposition are unique and never duplicated. Fingerprint images that are found or scanned are not of optimum quality. Their quality is improved by remove the noises. Some features are extracted by us like minutiae and matching. If the sets of minutiae are matched with those in the database, this is called that fingerprint is identified. After matching, post-matching steps are performed this may include showing details of identified candidate, marking attendance etc. A brief flowchart is shown in next section. In biometric system [1], fingerprints are considered as a best recognition system in world which gives response in very short time. Every person has unique so it is secured to use and do not change in lifetime of anyone. Except these, fingerprint recognition system implementation is cheap, easy and accurate up to satiability. Fingerprint recognition has been widely used in both forensic and civilian applications. Most proven technique is fingerprint that based on biometric system as compared to other techniques and has the largest market shares. Not only it is faster than other techniques but also the energy consumption by such systems is too less. II. WORK ALREADY DONE V. Vijaya Kumari and N. Suriyanarayanan [4] proposed a method which measure performance in fingerprint by detecting the edges of fingerprint images using five local operators namely Sobel, Roberts, Prewitt, Canny and LoG. Individual segments from image are extracted from the edge detected image. Raju Sonavane, and B.S. Sawant [5] presented a method for enhancement in fingerprint by using a special domain in which the fingerprint image is decomposed into a set of filtered images after that we estimated orientation field.