Biometric Signature Recognization

Biometric Signature Recognization

• 1.
  Presented By Faimin khan(2140672) Zeenat Sayyed (1130643) Under the Guidance of Mr. Shrinidhi Gindi
• 2.
  Contents  Introduction  ProblemDefinition  Proposed Methodology  Conclusion and future work References
• 3.
  Introduction  Nowadays, personidentification (recognition) and verification is very important in security and resource access control.  Biometrics is the science of automatic recognition of individual depending on their physiological and behavioral attributes.  For centuries, handwritten signatures have been an integral part of validating business transaction contracts and agreements.  Among the different forms of biometric recognition systems such as fingerprint, iris, face, voice, palm etc., signature will be most widely used.
• 4.
  Signature Recognition  SignatureRecognition is the procedure of determining to whom a particular signature belongs to.  Depending on acquiring of signature images, there are two types of signature recognition systems:  Online Signature Recognition  Offline Signature Recognition
• 5.
  Problem Definition  SignatureRecognition is the procedure of determining to whom a particular signature belongs to. In this work, the global and grid features are combined and used to differentiate among the signature images. These combined features are given back, so that particular signature image is recognized.
• 6.
  Proposed Model Block Diagramof Signature Recognition
• 7.
  Image Acquisition : Collection of signatures from 50 persons on blank paper.  The collected signatures are scanned to get images in JPG format to create database.
• 8.
  Pre-Processing : Image pre-processingis a technique to enhance raw images received from cameras/sensors placed on satellites, space probes and aircrafts or pictures taken in normal day-to-day life for various applications. The techniques for preprocessing used are  RGB to Gray Scale Conversion  Binarization  Thinning  Bounding Box
• 9.
   RGB toGray-Scale Convertion  Binarization RGB Image Gray-Scale Image Gray-Scale Image Binarized Image
• 10.
   Thinning  BoundingBox Binarized Image Thinned Image Thinned Image Bounded Image
• 11.
  Feature Extraction Features arethe characters to be extracted from the processed image. It has used two feature techniques  Global Features  Grid Features
• 12.
  Global Features  Height:  Width :  Number of Black Pixels :  Centroid of the signature : Width Height
• 13.
  Grid Features  Thecropped image is divided into 9 rectangular segments i.e. (3 Χ 3) blocks. 3*3 Blocks of Grid Image
• 14.
  DWT(Discrete Wavelet Transform) DWT applied on 1st block. Each block contributes horizontal, vertical and diagonal components. 1st Block Horizontal Vertical Diagonal
• 15.
   After applyingDWT to all 9 blocks, each block is divided into horizontal, vertical and diagonal components. From each components two features mainly horizontal and vertical projection positions are extracted. Total 54 (9 x 3 x 2) features are extracted. Grid features extracted from each block are  Horizontal Projection Position  Vertical Projection Position
• 16.
  Algorithm for Trainingphase Description: Retrieval of a signature image from a database Input: Training sample images. Output: Construction of Back Propagation Neural Network. Begin Read the training samples images Step1: Pre-processing  Convert the image into gray scale image.  Convert the gray scale image into binary image.  Apply thinning process.  Apply bounding box.
• 17.
  Step 2: FeaturesExtracted. Step 3: Back propagation neural network training. end // end of proposed algorithm
• 18.
  Testing In testing, inputimage from testing set is selected and its features are extracted and given them to the trained model, the trained model classifies given sample and produces output as type of signature and corresponding pattern Classification accuracy= Number of recognized signatures Total number of testing signatures
• 19.
  Output Pattern forRecognition
• 20.
  Conclusion  The objectiveof signature recognition is to recognize the signer for the purpose of recognition.  It has been observed that the global and grid features extracted using discrete wavelet transform are found to be efficient for offline signature recognition.  It achieved the accuracy rate ranging from 93%-89% for enrollment of 10 to 50 persons.
• 21.
  References  Gulzar A.Khuwaja and Mohammad S. Laghari, World Academy of Science, Engineering and Technology , “Offline Handwritten Signature Recognition”, 2011  V A Bharadi, H B Kekre, “Off-Line Signature Recognition Systems”, 2010  Mohammed A. Abdala & Noor Ayad Yousif, “Offline Signature Recognition and Verification Based on Artificial Neural Network”, 2008
• 22.
  Thank You.