iris ppt for machine laernig and voting.pptx

iris based voting

1. MACHINE LEARNING BASED IRIS RECOGNITION MODERN VOTING SYSTEM

2. ABSTRACT A Project ballot or an Electronic Voting Machine (EVM) based on Direct Response Electronic (DRE) or Identical Ballot Boxes have traditionally been used for voting. This study recommends a digital voting system based on Machine Learning algorithm that uses Iris recognition to address the flaws in the current voting process in order to fix the traditional voting system's flaws . A program called the Iris recognition-based Voting System identifies people based on the iris pattern of their eyes. Iris recognition is an automated biometric identification technology that analyses video evidence of one or both of an individual's iris to identify complex patterns that are distinct, stable, and visible from a distance. A voter may only cast one ballot, where the proposed technology prohibits multiple votes from the same person because it can spot duplicate entries. Additionally , this technique does away with the need for the user to carry a voter ID that has the relevant information since the Aadhar is incorporated with the voter ID thus enhancing the digitalization by means of digital verification of biometric and iris pattern available in Aadhar card of every user. At the voting venue, a simple iris scan will allow the voter's iris to be collected and used as identification . The iris recognition process consists of the following four steps: image acquisition, iris segmentation, feature extraction, and pattern matching. Iris recognition is one of the most trustworthy biometric modalities due to its high identification rate. Thereby this system eliminates the major drawbacks of traditional voting systems and enhances the digital voting by incorporating the modern transformation.

3. Introduction The biometric process has been mainly used to recognize individual types of physical aspects and features. For this purpose, a tremendous amount of acknowledgement technologies have been generally provided with the actual fingerprint, iris procedures and voice acknowledgement. The biometric mainly deals with the proper technical and technological fields for the body controls and body dimensions. The authentication system is based on the appropriate biometric security system that has increased the actual importance within all countries. The used system has been shown the proper valid and best impressive performance based on all these procedures and aspects. For this purpose, the fingerprint is the only procedure for providing the proper security techniques to provide the true uniqueness and the strong privacy properties of the entire system. The exceptional fingerprint assurance or the proper kind of imprint approval has been mainly insinuating the automated methods and procedures to ensure similarity between the two people fingerprints. The entire chapter has been generally provided with the actual purpose of the fundamental research that is overall dependent on the research objectives and respective research questions. In this chapter, the research framework of the entire study has also been provided. The fundamental research has described all the factors that are responsible for this recognition process

4. Problem statement There are various types of problems and significant issues that have been mainly faced by the biometric security system. The central and foremost issue is the biometric authentication process , and technologies have been mainly raised in the various types of privacy concerns and security concerns ( Hamd & Ahmed, 2018). During the processing time of the biometric data, there is no other option to undo or retrieve the respective information from the damage. For the case of the compromised passwords, anyone can modify it with fingerprint, iris scanner and the ear image effects. So for all these aspects, the simple working performance of the biometrics remains within the security risks and privacy risks. There are various types of problems that have been shown in the different slides of the iris recognition system , such as the sensor module, preprocessor module and feature extraction process. All these security and privacy issues can be adequately solved by the appropriate types of technologies and modern and advanced techniques. The security process should also be secured with the help of a strong password and robust system process.

5. Motivation For this purpose, several types of publications have been mainly documented with respect to the high accuracy states and the excellent reliability of the neural networks like the multilayer perceptions (MLP). This is mainly provided between the present times patterned recognition and accurate classifier applications. This research study there mainly used the particular machine learning technique "convolution neural network (CNN)" for improving the privacy security process within the validation system. The input image is mainly needed for reducing the size of the processed data and to achieve satisfactory working performance ( Herbadji et al . 2020). The respective working performance has been done within several image processing states like image enlargement, image partitioning and factor extraction.

6. Research Objectives With respect to the presented research aims, there have been mainly proposed the correct numbers of research objectives. All these research objectives have been mainly presented as the best outline of the fundamental research. All the research objectives are presented below. To represent the proper enhancement of the entire validation system with respect to the appropriate security tools. To elaborate the actual uniqueness, good reliability and the appropriate validity of the "iris biometric validation system" that is mainly used for the identification of the human ID. To enhance the various processes with the excess security aspects and factors for strengthening the private networks within the system. To analyze all types of validating security processes from the various research notes to highlight the most necessary and sufficient categories.  

7. Literature Survey "Smart Voting" is used to identify people who are trying to vote a second time, and once the fingerprint print And iris are scanned, authentication is complete, and the user is locked into login.[1]. Face detection, which is the major part of this project is done by using the Haar Cascade method. It is a machine learning object detection algorithm used to identify objects in an image or video[2]. The process of election data is recorded, stored and preceded as digital information. Electronic voting system is used to fling vote as well as counting number of votes. The electronic voting system uses AVISPA technique[3] Canny Edge detection algorithm for localizing the iris and pupils.[4]. Iris recognition system consists of five stages, such as, image acquisition, segmentation, normalization, feature extraction and matching.[5]. In security of voting system by bringing advanced technologies of neural networks with multimodal biometrics (face recognition, fingerprint scan, retina scan etc ).[6] Iris recognition refers to the automated method of verifying a match between two human IRIS. Iris scanner Capture the iris image and compare or match to database.[7]. RFID tags have been used. Each and every tag contains the information related to individual voters[8]. The voter identity card is replaced by smart card in which all the detail of the person is updated. Only the specified person can poll using their smart card[9]. The incorporation of biometric technologies can be as simple as using a single biometric. However, a single biometric measure is always subject to security breaches, if not properly attended and administered

8. . Existing System India being a democracy that too world’s largest, still conducts its elections using either Secret Ballet Voting or Electronic Voting Machines (EVM) both of which involves high costs, manual labor and are inefficient. So, the system must be optimized to be made efficient which would not leave room for unwanted means of voting. The most familiar issue faced by the election commission is inappropriate confirmation with respect to the arrangement of casting the votes, duplication or illegal casting of votes

9. Disadvantages of Existing System: Easy to Create a fake finger print Fake EVMs

10. Proposed System Proposed voting method, we use a biometric system that uses multiple sources of biometric behavior. This can be done by combining multiple features of an individual or multiple bio-extraction and matching algorithms running on the same biometrics. This system improves the accuracy of matching the data for the biometric system in the voting process. Since there is no way for any candidate to provoke government-issued biometric records before the election process, we use iris recognition and fingerprint scanning for accuracy and reasonable voting result. Many types of layers are applied in the "convolution neural network (CNN)" for the purpose of the "multimodal biometric human authentication" process. The authentication process mainly has been done with respect to the face, veins, iris scanner, fingerprints and palm for increasing the robustness and visibility of the entire recognition system. The entire recognition process is very much tricky for hacking and copying.

11. Advantages of Proposed System: 1. Best quality 2. Human IRIS 3. Advanced Voting Mechanism

12. Hardware and Software Requirements System : Pentium IV 2.4 GHz. Hard Disk : 40 GB. Floppy Drive : 1.44 Mb. Monitor : 14’ Colour Monitor. Mouse : Optical Mouse. Ram : 512 Mb. Software Requirements Operating system : Windows 7 Ultimate. Coding Language : Python. Front-End : Python.  

13. System Architecture T he algorithm starts with image normalization based on Daugman’s rubber sheet model [17]. This method uses information about centers and radiuses of iris and pupil. This solution was used because it can guarantee presentation clarity as well as it was much easier to work on transformed sample rather than the original iris sample. It is connected with the fact that it was much easier to analyze such samples. Before we will be ready to obtain all significant information and create sufficient feature vector, preprocessing algorithms have to be applied in the normalized image. All these actions are required because iris sample is not adapted to easily extract the most important features. At the beginning of the preprocessing stage, we used histogram equalization. After this operation, we obtained the image in which the most significant iris points have been strengthened. (It is connected with the fact that the proposed operation can highlight the most important parts of the processed image.) This step allowed to observe them even by human eye. The images after normalization and after histogram equalization are presented .

14. Convolution Neural Network technique (CNN) The "convolution neural network (CNN)" is a specific type of deep learning-based algorithm. This algorithm has been taken as an appropriate input image, an important attribute that is learnable weights with respect to the proper biasing system to the different types of objects. For this purpose, this particular system is very much effective to show the actual difference in the working process in each case.

15. Use Case Diagram

16. Sequence Diagram

17. State diagram:

18. Modules Description System administrator The system administrator registers the voters by simply filling a registration form to register the voters. User iris detection iris recognition is the process o recognizing a person by analyzing the random pattern of the iris. A person is identified by the iris which is the part of the eye using pattern matching or image processing. user verification iris verification verifies the identity of a person while iris identification establishes the identity of the person. User approval the system confirms the voter to be the eligible individual to vote by checking his/her aadhar details. Once confirmed the voter will be allowed to cast the vote. Convolutional  Neural Network (CNN) : A Convolutional Neural Network (CNN) is a type of deep learning algorithm that is particularly well-suited for image recognition and processing tasks. It is made up of multiple layers, including convolutional layers, pooling layers, and fully connected layers. The convolutional layers are the key component of a CNN, where filters are applied to the input image to extract features such as edges, textures, and shapes. The output of the convolutional layers is then passed through pooling layers, which are used to down-sample the feature maps, reducing the spatial dimensions while retaining the most important information. The output of the pooling layers is then passed through one or more fully connected layers, which are used to make a prediction or classify the image.

19. Dataset Description In this project author is divided the project into two parts and in first part he gave brief literature on technologies which can be used to improve vineyard growth and in second part he describe ‘IRIS-ML Database’ which can be used to train various machine learning algorithms such as SVM, KNN, Logistic Regression and many more. Once we trained model on ML algorithms then that trained model can be used to predict grape growth, harvest time and phenology (development cycle) type on new test images. In given database author has given five different types of dataset which describe below Dataset 1: This dataset can be used to train ML algorithms and this trained model can be used to predict harvest time Dataset 2: This dataset cab used to train ML algorithms which can be used to predict growth Dataset 3: This can be used to predict phenology stage. Dataset 4 and 5 can be used to predict maturity.

20. TEST CASES: S.no Test Case Excepted Result Result 1 Upload the dataset Dataset uploaded successfully pass 2 Generate CNN model CNN model Generated successfully pass 3 Load CNN model CNN model Loaded successfully pass 4 Generate loss and Accuracy graph loss and Accuracy graph Generated successfully pass 5 Upload Test image Test images uploaded successfully pass 6 Recognize image image Recognize successfully pass 7 Recognize iris through image iris Recognized through image successfully pass

21. Conclusion and Feature Enhancement We have presented a learning-based convolutional network, U-Net for iris segmentation. This CNN-based segmentation model has proven to be very successful with lower segmentation error and outperformed most of the state-of-the-arts. The proposed model does not require a great amount of training data like other deep learning network and works well without the use of data augmentation during training. The proposed method provides an end-to-end automation solution for iris segmentation without going through complicated hand-crafted image processing steps for iris detection, localization and segmentation. We will conduct more experiments to optimize its performance and evaluate its effect on iris recognition. This proposed project has presented an iris recognition system, in which segmentation was done using convolution neural network (CNN) algorithm. The database needs to be updated every year or before election so that new eligible citizens may be enrolled and those who are dead are removed from the voter list. In this proposed project, the Security of the voter is discussed and in general and the focus is on making the voting system more robust and reliable by eliminating dummy voters.

22. References [ 1] Aman Jatain , Yojna Arora, Jitendra Prasad, Sachin Yadav, Konark Shivam,Department of Computer Science, Amity University, Gurgaon, Haryana,Design and Development of Biometric Enabled Advanced Voting System May 2020. [2] Chandra Keerthi Pothina , Atla Indu Reddy, Ravikumar CV,Electronics and Communication Engineering, Vellore Institute of Technology, Vellore,Smart Voting System using Facial Detection April 2020. [3] Jayapriya J, Roghini M, Jayanthi S,Department of CSE, Agni College of Technology, Tamil Nadu, India, A Survey on Biometric Voting System using Iris Recognition Mar 2020. [4] Kennedy Okokpujie , Samuel Ndueso John, Etinosa NomaOsaghae,Charles Ndujiuba , Department of Electrical and Information Engineering,Covenant University, Ota, Ogun State, Nigeria, An Enhanced Voters Registration And Authentication Application Using Iris Recognition Technology February 2019.

23. Thank You