DOC-BLOCK: A Blockchain Based Authentication System for Digital Documents

Aim:

         The main aim of this project is to solve the problem of counterfeiting certificates we are proposing an digital certificate system based on blockchain technology and to verify the traveler’s identity using live camera, which allows faster convergence and more generalizable representations.

Synopsis:

            Numerous activities in our daily life require us to verify who we are by showing our ID documents containing face images, such as passports and driver licenses, to human operators. However, this process is slow, labor intensive and unreliable. As such, an automated system for matching ID document photos to live face images (selfies) in real time and with high accuracy is required. In this paper, we propose DocBlock to meet this objective.

          We first show that gradient-based optimization methods converge slowly (due to the underfitting of classifier weights) when many classes have very few samples, a characteristic of existing ID-selfie datasets. To overcome this shortcoming, to update the classifier weights, which allows faster convergence and more generalizable representations. Next, a pair of sibling networks with partially shared parameters are trained to learn a unified face representation with domain-specific parameters. Cross-validation on an ID selfie dataset shows that while a publicly available general face matcher.

Existing System:

           In the existing system, Identity verification plays an important role in our daily lives. For example, access control, physical security and international border crossing require us to verify our access (security) level and our identities. to verify who we are by showing our ID documents containing face images, such as passports and driver licenses, to human operators.

           However, this process is slow, labor intensive and unreliable. As such, an automated system for matching ID document photos to live face images (selfies) in real time and with high accuracy is required. After verifying a traveler’s identity by face comparison, the gate is automatically opened for the traveler to enter. For IDselfie matching, they are comparing a scanned or digital document photo.

 Problem Statement:

• The problem of ID-selfie matching poses numerous challenges that are different from general face recognition. For typical unconstrained face recognition tasks, the main challenges are due to pose, illumination and expression (PIE) variations.
• The low quality of document photos due to image compression1 and (2) the large time gap between the document issue date and the verification date remain as the primary difficulties.

Proposed System:

            We are proposing a certificate system based on blockchain to overcome the problem. Data are stored in different nodes, and anyone who wishes to modify a particular internal datum must request that other nodes modify it simultaneously. Thus, the system is highly reliable.We developed a decentralized application and designed a certificate system based on blockchain. This technology was selected because it is incorruptible, encrypted, and trackable and permits data synchronization. By integrating the features of blockchain, the system improves the efficiency operations at each stage. The system saves on paper, cuts management costs, prevents document forgery, and provides accurate and reliable information on digital certificates and compare user live face with verified document face.

Advantage:

• Their proposed model covers multidimensional authentication for credit transfer using blockchain, smart contract, and hash function.
• We used the most effective SHA-256 algorithm. SHA-256 can covert large input data to a fixed size 256-bit (32-byte) hash code.