| Title | Generating Digital Signature using Facial Landmlark Detection |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Pradhan, Chittaranjan, Banerjee, Debanjan, Nandy, Nabarun, Biswas, Udita |
| Conference Name | 2019 International Conference on Communication and Signal Processing (ICCSP) |
| Date Published | apr |
| Keywords | Audio recognition, biometric encryption, biometric identification, CDNU Algorithm, compressed textual signature, confidential information, cryptography, data compression, database storage overhead, Databases, digital security, digital signature generation, digital signatures, Encryption, face recognition, Facial features, facial landmark detection, facial landmarks, facial recognition, feature extraction, Huffman coding, Image coding, image texture, Information security, Metrics, Optimization, pubcrawl, real-time optimized encryption procedure, resilience, Resiliency, Scalability, secure digital signature, security advisors, social networking (online), user account information database |
| Abstract | Information security has developed rapidly over the recent years with a key being the emergence of social media. To standardize this discipline, security of an individual becomes an urgent concern. In 2019, it is estimated that there will be over 2.5 billion social media users around the globe. Unfortunately, anonymous identity has become a major concern for the security advisors. Due to the technological advancements, the phishers are able to access the confidential information. To resolve these issues numerous solutions have been proposed, such as biometric identification, facial and audio recognition etc prior access to any highly secure forum on the web. Generating digital signatures is the recent trend being incorporated in the field of digital security. We have designed an algorithm that after generating 68 point facial landmark, converts the image to a highly compressed and secure digital signature. The proposed algorithm generates a unique signature for an individual which when stored in the user account information database will limit the creation of fake or multiple accounts. At the same time the algorithm reduces the database storage overhead as it stores the facial identity of an individual in the form of a compressed textual signature rather than the traditional method where the image file was being stored, occupying lesser amount of space and making it more efficient in terms of searching, fetching and manipulation. A unique new analysis of the features produced at intermediate layers has been applied. Here, we opt to use the normal and two opposites' angular measures of the triangle as the invariance. It simply acts as the real-time optimized encryption procedure to achieve the reliable security goals explained in detail in the later sections. |
| DOI | 10.1109/ICCSP.2019.8698089 |
| Citation Key | pradhan_generating_2019 |
Generating Digital Signature using Facial Landmlark Detection