Browsing by Author "Bhilare, Shruti"

Now showing items 1-6 of 6

    • Cross-domain Person Re-identification 

      Shah, Raj H. (Dhirubhai Ambani Institute of Information and Communication Technology, 2022)
      The problem of person reidentification has been getting much attention in the computer vision community. The task is to recognize pictures of the same indi� viduals in images with different backgrounds taken from ...

    • English Handwritten Word Recognition 

      Shah, Vidit (2021)
      Today, tons of data is being generated every day and this helps with the automation of several tasks. Automated recognition of handwritten words from images is one such challenging task. This can be done by extracting the ...

    • Generating Targeted Adversarial Attacks and Assessing their Effectiveness in Fooling Deep Neural Networks 

      Gajjar, Shivangi Bharatbhai (Dhirubhai Ambani Institute of Information and Communication Technology, 2022)
      Deep neural network (DNN) models have gained popularity for most image classification problems. However, DNNs also have numerous vulnerable areas. These vulnerabilities can be exploited by an adversary to execute a successful ...

    • Increasing Transferability by Imposing Linearity and Perturbation in Intermediate Layer with Diverse Input Patterns 

      Shah, Meet Ashvinkumar (Dhirubhai Ambani Institute of Information and Communication Technology, 2022)
      Despite high prediction accuracy, deep neural networks are vulnerable to adversarial attacks, introduced by perturbations that humans may not even perceive. Hence, adversarial examples can mislead the trained networks. As ...

    • Investigating Robustness of Face Recognition System against Adversarial Attacks 

      Sarvaiya, Maulik Karshanbhai (Dhirubhai Ambani Institute of Information and Communication Technology, 2023)
      Facial Recognition (FR) systems based on deep neural networks (DNNs) are widelyused in critical applications such as surveillance and access control necessitat-ing their reliable working. Recent research has highlighted ...

    • Presentation Attack Detection in Face Recognition System 

      Sherasia, Kehkasha (2021)
      One of the quickest, most precise and easily available biometric recognition system is Face recognition. These systems have wide range of uses like phone verification, payment method security checks, border control and ...