Visual Memory - Model to Visualise and Back u...

Visual Memory - Model to Visualise and Back up your Brain Visual Signals using Deep Learning and IoT

Author Name : R. Haripriya, P. Vishnu Sivapriya, S. Vinitha, S. Sinduja

ABSTRACT

Vision is one of the most important components in the human perception system.Memorability of an image is a characteristic determined by the human observers' ability to remember images they have seen. Visual memorability is a method to measure how easily media contents can be memorized. Compared to previous works, this project focus on predicting the visual memorability of images based on human biological feedback (i.e., EEG signals).This project, proposed a model that extract and exploited EEG signals to predict the memorability of images using Bi-LSTM deep learning-based classification models.During the visual memory task, EEG signals are recorded from subjects as human biological feedback. The collected EEG signals are then used to train deep learning classification models for prediction of image memorability.This tool that consists in a web application that allows the annotation of the visual memorability EEG associated to still images and apply Bi-LSTM deep convolutional neural network model for visual memorability prediction on Visualised Image.

However, in our framework the process of stylization is driven by a specific module which ensures that the generated images have increased memorability and, implicitly, that most of the high-level content of the original images is preserved.