Faved! Biometrics: tell me which image you like and i’ll tell you who you are

FAVED! BIOMETRICS: TELL ME WHICH IMAGE YOU LIKE AND I’LL TELL YOU WHO YOU ARE

TO VIEW OUTPUT CLICK HERE!

ABSTRACT:

This paper builds upon the belief that every human being has a built-in image aesthetic evaluation system. This sort of personal aesthetics mostly follows certain aesthetic rules widely studied in image aesthetics (e.g., rules of thirds, colorfulness, etc.), though it likely contains some innate, unique preferences. This paper is a proof of concept of this intuition, presenting personal aesthetics as a novel behavioral biometrical trait. In our scenario, personal aesthetics activate when an individual is presented with a set of photos he may like or dislike. The goal is to distill and encode the uniqueness of his visual preferences into a compact template. To this aim, we extract a pool of low- and high-level state-of-the-art image features from a set of Flickr images preferred by a user, feeding them successively into a LASSO regressor. LASSO highlights the most discriminant cues for the individual, allowing authentication and recognition tasks. The results are surprising given only 1 image as test. We can match the user identity against a gallery of 200 individuals definitely much better than chance. Using 20 images (all preferred by a single user) as a biometrical trait, we reach an AUC of 96%, considering the cumulative matching characteristic curve. Extensive experiments also support the interpretability of our approach, effectively modeling what is the “what we like” that distinguishes us from others.

EXISTING SYSTEM:

Several biometrical traits have been designed, each analyzed from different perspectives like accuracy, efficiency, usability, acceptability, etc. From a very general point of view, they can be divided in two main classes:

• physical/physiological biometrical traits

• behavioral biometrical traits

Among the behavioral approaches, some – the so-called HCI-based behavioral biometrics -are based on the idea that every person has a unique way to interact with a personal computer: for example some methods successfully investigated the possibility of characterizing a person on the basis of keystrokes or mouse dynamics. In the same context, very recently some other approaches investigated the exploitation of Internet-based biometrical traits, like browsing histories or chatting. In this context, many CMA applications have been developed: from aesthetic photo ranking and preference aware view recommendation systems [29], to picture quality analysis.

DISADVANTAGES OF EXISTING SYSTEM:

·       It focuses only on the behavioral approaches does not consider the physiological approaches.

·       These technologies seem to forget the essential role that factors internal to the observer may have on preference.

·       It will not show the unique characteristics of the user against others.

PROPOSED SYSTEM:

This application makes a further step along this direction, and proposes a novel biometrical trait which exploits the “personal aesthetics” traits of people, i.e. those visual preferences that distinguish people from each other. Actually, it is known that people often get enjoyment from observing images and express preferences for some pictures over others. There is no scientifically comprehensive theory that explains what psychologically defines such preferences, even if some guidelines have been produced which suggest principles of general gratification– some of them have been modeled computationally in the field of Computational Media Aesthetics (CMA). For example, considering colors, a study reported in showed that human subjects prefer blue and dislike yellow, unveiling intriguing continuity between animal and human color aesthetics. Regarding shape, the most important principle discussed in the literature is that of the “Golden Ratio”: the idea is that a rectangle whose ratio between height and width is the same as the ratio of their sum to their maximum is more attractive than other rectangles. Recent studies limited the strength of this belief .

ADVANTAGES OF PROPOSED SYSTEM:

·       It focuses on both behavioral and physiological approaches.

·       Involving both verification and identification.

·       This will show that personal tastes act like a blueprint for a user, allowing to recognize him against others.

 

SYSTEM ARCHITECTURE:

 

SYSTEM CONFIGURATION:-

HARDWARE REQUIREMENTS:-

ü Processor                  -        Pentium –IV

ü Speed                        -        1.1 Ghz

ü RAM                         -        512 MB(min)

ü Hard Disk                 -        40 GB

ü Key Board                -        Standard Windows Keyboard

ü Mouse                       -        Two or Three Button Mouse

ü Monitor                     -        LCD/LED

SOFTWARE REQUIREMENTS:

•         Operating system :         Android.

•         Coding Language :         Android

•         Data Base             :         SQLite

•         Tool                     :         Eclipse

REFERENCE:

Pietro Lovato, Manuele Bicego, Cristina Segalin, Alessandro Perina, Nicu Sebe, Senior and Marco Cristani, “Faved! Biometrics: Tell Me Which Image You Like and I’ll Tell You Who You Are” IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, VOL. 9, NO. 3, MARCH 2014