Person Identification Using Discriminative Visual Aesthetic

Azam, Samiul; Gavrilova, Marina L.

doi:10.1007/978-3-319-57351-9_2

Cited by 9 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The increased enrollment time was mitigated using principle component analysis (PCA). This work was able to outperform the previous research on the same benchmark dataset 8 with a user identification accuracy of 84% 7 . In 2020, Bari et al 10 proposed the first deep learning‐based visual aesthetic system for person identification.…”

Section: Literature Reviewmentioning

confidence: 75%

“…The method was able to provide the user's identity with an accuracy of 66%. In 2017, Azam and Gavrilova 7 developed another system for aesthetic identification that utilized local perceptual features and histogram oriented gradient (HOG) features along with perceptual and content features. The increased enrollment time was mitigated using principle component analysis (PCA).…”

Section: Literature Reviewmentioning

confidence: 99%

“…Proliferation of the amount of content generated by social network users gave rise to the domain of social behavioral biometrics (SBB) that analyzes online human behavior 5,6 . One of the latest research directions of SBB is social aesthetic biometrics (SAB) 7 . Aesthetic preferences can be expressed as a person's favorite movies, games, songs, stories, or artworks.…”

Section: Introductionmentioning

confidence: 99%

“…5,6 One of the latest research directions of SBB is social aesthetic biometrics (SAB). 7 Aesthetic preferences can be expressed as a person's favorite movies, games, songs, stories, or artworks. Several studies have established the fact that aesthetic preferences can uniquely identify a person.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

RAIF: A deep learning‐based architecture for multi‐modal aesthetic biometric system

Iffath

Gavrilova

2023

Computer Animation & Virtual

View full text Add to dashboard Cite

Human aesthetics play a significant role in video game development, emotional‐aware robot design, online recommender systems, digital human, and other domains of research focusing on human‐computer interactions. Social network user recognition based on aesthetic preferences is an emerging research domain. In this paper, a novel deep learning architecture is proposed for multi‐modal audio‐visual person identification that combines audio and visual aesthetic features. A pre‐trained ResNet architecture is utilized to extract high‐level features from a set of user‐preferred audio and image samples. A novel deep learning‐based fusion technique called residual‐aided intermediate fusion (RAIF) is introduced in order to effectively merge the audio and visual features. The proposed RAIF method achieved an accuracy of 98% and a loss of 0.01 on a proprietary multi‐modal dataset, indicating its effectiveness in fusing audio and visual information.

show abstract

Section: Literature Reviewmentioning

confidence: 75%

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

RAIF: A deep learning‐based architecture for multi‐modal aesthetic biometric system

Iffath

Gavrilova

2023

Computer Animation & Virtual

View full text Add to dashboard Cite

show abstract

“…By introducing new feature categories to the images and with more sophisticated feature engineering, Azam and Gavrilova [15] obtained a rank 1 accuracy of 84% on the same dataset. The features were categorized into four distinctions: local/global perceptual features, HOG features, and content features with 861 total features.…”

Section: Related Workmentioning

confidence: 99%

Person Identification From Audio Aesthetic

Sieu

Gavrilova

2021

IEEE Access

View full text Add to dashboard Cite

Behavioral biometrics survey actions rather than the physical traits of the person. Within this categorization, social behavioral biometrics utilizes an individual's communications for biometric analysis. The investigation of the uniqueness of human preferences and their implications to other aspects of an individual, such as personality or gender, is both a psychological and a biometric problem. An emerging approach is the usage of an individual's aesthetic preferences for the purpose of person identification. Recent research into the identification from visual aesthetics has found that these preferences hold significant discriminatory value. However, aesthetic identification has only been conducted through a visual medium via a set of liked images. The contribution of this work is the development of the first audio aesthetic preference system for person identification. The proposed system extracts descriptive intra-song and intersong features from a set of songs favored by users and utilizes an ensemble of classifiers for prediction. The final decision is optimized by a genetic algorithm. Experimental results demonstrate that the developed audio aesthetic system achieves 95% user recognition accuracy on both proprietary and public audio datasets.INDEX TERMS audio aesthetics, behavioral biometrics, biometric security, human-machine interactions, pattern recognition

show abstract