Predicting Soft Biometric Attributes from 30 Pixels: A Case Study in NIR Ocular Images

Bobeldyk, Denton; Ross, Arun

doi:10.1109/wacvw.2019.00024

Cited by 11 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gender classification using iris images has been addressed in several studies following two main approaches [4]: classification using periocular iris images, and classification using normalized iris images. Classification using periocular iris images usually yields results close to and above 80% accuracy and has been repeated successfully over time [4,[9][10][11][12][15][16][17][18][19][20][21][22][23][24][25][26][27]. Using periocular images for gender classification benefits from additional gender cues that are not present in the iris.…”

Section: Related Workmentioning

confidence: 99%

Impact of Occlusion Masks on Gender Classification from Iris Texture

Yáñez,

Tapia,

Perez

et al. 2024

IET Biometrics

View full text Add to dashboard Cite

Gender classification on normalized iris images has been previously attempted with varying degrees of success. In these previous studies, it has been shown that occlusion masks may introduce gender information; occlusion masks are used in iris recognition to remove non-iris elements. When, the goal is to classify the gender using exclusively the iris texture, the presence of gender information in the masks may result in apparently higher accuracy, thereby not reflecting the actual gender information present in the iris. However, no measures have been taken to eliminate this information while preserving as much iris information as possible. We propose a novel method to assess the gender information present in the iris more accurately by eliminating gender information in the masks. This consists of pairing iris with similar masks and different gender, generating a paired mask using the OR operator, and applying this mask to the iris. Additionally, we manually fix iris segmentation errors to study their impact on the gender classification. Our results show that occlusion masks can account for 6.92% of the gender classification accuracy on average. Therefore, works aiming to perform gender classification using the iris texture from normalized iris images should eliminate this correlation.

show abstract

Section: Related Workmentioning

confidence: 99%

Impact of Occlusion Masks on Gender Classification from Iris Texture

Yáñez,

Tapia,

Perez

et al. 2024

IET Biometrics

View full text Add to dashboard Cite

show abstract

“…A person's ethnicity, age and gender may be ascertained, according to recent studies using biometric data [6][7][8][9]. Face and iris modalities have been widely investigated.…”

Section: Related Workmentioning

confidence: 99%

Dynamic Horizontal Voting Ensemble Deep Learning Approach to Combined Classification for Human Age, Gender and Ethnicity Soft Biometric Using Fingerprint Pattern

Olufunso

Evwiekpaefe

Irhebhude

2023

IJAIT

View full text Add to dashboard Cite

There is paucity of information regarding the probability that fingerprints may reveal combined soft biometric trait of human age, gender, and ethnicity. This challenge is due to lack of data. This has however, prompted academics to conduct their demographic classification-related work using the limited fingerprint dataset that is now available. However, complete fingerprint datasets collected under conventional and real-world conditions are not easily available for research reasons. This research aims to design a multi-task Deep Learning model for classifying the combined traits of ethnicity, gender, and age group estimation using fingerprint pattern. The fingerprint database was collected using a live scan method in real-world conditions, with subjects from three most numerous racial groups of Nigeria which are Yoruba, Igbo and Hausa, with consideration of the subject gender and age groups. The proposed method for the fingerprint image classification and training is the novel Dynamic Horizontal Voting Ensemble (DHVE) with Hybrid of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) being utilized as the base (weak) learner. The dynamic selection method was utilized to determine classifiers in the normal horizontal voting ensemble, hence enhancing the ensemble technique's average accuracy. Standard performance classification metric inclusive of Accuracy, hold in thoughts, Precision, and F1 rating had been implemented to evaluate the model's performance. The result shows 76% accuracy in predicting person’s combined age group, ethnicity and gender. We also compared its performance against other approaches. It outperforms other cutting-edge algorithm like the CNN model in terms of performance metrics.

show abstract

“…With recent advances in machine learning and deep learning for computer vision, the prediction of soft biometric attributes such as age, gender, and ethnicity from facial biometric data has been widely studied [9], [26], [27], [28], [29]. For instance, the use of convolutional neural networks for predicting the gender from face images has resulted in models with almost perfect prediction accuracy [28], [30], [31], [32], [33].…”

Section: Related Workmentioning

confidence: 99%

PrivacyNet: Semi-Adversarial Networks for Multi-attribute Face Privacy

Mirjalili,

Raschka,

Ross

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Recent research has established the possibility of deducing soft-biometric attributes such as age, gender and race from an individual's face image with high accuracy. However, this raises privacy concerns, especially when face images collected for biometric recognition purposes are used for attribute analysis without the person's consent. To address this problem, we develop a technique for imparting soft biometric privacy to face images via an image perturbation methodology. The image perturbation is undertaken using a GAN-based Semi-Adversarial Network (SAN) -referred to as PrivacyNet -that modifies an input face image such that it can be used by a face matcher for matching purposes but cannot be reliably used by an attribute classifier. Further, PrivacyNet allows a person to choose specific attributes that have to be obfuscated in the input face images (e.g., age and race), while allowing for other types of attributes to be extracted (e.g., gender). Extensive experiments using multiple face matchers, multiple age/gender/race classifiers, and multiple face datasets demonstrate the generalizability of the proposed multi-attribute privacy enhancing method across multiple face and attribute classifiers.

show abstract

Predicting Soft Biometric Attributes from 30 Pixels: A Case Study in NIR Ocular Images

Cited by 11 publications

References 19 publications

Impact of Occlusion Masks on Gender Classification from Iris Texture

Impact of Occlusion Masks on Gender Classification from Iris Texture

Dynamic Horizontal Voting Ensemble Deep Learning Approach to Combined Classification for Human Age, Gender and Ethnicity Soft Biometric Using Fingerprint Pattern

PrivacyNet: Semi-Adversarial Networks for Multi-attribute Face Privacy

Contact Info

Product

Resources

About