A Deep Learning Approach on Gender and Age Recognition using a Single Inertial Sensor (original) (raw)

BioDeep: A Deep Learning System for IMU-based Human Biometrics Recognition

Proceedings of the 18th International Conference on Informatics in Control, Automation and Robotics, 2021

Human biometrics recognition has been of wide interest recently due to its benefits in various applications such as health care and recommender systems. The rise of deep learning development, together with the massive data acquisition systems, made it feasible to reuse models trained on one task for solving another similar task. In this work, we present a novel approach for age and gender recognition based on gait data acquired from Inertial Measurement Unit (IMU). BioDeep design is composed of two phases, first of which is applying a statistical method for feature modelling, the autocorrelation function, then building a Convolutional Neural Network (CNN) for age regression and gender classification. We also use random forest as a baseline model to compare the results achieved by both methods. We validate our models using four publicly available datasets. The second phase is doing transfer learning over these diverse datasets. We train a CNN on one dataset and reuse its feature maps over the other datasets for solving both age and gender recognition problems. Our experimental evaluation over the four datasets separately shows very promising results. Furthermore, transfer learning achieved 20 − 30x speedup in the training time in addition to keeping the acceptable prediction accuracy.

IJERT-Gender Recognition and Age Approximation using Deep Learning Techniques

International Journal of Engineering Research & Technology (IJERT), 2020

https://www.ijert.org/gender-recognition-and-age-approximation-using-deep-learning-techniques https://www.ijert.org/research/gender-recognition-and-age-approximation-using-deep-learning-techniques-IJERTV9IS040268.pdf Age and gender that are the two key facial attributes, play a foundational role in social interactions, making age and gender estimation from one face image a crucial task in intelligent applications, like access control, human-computer interaction, enforcement, marketing intelligence and visual surveillance. The basic aim of this paper is to develop an algorithm that estimates age and gender of a person correctly. One of the most widely used techniques is haar cascade. In this paper we propose a model which can predict the gender of a person with the assistance of Haar Cascade. The model trained the classifier with different male and female images as positive and negative images. Different facial features are extracted. With the assistance of Haar Cascade classifier will determine whether the input image is male or female. We made use of Deep-Convolution neural network. It works efficiently even with limited data. For the age approximation task, the paper makes use of caffedeep learning framework. Caffe provides expressive architecture, extensible code. Caffe can process over 60M photos per day. This makes it one of the fastest convent implementation available.

Gender and age classification using deep learning

IRJET, 2022

Age and gender, two of the key facial attributes, play a very foundational role in social interactions, making age and gender estimation from a single face image an important task in intelligent applications, such as access control, human-computer interaction, law enforcement, marketing intelligence and visual surveillance, etc. We will be using convolutional neural networks as a deep learning technique to predict age and gender of the facial image. The benchmark dataset that we will be using to train the model is the UTK Face dataset which is obtained from Kaggle. It is not a pre-processed dataset. At the end, an offline mobile application will be built to predict age and gender of the given input image i.e., facial image.

Classification of Age and Gender using Deep Learning

With time, the gender classification and age classification has picked up significance and has turned into a dynamic zone of research . Face recognition is an extremely difficult issue in the field of image analysis and computer vision on the grounds that the human face being a dynamic question is vulnerable to a high level of changeability in its appearance. Programmed age estimation from true and unconstrained face pictures is quickly picking up importance . In our proposed work, a profound CNN demonstrate that was prepared on a database for face recognition undertaking is utilized to appraise the age data . The paper talks about a way to deal with order images or a video stream as indicated by gender and age in light of Convolutional Neural Networks and furthermore traces a comparison of CNN with the consequences of traditional ML strategies, for example, SVM and Logistic Regression.

Wearable Sensor-Based Gait Analysis for Age and Gender Estimation

Sensors

Wearable sensor-based systems and devices have been expanded in different application domains, especially in the healthcare arena. Automatic age and gender estimation has several important applications. Gait has been demonstrated as a profound motion cue for various applications. A gait-based age and gender estimation challenge was launched in the 12th IAPR International Conference on Biometrics (ICB), 2019. In this competition, 18 teams initially registered from 14 countries. The goal of this challenge was to find some smart approaches to deal with age and gender estimation from sensor-based gait data. For this purpose, we employed a large wearable sensor-based gait dataset, which has 745 subjects (357 females and 388 males), from 2 to 78 years old in the training dataset; and 58 subjects (19 females and 39 males) in the test dataset. It has several walking patterns. The gait data sequences were collected from three IMUZ sensors, which were placed on waist-belt or at the top of a b...

Gender and Age Detection using Deep Learning

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2021

For the past few years, gender and age detection has been an active area of study and researchers have been putting a lot of effort to contribute quality research in this area. Starting from preprocessing of data to building a model which gives high precision results is tedious task for researchers. There is a immense dormant field of study as it can be used in monitoring, surveillance, human-computer interaction and security. However, there is still a lack of the performance of existing methods on real live images. Many difficult tasks such as computer vision, speech recognition, and natural language processing are easily solved with deep learning. Therefore, the approach of deep learning remarkably growing and this also takes place in image classification. Therefore, to analyses and focuses on comparative study of different algorithms for gender and age recognition system to give elevated degree of precision is required.

Age and gender detection using deep learning

IRJET, 2022

The extraction of auxiliary data from various biometric approaches, including fingerprints, faces, iris, palms, voices, etc., is currently the subject of research. Gender, age, beard, mustache, scars, height, hair, skin tone, glasses, weight, facial scars, tattoos, and other traits are all included in this data. Each piece of information acquires relevance during identification. One of the most important developments in facial recognition is the ability to determine a person's age and gender. Given the significance of age and gender in social interactions, it might be challenging to infer these two facial characteristics from a single-face photo. The term "computer vision" refers to the several terminologies used to scan images and determine an individual's age and gender.

Gender and Age Estimation from Human Faces Based on Deep Learning Techniques: A Review

International Journal of Computing and Digital Systems, 2023

Due to the advancement of the methodologies employed in this field and the increased attention being paid to the deep learning (DL) techniques' implementation, focusing on convolutional neural networks (CNNs), gender and age estimates have recently assumed a significant amount of relevance. It is important to precisely predict the gender, including the age of a person, provided that it is used in many applications for smart devices, including those related to security, health, and other areas. Although there have been several studies and research in this area, gender, and age estimation still confront certain problems and difficulties, such as existing of earrings, races, masked faces, makeup, etc. which might interfere with the systems' operations and decrease their accuracy. In this paper, we assess the accuracy of the models employed in three of the most well-known datasets: MORPH2, FG-NET, and OUI-Adience. Our focus is on the best and most recent technology available in this field. Additionally, we have mentioned a list of most of the challenges that may face in the process of estimating age and gender, as well as a list of applications and areas in which it can be used.

Gender Recognition and Age Approximation using Deep Learning Techniques

International Journal of Engineering Research and, 2020

Age and gender that are the two key facial attributes, play a foundational role in social interactions, making age and gender estimation from one face image a crucial task in intelligent applications, like access control, human-computer interaction, enforcement, marketing intelligence and visual surveillance. The basic aim of this paper is to develop an algorithm that estimates age and gender of a person correctly. One of the most widely used techniques is haar cascade. In this paper we propose a model which can predict the gender of a person with the assistance of Haar Cascade. The model trained the classifier with different male and female images as positive and negative images. Different facial features are extracted. With the assistance of Haar Cascade classifier will determine whether the input image is male or female. We made use of Deep-Convolution neural network. It works efficiently even with limited data. For the age approximation task, the paper makes use of caffedeep learning framework. Caffe provides expressive architecture, extensible code. Caffe can process over 60M photos per day. This makes it one of the fastest convent implementation available.

Real-Time Gait-Based Age Estimation and Gender Classification from a Single Image

2021 IEEE Winter Conference on Applications of Computer Vision (WACV), 2021

In this paper, we propose a unified real-time framework for gait-based age estimation and gender classification that uses just a single image, which reduces the latency in video capturing compared with the existing methods based on a gait cycle. To cope with the problem of lacking motion information in the input single image, we first reconstruct a gait cycle of a silhouette sequence from the input image via a gait cycle reconstruction network. The reconstructed gait cycle is then fed into a state-of-the-art gait recognition network for feature representation learning, which is further used to obtain the class of the gender and the estimated probability distribution of integer age labels. Unlike the existing methods focusing on the gait sequences captured from the side view, the proposed method is applicable to the gait images from an arbitrary view with a single trained model, which is more suitable for real-world application scenarios (e.g., automatic access control). Stand-alone and client-server online systems were implemented based on the proposed method, which validates the real-time/online property in actual scenes. The experiments on the world's largest multi-view gait dataset demonstrate the effectiveness of the proposed method, which achieves performance improvement compared with the benchmark algorithms.