International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 09 Issue: 05 | May 2022
p-ISSN: 2395-0072
www.irjet.net
A Survey on different techniques used for age and gender classification Dr. Vandana S Bhat1, Shivani A Patilkulkarni2, Pratiksha Karkannavar3, Aditi M4, Madhura Chandunavar5 1 Professor,
Department of Information Science and Engineering, SDMCET, Dharwad, Karnataka, India Student, Department of Information Science and Engineering, SDMCET, Dharwad, Karnataka, India ---------------------------------------------------------------------***--------------------------------------------------------------------2-5
Abstract - Age and gender, the two main facial features,
different strategies that can be used to differentiate age and gender.
play a very important role in social interaction, making the measurement of age and gender from a single face image an important function in intelligent systems, such as access control, computer interaction, law, marketing intelligence, and visual monitoring, etc. In this survey paper, we looked at a few papers and concluded that the convolutional neural network is the most appropriate application for age and gender segregation.
1] Malik, Rati, et al. (IRJET, 2020) has proposed a comprehensive learning solution for measuring age and gender recognition. Using in-depth reading concepts, you can easily distinguish age and gender more accurately, even if the numbers are slightly accurate. We use the Kaggle database, which is the largest human face database available for training. Contains all meta information. Age and gender segregation uses the advanced Karas TensorFlow API. karas are used to build and train models. If you have a small amount of data, you can easily interpret gender and age using TensorFlow, a key open-source library that helps you improve models. They used the VGG face model to measure age using the VGG16 architecture that works with cropped facial images.
Keywords: Age, Gender, Personal Computer Interaction, Access Control, Convolutional Neural Network, visual monitoring.
1. INTRODUCTION Age and gender data are important for a variety of realworld applications, including social comprehension, biometrics, identity verification, video surveillance, personal computer interaction, electronic customers, crowd behavior analysis, online advertising, object recommendations, and much more. Without being overused, measuring age and gender from facial images is a difficult problem to solve. The many sources of infraclass variation in human facial expressions limit the effectiveness of these models in realworld systems. In this project, the application is designed to determine the age and gender of the person in the photo. The app is built using android and the internal part of the android app that finds age and gender is built using in-depth learning. The UTF K Face data database containing approximately 20000 images is used to train an in-depth learning model. UTF K Face data set is not a data set previously processed. Therefore, we will need to process the database and apply it to a deeper learning model. The mobile net model is used as an in-depth learning model due to its lightweight characters, which helps to build applications of smaller sizes. Mobile net is an in-depth learning model provided for tensor flow. Our paper is organized into four sections. Category I contains an introduction to age and gender classification. Phase II covers the literature review of the various age and gender adoption papers. Section III contains a discussion and analysis of the various papers and data sets. Section IV contains the conclusion of the survey paper.
2] Trivedi, Pisa (International Journal of Computer Applications, 2020) has suggested that a person's face provides more information about age, gender, attitude, etc. Influenced by a number of changing factors that change over time, such as aging, hair loss, facial features, and more. Automation has covered a wide range of virtual reality applications. Similarly, age and gender factors can also be adjusted automatically. Methods of differentiating age by gender can improve the understanding and power of computer interactions. CNN is an efficient in-depth learning platform that captures multimedia data such as images, videos, or various 2D / 3D data. Obviously, determining gender and age by facial features interacts with photo and video data. 3] Saxena, Singh, et al. (IEEE, 2021) has proposed a paper that systematically describes the whole process, the various methods and algorithms that can be used, the most accurate method, and how all of this is integrated. We will also highlight its importance and how it can be useful in our daily lives. The main goal of this article is to create a gender and age identifier that can predict the gender and age of a person's face in an image using in-depth reading of the targeted database. In addition, get the most effective predictions and results by overcoming the problem of accuracy and timing.
2. LITERATURE SURVEY
4] Agrawal, and Dixit (Springer, 2020) A proposed study that states that from a human point of view, it is possible to measure a person's age by age on the basis of imagination
A survey of age and gender segregation strategies was developed and described below and concluded by comparing
© 2022, IRJET
|
Impact Factor value: 7.529
|
ISO 9001:2008 Certified Journal
|
Page 3559