A Framework for Age and Gender Prediction from Images using Deep Learning Techniques

Project Title

A Framework for Age and Gender Prediction from Images using Deep Learning Techniques

Project Area of Specialization Artificial IntelligenceProject Summary

In our project, two attributes can be predicted from an image of a face, such as age and gender. It is easy to imagine the possible applications, from human-computer interaction to marketingtosecurity systems. To train age and gender models it is necessary to have labeled datasets. Thereare many publicly available datasets with age or gender annotations. Another option is to create a new dataset by manually labeling face images.

Project Objectives

Build a gender and age classification system based on facial images. Compare and find the algorithm that can handle large training samples while retainingreliable accuracy. Recommends suitable classification method for gender and age classification application.

Project Implementation Method

Face detection in computer vision face detection identifies human faces on images. Therearenumerous approaches for unconstrained face detection. Facial landmarks detectingfacial landmarks is a crucial step for face alignment. Facial landmarks are used to localize facial structures such as nose, eyebrows, eyes, mouth and jaw. It uses a cascade of regressiontrees, © University of Education where each tree updates a vector of facial landmark coordinates. A convolution neural network(CNN) is a type of artificial neural network used in image recognition and processingthat isspecifically designed to process pixel data. CNN are powerful image processing, artificial intelligence that use deep learning to perform both generative and descriptive tasks, oftenusingmachine vision that includes image and video recognition, along with recommended systems andnatural language processing. After finding all facial features various ratios are computed. Usingthe computed ratios the face is then classified. The approach also uses the presence of wrinklesin an area of face to infer the age. The problem of gender prediction and classification is closely related to face detection. More recently the gender classification problem has been treatedasasub problem of age prediction. Current approaches use the same neural network architectureforage as well as gender prediction

Benefits of the Project

Age and gender information are very important for various real world applications, such as social understanding, biomet- rics, identity verification, video surveillance, human-computer interaction, electronic customer, crowd behavior analysis, on- line advertisement, item recommendation.Development Tools:  PyCharm , Google Colab.

Technical Details of Final Deliverable

Technologies Computer Vision: Computer vision is a field of artificial intelligence that trains computers to interpret and understand the visual world. Using digital images from cameras and videos and deep learning models, machines can accurately identify and classify objects —andthen react to what they “see.

Final Deliverable of the Project Software SystemCore Industry ITOther Industries Education Core Technology Big DataOther Technologies Artificial Intelligence(AI)Sustainable Development Goals Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	65000
GPU	Equipment	1	50000	50000
PC	Equipment	1	15000	15000