Age and Gender Based Organisation of Shelter Homes using Convolutional Neural Networks

The number of abandoned, homeless and poor people have increased drastically in the recent days. Allotting these people to different shelter home is a very difficult task because volunteers in NGO have to do all the work manually and homeless people don’t have valid documentation regarding their Age and Gender. Volunteers usually estimate the person’s Age and Gender on the basis of naked eye estimation but this estimation or prediction sometimes will not be accurate. This problematic situation can be solved by using Deep Learning algorithm like Convolutional Neural Network (CNN). So in our project, we use CNN algorithm to estimate the Age and Gender from the facial image which proves to be a challenging task for a machine due to the high extent of variability, lighting and other supporting conditions. The system proposes building a model which has multiple convolutional layers along with dropout and maxpooling layers in between. The proposed model has been trained on UTKFace dataset and Fairface dataset. The proposed system aims to produce a high accuracy in allotting the right shelter home for people under various Age and Gender. The web application also accepts donations from the users visiting the website who are willing to help the shelter home residents.