click here to download project abstract of learning deep learning
click here to download the base paper of learning deep learning
ABSTRACT
When a person is uniquely identified then it is because of the face which is the crucial part. With the help of a face, different people are classified and also besides these, a large number of applications can be implemented like for security purposes at banks, various organizations and also in the areas where there is a large public gathering. As the raise in usage of social media and social platforms reached up in the air, age and gender detection became prominent. The attribute information such as age and gender improves the performance of face recognition. This project proposes age and gender detection method from face images using Deep-convolutional neural network(CNN). In this study, face images of persons are trained using CNN. Training of deep models shows exceptional performance with large datasets, but they are not suitable for learning from few samples. The input faces are compared with the images in the data set and will be recognized. There are many methods which have been proposed in the literature for age estimation and gender classification. However, all of them still have a disadvantage such as partial reflection about face structure and face texture. This technique applies to both face alignment and recognition and significantly improves these two aspects. To this end, we propose a simple convolutional network architecture that can be used even when the amount of learning data is limited.
Keywords: face recognition, attribute information, Deep-Convolutional neural networks, gender classification, age-classification.
INTRODUCTION
Facial analysis has gained much recognition in the computer vision community in the recent past. 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, etc. We formulate the age and gender classifications task as a classification problem in which the CNN model learns to predict the age and gender from a face image. We need to propose a model that uses CNN architecture to predict the age group and gender of human’s faces from unfiltered real-world environments. The CNN approach addresses the age and gender labels as a set of discrete annotations and train the classifiers that predict the human’s age group and gender. Then we design a quality and robust image preprocessing algorithm that prepares and preprocesses the unfiltered images for the CNN model and this greatly has a very strong impact on the performance accuracy of our age and gender classifiers. We demonstrate that pertaining on large-scale datasets allows an effective training of our age and gender CNN model which enable the classifiers to generalize on the test images and then avoid overfitting. Finally, UTK Face dataset is used to evaluate the performance of the CNN model, and despite the very challenging nature of the images in the dataset, the approach produces significant improvements in age group and gender classification accuracy. Face recognition techniques described in the last few years have shown that tremendous progress can be made by the use of deep convolutional neural networks (CNN). We demonstrate similar gains with a simple network architecture, designed by considering the rather limited availability of accurate age and gender labels in existing face data sets.
Advantages of CNN:
- Processing speed.
- Flexible and Robust
- Versatile in nature / Dynamic Behavior.
Applications of CNN:
- Decoding Facial Recognition.
- Analyzing Documents.
- Understanding Climate
NEURAL NETWORKS
Neural Network (or Artificial Neural Network) has the ability to learn by examples. ANN is an information processing model inspired by the biological neuron system. ANN biologically inspired simulations that are performed on the computer to do a certain specific set of tasks like clustering, classification, pattern recognition etc. It is composed of a large number of highly interconnected processing elements known as the neuron to solve problems. It follows the non linear path and process information in parallel throughout the nodes. A neural network is a complex adaptive system. Adaptive means it has the ability to change its internal structure by adjusting weights of inputs.
Fig : Basic Neural Network
