Skip to main content

Solve the problem of human recognition from their faces using machine learning techniques.


Objective: Solve the problem of human recognition from their faces using machine learning techniques.

Theory:
Let us introduce a new benchmark data set of face images with variable makeup, hairstyles and occlusions, named BookClub artistic makeup data, and then examine the performance of the ANNs under different conditions. Makeup and other occlusions can be used not only to disguise a person's identity from the ANN algorithms, but also to spoof a wrong identification.

ANN Algorithm:
Artificial Neural Network (ANN) are capable of learning patterns of interest from data in the presence of variations. An Artificial Neural Network in the field of Artificial intelligence where it attempts to mimic the network of neurons makes up a human brain so that computers will have an option to understand things and make decisions in a human-like manner. The artificial neural network is designed by programming computers to behave simply like interconnected brain cells.


Artificial Neural Network primarily consists of three layers:

  • Input Layer
  • Hidden Layer
  • Output Layer







Procedure:

  1. The images used in this are kept coloured and downsized and compressed into JPEG format with the dimension of 48x48 pixels.
  2. The downsizing is done due to computational restrictions to keep processing times reasonable. However, observations made on the small size images are extendable to larger sizes.
  3. For computational experiments, ‘Keras’ library with Tensorflow back-end were used.
  4. The ANN consists of the four sequential groups of layers of the Gaussian noise, convolution with ReLU activation functions, normalization, pooling and dropout layers.
  5. It is topped with the fully connected layers, the softmax activation function of the last layer and cross-entropy loss function. "Adam" learning algorithm with 0:001 coecient, mini-batch size 32 and 100 epochs parameters are used.

Output:





Conclusion:
Despite the small size images were scaled to and not very deep ANN, mean accuracy of the face recognition of the model trained on the samples from all photo-sessions of all subjects is quite high at 92%, and higher (up to 99:9%)

Labels:

Comments

Post a Comment

Popular posts from this blog

Write a code simulating ARP /RARP protocols

   Write a code simulating ARP /RARP protocols . Aim:        To write a java program for simulating ARP/RARP protocols ALGORITHM: server 1. Create a server socket and bind it to port. 2. Listen for new connection and when a connection arrives, accept it. 3. Send server ‟ s date and time to the client. 4. Read client ‟ s IP address sent by the client. 5. Display the client details. 6. Repeat steps 2-5 until the server is terminated. 7. Close all streams. 8. Close the server socket. 9. Stop. Client 1. Create a client socket and connect it to the server ‟ s port number. 2. Retrieve its own IP address using built-in function. 3. Send its address to the server. 4. Display the date & time sent by the server. 5. Close the input and output streams. 6. Close the client socket. 7. Stop. Program Program for Address Resolutuion Protocol (ARP) using TCP Client: import java.io.*; import java.net.*; impor...
Post a Comment
Read more

Importants Links of Leetcode

  Here are all the important discussion posts which contain brief descriptions about a topic with its problem list. Recursion:- A.   https://leetcode.com/tag/recursion/discuss/1733447/Become-Master-In-Recursion Binary Tree and Binary Search Tree:- A.   https://leetcode.com/tag/binary-tree/discuss/1212004/Binary-Trees-study-guide B.   https://leetcode.com/tag/binary-tree/discuss/1820334/Become-Master-in-Tree C.   https://leetcode.com/tag/binary-tree/discuss/1094690/Views-and-Traversal-of-binary-tree-or-Important-topics-or-Must-Read-%3A- ) Dynamic Programming:- A.   https://leetcode.com/discuss/study-guide/458695/Dynamic-Programming-Patterns B.   https://leetcode.com/tag/dynamic-programming/discuss/1437879/Dynamic-Programming-Patterns C.   https://leetcode.com/tag/dynamic-programming/discuss/662866/DP-for-Beginners-Problems-or-Patterns-or-Sample-Solutions D.   https://leetcode.com/tag/dynamic-programming/discuss/1050391/Must-do-Dynamic-programm...
Post a Comment
Read more

The Future of Web Development: Why Next.js is Going Viral

  Are you ready to level up your web development game? Look no further than Next.js, the latest sensation in the world of web development that's taking the industry by storm. With its powerful features, flexibility, and performance optimizations, Next.js is becoming the go-to framework for building modern web applications. In this blog post, we'll explore why Next.js is going viral and how it's changing the landscape of web development. Supercharged Performance: One of the main reasons why Next.js is making waves is its superior performance capabilities. With built-in optimizations like automatic static site generation (SSG) and server-side rendering (SSR), Next.js allows you to create blazing-fast web applications that load quickly and deliver seamless user experiences. This is especially important in today's fast-paced digital world, where users demand instant gratification and have little patience for slow-loading websites. Flexibility and Scalability: Next.js provid...
Post a Comment
Read more