This project was created referring to the paper "Siamese Neural Networks for One-shot Image Recognition" which is present in the files above
- You can find detailed explaination of the project https://medium.com/@archisha.srivastava078/face-verification-app-using-siamese-like-cnn-8f4676018d21
Neural networks are good at almost every task but they rely on more and more data to perform well. For certain problems like facial recognition and signature verification, we can’t always rely on getting more data. To solve these kinds of tasks we have a new type of neural network architecture called siamese networks.
A siamese neural network (SNN) is a class of neural network architectures that contain two or more identical sub-networks. “Identical” here means they have the same configuration with the same parameters and weights. Parameter updating is mirrored across both sub-networks and it’s used to find similarities between inputs by comparing feature vectors.
- 👉 are capable of learning generic image features useful for making predictions about unknown class distributions even when very few examples from these new distributions are available;
- 👉 are easily trained using standard optimization techniques on pairs sampled from the source data;
- 👉 provide a competitive approach that does not rely upon domain-specific knowledge by instead exploiting deep learning techniques.
- Data Colection
- Preparing Data
- Building the Network
- Training the Network
- Making Kivy app using OpenCV and Tensorflow
Working of the application
Initiate the verification by clicking on the Verify button.
After Initiation click on the verify button again to verify
Image verified by the application
Image unverified by the application
