Using CMU PIE Human Face Database to a Convolutional Neural Network - Neocognitron
نویسندگان
چکیده
This work presents the application of Neocognitron to the human face recognition. Using a large-scale human face database (CMU PIE), the optimal thresholds of the Neocognitron to human face recognition are verified. During the first experiment, increasing the activation thresholds of the Neocognitron, their best values to be used in the second experiment, increasing the number of training images per subjects, are obtained. As a result it is verified that a number of 25 training images per subjects is enough to obtain very high recognition rate (98%) to the frontal pose images from the database. 350 validation images, non-overlapping with the training images, were used.
منابع مشابه
Parallel Face Recognition Processing using Neocognitron Neural Network and GPU with CUDA High Performance Architecture
This chapter presents an implementation of the Neocognitron Neural Network, using a high performance computing architecture based on GPU (Graphics Processing Unit). Neocognitron is an artificial neural network, proposed by Fukushima and collaborators, constituted of several hierarchical stages of neuron layers, organized in two-dimensional matrices called cellular plains. For the high performan...
متن کاملDeep Secure Encoding: An Application to Face Recognition
In this paper we present Deep Secure Encoding: a framework for secure classification using deep neural networks, and apply it to the task of biometric template protection for faces. Using deep convolutional neural networks (CNNs), we learn a robust mapping of face classes to high entropy secure codes. These secure codes are then hashed using standard hash functions like SHA-256 to generate secu...
متن کاملMaximum Entropy Binary Encoding for Face Template Protection
In this paper we present a framework for secure identification using deep neural networks, and apply it to the task of template protection for face authentication. We use deep convolutional neural networks (CNNs) to learn a mapping from face images to maximum entropy binary (MEB) codes. The mapping is robust enough to tackle the problem of exact matching, yielding the same code for new samples ...
متن کاملRecognition of Handwritten Digits and Human Faces by Convolutional Neural Networks
Convolutional neural networks provide an eecient method to constrain the complexity of feedforward neural networks by weightsharing. This network topology has been applied in particular to image classiication when raw images are to be classi-ed without preprocessing. In this paper two variations of convolutional networks-Neocognitron and Neoperceptron-are compared with classiiers based on fully...
متن کاملHardware and Software modifications on the Neocognitron and its binary implementations on FPGA
Abstracat: Convolutional neural network (CNN) is a well-known robust image recognition model. It is a multi-layer architecture where the successive layers are designed to learn progressively higher-level features, until the last layer which produces categories. In order to apply this model to robot vision or various intelligent systems, its VLSI implementation with high performance is required....
متن کامل