Recognition of Handwritten Digits and Human Faces by Convolutional Neural Networks
نویسنده
چکیده
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 connected feedforward layers (i.e. Multilayerperceptron, Nearest Neighbor Classiier, Autoencoding network) with respect to their visual recognition performance. Beside the original Neocognitron a modiication called Neoperceptron is proposed which combines neurons from Perceptron with the localized network structure of Neocognitron. Instead of training convolutional networks by time-consuming error backpropagation in this work a modular procedure is applied, whereby layers are trained sequentially from the input to the output layer in order to recognize features of increasing complexity. For a quantitative experimental comparison with standard classiiers two very diierent recognition tasks have been chosen: handwritten digit recognition and face recognition. In the rst example on handwritten digit recognition the generalization of convolutional networks is compared to fully connected networks. In several experiments the innuence of variations of position, size and orientation of digits is determined and the relation between training sample size and validation error is observed. In the second example recognition of human faces is investigated under constrained and variable conditions with respect to face orientation and illumination and the limitations of convolutional networks are discussed.
منابع مشابه
Persian Handwritten Digit Recognition Using Particle Swarm Probabilistic Neural Network
Handwritten digit recognition can be categorized as a classification problem. Probabilistic Neural Network (PNN) is one of the most effective and useful classifiers, which works based on Bayesian rule. In this paper, in order to recognize Persian (Farsi) handwritten digit recognition, a combination of intelligent clustering method and PNN has been utilized. Hoda database, which includes 80000 P...
متن کاملHand Gesture Recognition from RGB-D Data using 2D and 3D Convolutional Neural Networks: a comparative study
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement dynamics, represented by temporal features, have to be extracted by analyzing the total fr...
متن کاملEstimation of Hand Skeletal Postures by Using Deep Convolutional Neural Networks
Hand posture estimation attracts researchers because of its many applications. Hand posture recognition systems simulate the hand postures by using mathematical algorithms. Convolutional neural networks have provided the best results in the hand posture recognition so far. In this paper, we propose a new method to estimate the hand skeletal posture by using deep convolutional neural networks. T...
متن کاملHandwritten Digits Recognition using Deep Convolutional Neural Network: An Experimental Study using EBlearn
In this paper, results of an experimental study of a deep convolution neural network architecture which can classify different handwritten digits using EBLearn library [1] are reported. The purpose of this neural network is to classify input images into 10 different classes or digits (0-9) and to explore new findings. The input dataset used consists of digits images of size 32X32 in grayscale (...
متن کامل