Age Recognition of Children by Using Neural Networks (original) (raw)
Related papers
Neural Network Based Age Classification Using Linear Wavelet Transforms
2012
The facial image analysis for classifying human age has a vital role in Image processing, Pattern recognition, Computer vision, Cognitive science and Forensic science. The various computational and mathematical models, for classifying facial age includes Principal Component Analysis (PCA) and Wavelet Transforms and Local Binary Pattern (LBP). A more sophisticated method is introduced to improve the performance of the system by decomposing the face image using 2-level linear wavelet transforms and classifying the human age group using Artificial Neural Network. This approach needs normalizing the facial image at first and then extracting the face features using linear wavelet transforms. The distance of the features is measured using Euclidean distance and given as input to Adaptive Resonance Theory (ART). The network is trained with an own dataset consisting of 70 facial images of various age group. The goal of the proposed work is to classify the human age group into four categorie...
Speaker Recognition Using Discrete Wavelet Transform and Artificial Neural Networks
2016
In recent years biometrics has emerged as applied scientific discipline with the objective of automatically capturing personal identifying characteristics that distinguish one individual from another and using the measurements for security, surveillance, and forensic application. Speaker recognition is the process of automatically recognizing who is speaking based on individual information included in the speech waves. This paper presents the speaker identification method based on Discrete Wavelet Transform (DWT) and Artificial Neural Networks (ANN). In this study the DWT is used to extract a speaker's discriminative features from the mathematical representation of the speech signal. These feature vectors are used to train a feedforward neural network which is used to model the speakers and make the decision task. A database of 20 speakers (10 male and 10 female) has been used with a vocabulary of Kurdish words. The system led to 100% identification rate for text-dependent and 8...
Speech Recognition System Based on Wavelet Transform and Artificial Neural Network
For the past several decades, designers have processed speech for a wide variety of applications ranging from mobile communications to automatic reading machines. Speech recognition reduces the overhead caused by alternate communication methods. Speech has not been used much in the field of electronics and computers due to the complexity and variety of speech signals and sounds. However, with modern processes, algorithms, and methods we can process speech signals easily and recognize the text. This paper presents an expert speech recognition system for isolated words based on a developed model of Discrete Wavelet Transform (DWT) and Artificial Neural Network (ANN) techniques to improve the recognition rate. The data set was created by using English digits from zero to five and other nine words (spoken words) which was collected from four individuals in various time intervals. The feature vector was formed by using the parameters extracted by DWT. We have employed Daubechies 4-tap (d...
SPEAKER RECOGNITION METHOD COMBINING FFT, WAVELET FUNCTIONS AND NEURAL NETWORKS
The method of speaker recognition based on wavelet functions and neural networks is presented in this paper. The wavelet functions are used to obtain the approximation function and the details of the speaker's averaged spectrum in order to extract speaker's voice characteristics from the frequency spectrum. The approximation function and the details are then used as input data for decision-making neural networks. In this recognition process, not only the decision on the speaker's identity is made, but also the probability that the decision is correct can be provided. INTRODUCTION The method is based on spectral analysis of time windowed speaker's voices, using the Fast Fourier Transform (FFT) and creating the averaged spectrum over the defined time. After the averaged spectrum has been created, it is divided into 22 subbands (up to approximately 8 kHz), consistent with the critical frequency bands (barks) of the human auditory system. After the spectral division is m...
Automatic Emotion Recognition (AER) from discourse finds more prominent importance in better man machine interfaces and apply autonomy. Discourse feeling based investigations firmly identified with the databases utilized for the examination. We have made and broke down three enthusiastic discourse databases. Discrete Wavelet Transformation (DWT) was utilized for the component extraction and Artificial Neural Network (ANN) was utilized for example characterization. Highlight extraction in discourse preparing is one of the primary stages to create discourse handling applications. An extensive arrangement of highlight extraction techniques is accessible to actualize on discourse handling approaches, anyway the decay through Wavelet bundles is a standout amongst the most mainstream these days for its strength. This paper portrays the improvement and usage of the WPD method utilizing discourse tests of the expressions of/cero/and/uno/. The trademark coefficients that after effect of the WPD are entered in an example acknowledgment dependent on neural systems to characterize information and perceive between the expressed words. The outcomes demonstrate an order above 75%, which shows the appropriateness of the strategy for acknowledgment.