Neural Network based Age and Gender Classification for Facial Images

Abstract

Automatic face identification and verification from facial images attain good accuracy with large sets of training data while face attribute recognition from facial images still remain challengeable. Hence introducing an efficient and accurate facial image classification based on facial attributes is an important task. This paper proposes a methodology for automatic age and gender classification based on feature extraction from facial images. In contrast to the other mechanisms proposed in the literature, the main concern of this methodology is the use of biometric feature variation of male and female for the classification. It uses two types of features namely, primary and secondary features and it includes three main iterations: Preprocessing, Feature extraction and Classification. This study has been carried out using facial images of age range 8-60 years consisting of both gender types and the age classification has been done according to predefined age ranges. Proposed solution is able to classify images in different lighting conditions and different illumination conditions. Classification is done using Artificial Neural Networks according to the different shape and texture variations of wrinkles on face images. This study has been evaluated and tested on both foreign and Asian face images in both gender types and the four age categories used.

Odour Based Human Identification and Classification using Neural Networks

“…Efficient and accurate results obtained for fingerprint detection and face recognition using artificial neural net [2,8,11,12,15]. Palm print and biometric hands detection employing back-propagation neural net with Levenberg-Marquardt training algorithm used in the classification of Palm print Biometrics.…”

Effects of Handling Missing Values of VOCS Gases Emitted From Human for Human Detection

“…The study objective was to apply e-nose system to diagnose heart failure through identifying disease-related VOCs from sweat produced by the skin surface and triggered by an impaired metabolic [19]. Efficient and accurate results obtained for fingerprint detection and face recognition using artificial neural net [4,10,13,14,17]. Palm print and biometric hands detection employing back-propagation NN with Levenberg-Marquardt algorithm applied for classification of Palm print Biometrics.…”

Clasificación de género utilizando medidas antropométricas, análisis de texturas y la arquitectura ANFIS

“…Los autores [15] proponen un método usando redes neuronales para la clasificación de grupos de edad y género, el cual utiliza 4 grupos de edad, su clasificación está basada en la geometría del rostro dependiendo del género, y en el análisis de textura de la piel, su metodología propuesta se divide en tres pasos principales : preprocesamiento , extracción de características y clasificación.…”

“…La metodología de desarrollo que se utilizó está basada en los siguientes autores [15], [5] y [2], los cuales proponen una metodología para el problema de la clasificación de edad y género utilizando comúnmente las redes neuronales, en este caso se usó en la fase de clasificación la arquitectura ANFIS [19], la cual es un tipo de red neuro difusa que utiliza las técnicas de lógica difusa y redes neuronales, por lo tanto de la combinación de estas técnicas se espera una herramienta poderosa [20].…”

“…El ubicar los puntos fue necesario para establecer 7 características las cuales son medidas entre los puntos encontrados en la imagen, las medidas fueron inspiradas en [15], véase Fig. 8 (b), a continuación, en la Tabla 1, se muestran las características y la forma en la que fueron extraídas según la Fig.…”