Classification of Different Age Groups of People by Using Deep Learning
The Purpose of this study is to classify human images ofdifferent age groups with VggNet which is one of the Deep Learning (DL) models.Artificial intelligence, machine learning and computer vision have been carriedout in recent years at very advanced level. Undoubtedly, it is a great contri...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tokat Gaziosmanpasa University
2018-12-01
|
| Series: | Journal of New Results in Science |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/en/download/article-file/582149 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The Purpose of this study is to classify human images ofdifferent age groups with VggNet which is one of the Deep Learning (DL) models.Artificial intelligence, machine learning and computer vision have been carriedout in recent years at very advanced level. Undoubtedly, it is a great contribution of DL in the rapid progress ofthese studies. Although DL foundational is based on past history, it has becomepopular in the imageNet competition held in 2012. This is because the top-5 errorrate of 26.1% for visual object description has fallen to 15.3% for the firsttime with a sharp decline that year with DL. The Convolution Neural Network(CNN) is basis of DL models. It is basically composed of 4 layers. These areConvolution Layer, ReLu Layer, Pooling Layer and Full Connected Layer. DL modelsare designed using different numbers of these layers. In this study, people aredivided into 12 classes according to age groups. These classes are man, woman,man face, woman face, old man, old woman, old man face, old woman face, boy,girl, boy face, girl face respectively. A new data set was created for peoplein 12 different age categories. For Each class 150 and totally 1800 images werecollected. 90% of these images were used for training and the remaining 10%were used for testing. VggNet was trained with this data set. As a result ofthe study, it was seen that people in different age groups were estimated with78.5% accuracy with VggNet model. DL models need to be trained with large datarequired. But it has been seen that training success has achieved a certainvalue with little data. |
|---|---|
| ISSN: | 1304-7981 |