Determination of whether Skin or non Skin from the Color Pixels Using Neural Network

Ali Yasar and Ismail Saritas
Additional contact information
Ali Yasar: Selcuk University, Turkey
Ismail Saritas: Selcuk University, Turkey

from ToKnowPress

Abstract: In this study using the artificial neural network method of artificial intelligence techniques, using the pixel values of color which were obtained from people who belong our data such as RGB (REDGREEN- BLUE), we realized classification process as the skin or non-skin form of people's image. There are 3 entries in the artificial neural network. Hidden layers are included in our system. The skin of the dataset is collected by randomly sampling the R, G, B values from face images of various age groups (young, middle, and old), race groups (white, black, and Asian), and genders obtained from FERET database and PAL database . Total learning sample size is 245057; out of which 50859 is the skin sample and 194198 is non-skin samples. These 3 input reach our 10-layer hidden layer at our net and from here by processing a classification process is done. Classification of artificial neural network of 245057 data are determined as successful as set of real data classification. Regression results of classification process is quite high. Training regression R = 0.99123, test regression R= 0.99056 and validation regression are defined as 0.99131. With the artificial neural networks in the classification process has been shown to be achieved outstanding success.

Keywords: ANN; classification; artificial neural network; skin; non-skin; machine learning database; RGB (search for similar items in EconPapers)
Date: 2015
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.toknowpress.net/ISBN/978-961-6914-13-0/papers/ML15-421.pdf full text (application/pdf)
http://www.toknowpress.net/ISBN/978-961-6914-13-0/MakeLearn2015.pdf Conference Programme (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:tkp:mklp15:2021-2027

Access Statistics for this chapter

More chapters in Managing Intellectual Capital and Innovation for Sustainable and Inclusive Society: Managing Intellectual Capital and Innovation; Proceedings of the MakeLearn and TIIM Joint International Conference 2015 from ToKnowPress
Bibliographic data for series maintained by Maks Jezovnik ().