IDEAS home Printed from https://ideas.repec.org/h/tkp/mklp15/2021-2027.html
   My bibliography  Save this book chapter

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

Author

Listed:
  • Ali Yasar

    (Selcuk University, Turkey)

  • Ismail Saritas

    (Selcuk University, Turkey)

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.

Suggested Citation

  • Ali Yasar & Ismail Saritas, 2015. "Determination of whether Skin or non Skin from the Color Pixels Using Neural Network," Managing Intellectual Capital and Innovation for Sustainable and Inclusive Society: Managing Intellectual Capital and Innovation; Proceedings of the MakeLearn and TIIM Joint International Conference 2,, ToKnowPress.
    • Handle: RePEc:tkp:mklp15:2021-2027
    as

    Download full text from publisher

    File URL: http://www.toknowpress.net/ISBN/978-961-6914-13-0/papers/ML15-421.pdf
    File Function: full text
    Download Restriction: no
    File URL: http://www.toknowpress.net/ISBN/978-961-6914-13-0/MakeLearn2015.pdf
    File Function: Conference Programme
    Download Restriction: no
    ---><---

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:tkp:mklp15:2021-2027. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Maks Jezovnik (email available below). General contact details of provider: http://www.toknowpress.net/proceedings/978-961-6914-13-0/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.