M. Parashar et al. (Eds.): IC3 2012, CCIS 306, pp. 471–480, 2012.
© Springer-Verlag Berlin Heidelberg 2012
Skin Infection Identification Using Color and Euclidean
Distance Algorithm
Manish Kumar Sharma
1
, Rohit Maurya
2
, Ajay Shankar Shukla
3
, and P.R. Gupta
4
1
GNIT Greater Noida
2
Gameloft India Pvt. Ltd
3
ABV- IIITM Gwalior
4
CDAC Noida
Abstract. In this paper we have discussed the method to detect skin
identification. This method includes three main steps: First segmentation based
on the pixel values, in which when the particular pixel values lies in the range it
is skin area. Second is the post processing stage in which some area which is
not the skin color but counted as a skin area is eliminated and some which is not
counted as skin is added as possible. Third the segmented area is masked with
original image (input image) and Finally Euclidean Distance is applied to find
out Color difference between the segmented skin and mean of reference image
based on threshold values classify the skin is infected or not.
Keywords: Image Histogram, Pixel-Based Skin Detection, Morphological
Processing, Masking, Euclidean Distance Algorithm.
1 Introduction
Skin detection and identification has been topics of extensive research for several past
decades. Many researchers have been done work on the topic Skin Detection but very
little has been done on the Skin identification to find out the skin having rashes or
infection. The process of skin identification is very difficult due to the fact, there is no
certainty of skin color, it may be of red, pink, white, black etc. And the skin color of
the same person is not homogenous through his various body parts. [1]
Skin is an organ composed of several kinds of tissues, It is Largest organ, Performs
many functions such as Prevents harmful substances, chemicals, microorganisms
from entering body, water loss, Maintains temperature, Houses sensory receptors,
Produces chemicals such as Vitamin D, Excretes wastes. There are two layers of skin.
First: Epidermis- The outer layer of skin is epidermis, it is a thin layer and Second:
Dermis- the Inner layer of skin is dermis (thicker than epidermis). Our Experiment is
carried out on the Epidermis, which is the outer layer of skin. For many years, a
premise has been accepted in the field of skin identification that in order to have a
valid identification that the skin is infected or not, it can be obtained when we find
dissimilarities or similarities respectively in the skin region.