You are on page 1of 9


DATE : 6-02-2018
Detecting and Recognizing Skin Diseases
Using SVM Classifier

Skin diseases are becoming a common phenomenon these days as different types
of allergies are increasing rapidly. Most skin diseases tend to pass on from one person
to another and therefore it is important to control it at initial stages to prevent it from
spreading. In this project, I study the problem of skin disease automated detection and
provide the user advises or treatments based on the results obtained in a shorter time
period than the existing methods. I will be constructing a diagnosis system based on the
techniques of image processing and data mining. In this project, I using the SVM
Algorithm to detect and recognize the skin diseases. I will be making use of Matlab
software to perform the pre-processing and processing of the skin images which will be
obtained from the given data set
1. Project Definition and Description:
Skin cancer is a deadly disease. Skin has three basic layers. Skin cancer begins
in outermost layer, which is made up of first layer squamous cells, second layer basal
cells, and innermost or third layer melanocytes cell. In today’s world, people of different
age groups are suffering from skin diseases such as eczema, scalp ringworm, skin fungal,
skin cancer of different intensity, psoriasis etc. These diseases strike without warning and
have been one among the major disease that has life risk for the past ten years. If skin
diseases are not treated at earlier stage, then it may lead to complications in the body
including spreading of the infection from one individual to the other.
The skin diseases can be prevented by investigating the infected region at an early
stage. It is important to control it at initial stages to prevent it from spreading. Also damage
done to the skin through skin diseases could damage the mental confidence and
wellbeing of people. Therefore this has become a huge problem among people and it has
become a crucial thing to treat these skin diseases properly at the initial stages itself to
prevent serious damage. Many of the skin diseases are very dangerous, particularly if not
treated at an early stage. Skin diseases are becoming common because of the increasing
pollution. Skin diseases tend to pass from one person to another. Human habits tend to
assume that some skin diseases are not serious problems. Sometimes, most of the
people try to treat these infections of the skin using their own method. However, if these
treatments are not suitable for that particular skin problem then it would make it worse.
And also sometimes they may not be aware of the dangerousness of their skin diseases,
for instance skin cancers. With advance of medical imaging technologies, the acquired
data information is getting so rich toward beyond the human’s capability of visual
recognition and efficient use for clinical assessment.
2. Module Description:
A. Image processing unit.
Image processing is the main part of the design process in our system as it is
required to identify the region of skin infected with the disease and in order to do that
the imge processing part of this process should be carried out.
B. Data mining unit
The results obtained from the image processing unit will be examined and the
disease will be identified and displayed by this unit


1. Formal diagnosis method to skin cancer detection is Biopsy method. A biopsy

is a method to remove a piece of tissue or a sample of cells from patient body
so that it can be analyzed in a laboratory.
2. It is uncomfortable method.
3. Biopsy Method is time consuming for patient as well as doctor because it takes
lot of time for testing. Biopsy is done by removing skin tissues (skin cells) and
that sample undergoes series of laboratory testing.
4. There is possibility of spreading of disease into other part of body. It is more


1. We propose a diagnosis system which will enable users to detect and

recognize skin diseases. With the help of image processing and data mining
techniques and provide the user advises or treatments based on the results
obtained in a shorter time period than the existing methods.
2. It is comfortable method.
3. The results obtained will be classified according to the given prototype and
diagnosis accuracy assessment will be performed to provide users with efficient
and fast results.
4. This processing will be conducted on the different skin patterns and will be
analyzed to obtain the results from which we can identify which skin disease
the user is suffering from. This data will help in early detection of the skin
diseases and in providing their cure.
5. Through this we will be finding a cost effective and feasible test method for the
detection of skin disorders.
System Design
Architectural Design:
(Block Diagram )

User Interface Design:

System Implementation
Module Description:
Input image:

Input to proposed system is dermoscopic images, dermoscopic images are images

taken by dermatoscope. It is kind of magnifier used to take pictures of skin lesions (body
part). It is hand held instrument make it very easier to diagnose skin disease.

Preprocessing :

Goal of pre-processing is an improvement of image data that reduces unwanted

distortions and enhances some image features important for further image processing.
Image pre-processing involves three main things

1) Gray scale conversion

2) Noise removal
3) Image enhancement.

Grayscale conversion:

Grayscale image contains only brightness information. Each pixel value in

grayscale image corresponds to an amount or quantity of light. The brightness graduation
can be differentiated in grayscale image. Grayscale image measures only light intensity.
8 bit image will have brightness variation from 0 to 255 where ‘0’ represents black and
‘255’ represents white. In grayscale conversion colour image is converted into grayscale.
Grayscale images are easier and faster to process than coloured images. All image
processing technique are applied on grayscale image. In our proposed system coloured
or RBG image is converted into grayscale image by using weighted sum.
Noise Removal:

The objective of noise removal is to detect and removed unwanted noise from
digital image. The difficulty is in deciding which features of an image are real and which
are caused by noise. Noise is random variations in pixel values. In our proposed system
we are using median filter to remove unwanted noise. Median filter is nonlinear filter, it
leaves edges invariant. Median filter is implemented by sliding window of odd length.
Each sample value is sorted by magnitude, the center most value is median of sample
within the window, is a filter output.

Image enhancement :

The objective of image enhancement is to process an image to increase visibility

of feature of interest. Here contrast enhancement is used to get better quality result.


Segmentation is process of removing region of interest from given image. Region

of interest containing each pixel similar attributes. Here we are using maximum entropy
thresholding for segmentation. First of all we have to take gray level of original image then
calculate histogram of gray scale image then by using maximum entropy separate
foreground from background. After maximum entropy we obtained binary image that is
black and white image.

Feature extraction :

Feature extraction plays an important role in extracting information present in given

image. Here we are using gray level co-occurrence matrix. (GLCM). GLCM for texture
image analysis. GLCM is used to capture spatial dependency between image pixels.
GLCM works on gray level image matrix to capture most common feature such as
contrast, mean, energy, homogeneity.
The purpose of feature extraction (GLCM) is to suppress the original image data
set by measuring certain values or features that helps to classify different images from
one another.


Classifier is used to classify cancerous image from other skin diseases. For
simplicity Support Vector machine classifier is used here. SVM takes set of images and
predicts for each input image belongs to which of the two categories of cancerous and
non-cancerous classes. The purpose of SVM is create hyper plane that separates two
classes with maximum gap between them. In our proposed system output of GLCM is
given as input to SVM classifier which takes training data, testing data and grouping
information which classifies whether given input image is cancerous or non-cancerous.