IV. IMAGE ANALYSIS
A. Image Acquisition
Image acquisition in image processing can be broadly
defined as the action of retrieving an image from some source.
Image acquisition in image processing is always the first step
in the workflow sequence because, without an image, no
processing is possible. Acquisition of image can be done
under uniform lighting by Samsung mobile Digital camera
[10] [9] [11].
B. Image Pre-processing and Smoothing.
The aim of pre-processing is an improvement of
image data that suppresses unwanted distortion or enhances
some image features for further processing. For human
viewing, Image Enhancement improves the quality and clarity
of images. Removing noise and blur, rising contrast and
enlightening details from images are example of enhancement
operation. Noise tends to attack images when picture are taken
in low light setting.
While capturing the image, sometime it has been distorted
and hence image is to be enhanced by applying special
median filtering to the image to remove noise [12].Filtering
types ,noise reduction techniques such as Averaging, Gaussian
filters are used and causes image smoothing .In this paper
,Median filter is used for smoothing because it protect the
edges of the image during noise removal and is mostly used
in digital imaging and effective with salt and pepper noise and
speckle noise .The noise in the input gray color image is
detached using median filter [10].
C. Image Segmentation
After image enhancement, the next process in image
processing is the image segmentation and the very first step in
image analysis is image segmentation where the image is
subdivided into different parts or object. Basically the image
is subdivided until we segregate the interested object from
their background. Generally there are two approaches for
segmentation algorithms. one is based on the discontinuity of
gray level values and the other is based on the similarity of
gray level values and for this different approaches like
thresholding, region growing ,region splitting and merging
can be used [12] [10] [9] [13]. Image segmentation is typically
used to locate objects and boundaries in images.
Segmentation can also be done using edge detection. Edge
detector detect the discontinuities in color, gray level, texture
etc. canny, sobel are edge detection operator which are
basically used for detecting an edge [10] [12] [14] [15].
The simplest method of image segmentation is called the
thresholding method. By using threshold value, image
binarization is performed. Threshold is used to separate the
region in an image with respect to the object, which is to be
analysed and this is based on the variation of intensity
between the object pixel and background pixel.