Copyright © 2018 Authors. This is an open access article distributed under the Creative Commons Attribution License, which permits
unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
International Journal of Engineering & Technology, 7 (1.1) (2018) 121-124
International Journal of Engineering & Technology
Website: www.sciencepubco.com/index.php/IJET
Research paper
Measuring distinct regions of grayscale image using pixel values
S. Jeyalaksshmi
1*
, S. Prasanna
2
1
Assistant Professor, Dept of IT, Vels University, Pallavaram, Chennai.
2
Associate Professor, Dept. of Computer Application, Vels University, Pallavaram, Chennai.
*Corresponding author E-mail:pravija.lakshmi@gmail.com
Abstract
Grayscale is a series of shades of gray without apparent color. The total absence of transmitted or reflected light, which is the darkest
shade, black. The total reflection or transmission of light at all observable wavelengths, which is nothing but lightest possible shade i.e.,
white. Intermediate shades of gray are characterized by equal brightness levels of the primary colors (red, green and blue) for
transmitting light, or equal amounts of the three primary pigments (magenta,cyan, and yellow) for reflected light. This paper focuses
mainly on measuring the properties of objects in a grayscale image using Regionprops to calculate the standard Deviation. This is
achieved by segmenting a grayscale image to get objects of a binary image. Although, the common problem of including chromatic
values to a grayscale image has objective solution,not exact, the present approach tries to provide an approach to help minimize the
amount of human labor required for this task. We transfer the source’s whole color “mood” to the target image by matching texture
information and luminance between the images rather than selecting RGB colors from a group of colors to an individual color
components. We pick out to transfer only chromatic information and retain the target image’s original luminance values. Further, the
procedure is improved by permitting the user to match areas of the two images with rectangular swatches. It is essential to develop
grayscale image pixel value, resultant to each object in the binary image to inspect the original grayscale image.Based on the original
grayscale image pixel values, the pixel value properties in grayscale image are used to do routine calculations.
Keywords: Grayscale image, regionprops, binary image, pixel value.
1. Introduction
The colors are extremely subjective and personal. They have a
prominent feature by which we try to identify images better and
improve the visual appearance of the image. A grayscale image is
also known as Black and white, in which the each pixel
valuecarries only intensity information. The black and white or
grayscale image composed full of gray shades, changing from
black at the feeblest intensity (weak) to white at the sturdiest
(strong).
The fundamental process of color followed by the human brain in
perceiving color is a psychological wonder that is not yet fully
understood, the color’s physical nature can be expressed on a
formal basis supported by experimental and theoretical results.
Image analysis involves investigation of the image data for a
specific application. Normally, the raw data of a set of images are
analyzed to advantage insight into what's going on with the photos
and the way they can be used to extract desired information. The
processing of an image, recognition of pattern and extraction of
feature is a critical step, which is nothing but a distinct form of
reduction of dimensionality. When the data(input) are just too
large to be processed and alleged to be redundant, then the data is
converted into a comprised set of feature depictions. The process
of remodeling the input data into a set of capabilities is known as
feature extraction. Features regularly comprise information
relative to shape, color, context or texture. Basically, the colors we
observe in an object are decided by means of the nature of the
light pondered from the object.
Due to the human eye’s structure, all colors are visible as variable
mixtures of the three so-called Primary colors Red, Green and
Blue (RGB). Digital image processing permits the use of
complicated computer algorithms to carry out image processing
digital images. An image is captured through a sensor and
digitized. There is a massive representational gap between the
image and the concept which describes or abstracts the image
data. To connect that gap, image processing has a variety of
representations connecting the inputs and the output. Then the
Image processing tasks involve in the layout of these intermediate
representations and the implementation of algorithms to assemble
them and relate them to each other. A Grayscale image is more
than a few shapes of gray in obvious color. The darkest color is
black and the lightest shade is white. The intermediate shades of
gray are represented with the aid of equal brightness level of
primarycolors (red, blue, green). Grayscale image may have any
value for each pixel between 0 (zero) and 256. A binary image is a
digital image that has only two possible intensity values for each
pixel. They are commonly displayed as black and white. Binary
images are produced with the aid of segmenting the grayscale
images containing the objects in the image.
2. Literature review
Satyajit Mondal et al.,[1] has proposed a method for similarity
measurement of image using the property-regionprops, color and
texture. Swain and Ballard[4] has proposed amethod to measure
the image similarity by histogram analysis, intersection. Jitendra
Malik et.al., has proposed an algorithm for partitioning. There, the