whose goal is to separate individual objects in the perception of the scene. A common problem
in segmentation of monochrome image occurs when an image has a background of varying
gray levels such as gradually changing shades [4]. This problem is inherent, since intensity is
the only available information from monochrome images. It has long been recognized that the
human eye can sense only in the neighborhood of one or two dozen intensity levels at any one
point in a complex image due to its brightness adaptation but can discern thousands of color
shades and intensities [5]. Color image segmentation techniques can be roughly classified into
four types such as histogram based approaches, neighborhood based approaches, clustering
based approaches and hybrid based approaches. Gray-level thresholding is one of the oldest
techniques for image segmentation [6]. Threshold may be chosen based onhistogram [7] or on
gray-level co-occurrence matrix [8], or by analyzing intra-region and inter-region homogeneity
[9]. Histogram thresholding is a popular technique that looks for the peaks and valleys in
histogram [10] [11]. It assumes that images are composed of regions with different gray level
ranges. The histogram of an image can be separated into a number of peaks (modes), each
corresponds to one region, and there exists a threshold value corresponding to the valley
between two adjacent peaks. The most important advantage of this technique deceit is its
simple computation [11]. In this experiment, our idea is only to develop the process of
recognition of seeds using the techniques of image processing and computer vision. By using
this technique we can visualize the above processes using camera and the computer. The idea
surrounds near the execution of a well-known technique, “mathematical morphology” used in
image processing and computer vision [12] [13] [14]. In this, the shape oriented approach treats
the image as one set and the kernel of operation, commonly known as structuring element (SE),
as another set. Different standard morphological operations namely dilation, erosion, opening,
closing etc. are basically set-theoretic operations between these two sets. The shape and the size
of the SE plays an important role in detecting or extracting features of given shape and size
from the image. Applications of mathematical morphology in gray-level image segmentation
can be found in [15] [16] [17].