Enhanced Automatic X-Ray Bone Image Segmentation using
Wavelets and Morphological Operators
S.K.Mahendran
1
and S.Santhosh Baboo
2
1
Assistant Professor, **
2
Reader, ***
Abstract. X-ray bone segmentation is a vital step in X-Ray image analysis techniques. the main aim of
segmentation is to subdivide the various portions, so that it can help medical practitioners (i) During the
study of bone structure, (ii) Identification of bone fracture, (iii) Measurement of fracture treatment, (iv)
Treatment planning prior to surgery. It is considered as a challenging task because the bone x-ray images are
complex in nature and the output of segmentation algorithm is affected due to various factors like partial
volume effect, intensity inhomogeneity, presence of noise and artifacts and Closeness in gray level of
different soft tissues
Keywords: X-Ray Bone Segmentation, Long Bone, Tibia, Wavelets, Morphological Operators.
1. Introduction
Digital images are increasingly used by medical practitioners to help them during disease diagnosis.
These images display various body organs and are used during treatment decision making process. The
images are produced by several state-of-the-art medical equipments like MRI, CT, ultrasound and X-Ray.
Out of these, X-Ray is one the oldest and frequently used devices, as they are non-intrusive, painless and
economical. The X-Ray images are used during various stages of treatment which include fracture diagnosis
and treatment, evaluation of skeletal maturation and bone densitometry.
X-Ray image analysis techniques to access bone content and bone structure is an area of research that
has attracted many researchers [9, 12, 2]. Almost all these techniques, extract features from x-ray images for
bone analysis. One important a sub-field of image analysis is the segmentation of bone structure from the x-
ray image. Image segmentation is used to classify or assign each pixels into a group (label), where each
group represent membership to a set of pixels that define an object or region in the image. Thus, the main
aim of segmentation is to subdivide the various portions, so that it can help medical practitioners (i) During
the study of bone structure, (ii) Identification of bone fracture, (iii) Measurement of fracture treatment, (iv)
treatment planning prior to surgery. It is considered as a challenging task because the bone x-ray images are
complex in nature and the output of segmentation algorithm is affected due to various factors like partial
volume effect, intensity in homogeneity, presence of noise and artifacts and Closeness in gray level of
different soft tissues.
The solutions proposed can be categorized into two main groups, namely, gray level feature-based
methods and texture feature-based methods. Gray level feature-based methods analyze the gray level or color
features of an image to segment an image. Histogram-based methods [01], Edge-based methods [3], region-
based methods [13] all belong to this category. Histogram-based methods are the simplest and work with a
threshold value. The result of segmentation depends on the correct selection of threshold, which often is
difficult. The performance of these methods often degrades in the presence of noise. The edge-based
methods works well for noise-free images, but its performance degrades with noisy images or when fake or
weak edges are present in the image.
** S.K.Mahendran
1
is Assistant Professor, HOD, Department of Computer Science, Sankara College of Science and
Commerce,Coimbatote, Tamil Nadu, India. MobileNumber:91-9842260168; e-mail: sk.mahendran@yahoo.co.in
*** Lt.Dr.S.Santhosh Baboo
2
, is Reader in the Postgraduate and Research department of Computer Science at Dwaraka Doss
Goverdhan Doss Vaishnav College, Chennai, Tamil Nadu. India. Mobile Number :+91-944-4063888; emaill:santhos2001@sify.com
2011 International Conference on Information and Electronics Engineering
IPCSIT vol.6 (2011) © (2011) IACSIT Press, Singapore
125