International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 04 Issue: 07 | July -2017
p-ISSN: 2395-0072
www.irjet.net
Tumor segmentation using Improved watershed transform for the application to mammogram image compression Amrutha Varshini N1, K S Babu2 MTech Student, Biomedical Signal Processing and Instrumentation, Dept. of IT, SJCE, Mysuru, Karnataka, India 2Assistant Professor, Dept. of IT, SJCE, Mysuru, Karnataka, India ---------------------------------------------------------------------***--------------------------------------------------------------------1
Abstract - In this work, an automatic image segmentation method is used for the tumor segmentation from mammogram images by means of improved watershed transform using prior information. The segmented regions are then applied to perform a loss and lossless compression for the storage efficiency according to the importance of region data. These are mainly performed in two procedures, including region segmentation and region compression. In the first procedure, an Improved watershed transform based on intrinsic prior information is then adopted to extract tumor boundary. Finally, the tumor regions are detected , and are segmented in mammogram. In the second procedure, Discrete Cosine Transform(DCT) is applied on the regions with different compression rates according to the importance of region data so as to simultaneously reserve important tumor features and reduce the size of mammograms for storage efficiency. Experimental results show that the proposed method gives promising results in the compression applications.
techniques related to the watersheds have been presented in recent decades. The main drawback of watershed algorithm is that it produces over-segmented results. That is, when the watershed obtains catchment basins from the gradient of image, the results of watershed contain too many small regions. Moreover, it is sensitive to noise. Local variations of the image can significantly change the results. In addition, it is poor detection in significant areas with low contrast boundaries. If the signal to noise ratio is not high enough at the contour, the watershed transform will be unable to detect it accurately. Accordingly, the improved version of watershed algorithm may be overcome the intrinsic problems. In addition, various kinds of pre-processing have been developed to solve the problems of over-segmentation, such as the median filter and anisotropic diffusion filter. In this study, an automatic image segmentation method based on improved watershed transform using prior information is proposed for the tumor segmentation from mammogram images.
Key Words: Image segmentation, Mammogram, Tumor, Improved watershed transform, Discrete Cosine Transform, Compression.
Moreover, for medical applications, we should be very cautious to retain sufficient image information in supporting different diagnosis purposes so we will go for image compression.
1.INTRODUCTION Breast cancer is the most common one for women in worldwide. The women disease incidence rate that the breast cancer leaps to first poses the quite big threat to the domestic women. The Digital X-ray mammography is an effective method to achieve the goal of early diagnoses. Accordingly, the accurate segmentation of tumor in mammogram images in very important.
Image compression is very important for efficient transmission and storage of images. Demand for communication of multimedia data through the telecommunications network and accessing the multimedia data through Internet is growing explosively .With the use of digital cameras, requirements for storage, manipulation, and transfer of digital images, has grown explosively . These image files can be very large and can occupy a lot of memory. A gray scale image that is 256 x 256 pixels has 65, 536 elements to store, and a a typical 640 x 480 colour image has nearly a million. Downloading of these files from internet can be very time consuming task. Image data comprise of a significant portion of the multimedia data and they occupy the major portion of the communication bandwidth for multimedia communication. Therefore development of efficient techniques for image compression has become quite necessary.
Image segmentation plays an important role and is an essential process in medical images. General segmentation is the process of partitioning the image into disjointed regions so as to the characteristics of each region are homogeneous. A large variety of image segmentation methods have been presented. Among these methods, the watershed that is a region-based approach is a traditional but popular method from mathematical morphology. The region-based approaches group similar pixels into a region based on some pixel information. The advantages of watershed approach are that it is fast, it can be parallelized, and it produces a complete division of image even if its contrast is low. Many
Š 2017, IRJET
|
Impact Factor value: 5.181
Fortunately, there are several methods of image compression available today. These fall into two general
|
ISO 9001:2008 Certified Journal
| Page 1693