Cuckoo Search Framework For Feature Selection And Classifier Optimization In Compressed Medical Image Retrieval

Vol. 3  Issue 1
Year: 2016
Issue:Jan-Mar 
Title:Cuckoo Search Framework For Feature Selection And Classifier Optimization In Compressed Medical Image Retrieval
Author Name:Reddi Kiran Kumar and Vamsidhar Enireddy
Synopsis:
With the availability of different medical imaging equipment for diagnoses, medical professionals are increasingly depending on the computer aided techniques for retrieving similar images from large repositories. This work investigates medical image retrieval problem for lossless compressed images. Lossless compression technique is utilized for compressing the medical images for easy transmission and storage. Texture features are extracted using Gabor filters, Shape features using the Gabor - shape and best features of these are selected by using a novel Cuckoo Search algorithm and compared with other statistical techniques. Classification was done by using the Recurrent neural Network. Optimization of the neural network is done using the Cuckoo Search. Experimental results show the advantages of the proposed framework.

Adaptive Thresholding For Porosity Measurement In Sand Particles

Vol. 2  Issue 4
Year: 2015
Issue:Oct-Dec
Title:Adaptive Thresholding For Porosity Measurement In Sand Particles
Author Name:Maheswaran U and Priyadharshini S
Synopsis:
In this paper, the authors evaluate the porosity of given sand images using image processing technique. An adaptive thresholding technique has been used to calculate this. It has been shown that, the flow and shear characteristics of granular particles such as soils are significantly dependent on the shape of the particles. This is important from a practical viewpoint because a fundamental understanding of granular behavior will lead to an improved understanding of soil stability and influence the design of structural foundations. Furthermore, the calculation of soil stability and, consequently, structural stability is particularly useful during earthquake events. In previous work, the author have demonstrated the applicability of X-ray and optical tomography measurements for characterizing 3-D shapes of natural sands and manufactured granular particles. In this paper, the authors name extended the work to measure the arrangement and the orientation of an assemblage of such particles. A combination of X-ray Computed Tomography (CT) for measuring the coordinates of the individual particles and an iterative adaptive thresholding technique for computing the local variations in porosity is employed to generate porosity maps. Such maps can be used to gain a more fundamental understanding of the shear characteristics of granular particles. In this paper, author demonstrate the success of technique by exercising the method on several sets of granular particles—glass beads (used as a control), natural Michigan Dune and Daytona Beach sand, and processed Dry #1 sand.

Non Linear Robust Edge Detector For Noisy Images

Vol. 2  Issue 4
Year: 2015
Issue:Oct-Dec
Title:Non Linear Robust Edge Detector For Noisy Images
Author Name:Atluri Srikrishna, B. Eswara Reddy and M. Pompapathi
Synopsis:
Identification of edge pixels of the noisy signal without doing regularization is still a challenging problem for researchers. There exists different methods and each method has its own assumptions, advantages, and limitations. Author propose a Non Linear Robust Edge Detector (NLRED), which uses n x n window in order to detect the edges of all possible orientations at noisy images. The proposed method partitions the neighbors of the pixel which is under observation for edge candidature into two sub regions based on differences in the local gray level value. The proposed method calculates test statistic for pixel of each sub region by calculating mean, the placement of each member, index of variability and test statistics. The test statistics with maximum value is considered based on two sub regions. These statistics are calculated for eight different orientations. Among these, the statistic with minimum value is considered for edge candidature. The performance is measured in terms of Figure of Merit (FOM) to show the efficiency of the proposed method by comparing with statistical edge detector CANNY approach, in order to detect all possible edges.

A Computer Aided Diagnosis (CAD) System For Segmentation And Analysis Of Brain Magnetic Resonance Images

Vol. 2  Issue 4
Year: 2015
Issue:Oct-Dec
Title:A Computer Aided Diagnosis (CAD) System For Segmentation And Analysis Of Brain Magnetic Resonance Images
Author Name:T. Chandra Sekhar Rao and G. Sreenivasulu 
Synopsis:
Medical image processing has become the main stay of diagnosis for a multitude of diseased conditions. The advent of sophisticated image processing procedures coupled with the exponential growth in processing power of systems and storages has resulted in huge volume of data that has to be interpreted and analyzed. The huge volume data implies the need for automated analysis system to reduce the burden on radiologists and help in providing quality diagnosis. This paper presents a Computer Aided Diagnosis (CAD) system for segmentation and analysis of Brain tumors in magnetic resonance images. The system has scope for making different analysis like edge analysis, morphological processing, histogram analysis etc. As part of system four different segmentation approaches like, K means segmentation, Watershed segmentation; Fuzzy C Means (FCM) segmentation and Enhanced Independent Component Analysis (EICA) and Mixture model based segmentation are implemented. The performance of the segmentation approaches are evaluated using different performance measures.

Image Denoising Using Hybrid Filter In Presence Of Multiple Noises And Graphical User Interface For Medical Image Enhancement

Vol. 2  Issue 4
Year: 2015
Issue:Oct-Dec
Title:Image Denoising Using Hybrid Filter In Presence Of Multiple Noises And Graphical User Interface For Medical Image Enhancement
Author Name:Gopi Karnam and Ramashri Tirumala
Synopsis:
In the field of image processing, the filtering algorithms are functional over the noisy images to eliminate the noise and protect the image details. In medical diagnosis, removing noise is a very challenging issue, as images are corrupted by multiple noises. Medical images like CT, MRI, and PET have information about the heart, nerves and brain. These images are to be precise and free from noise. This paper presents an efficient method for noise reduction, contrast enhancement for medical images. The projected method uses Hybridization of adaptive median filter with the wiener filter for denoising multiple noises. Wiener filter have enhanced stability between smoothness and precision. It also shows the GUI representation of Image smoothing, Histogram Equalization. The method is experimented on the MRI (Magnetic Resonance Image) and performance is evaluated in terms of the Peak Signal to Noise Ratio (PSNR), Correlation coefficient, Mean Absolute Error (MAE) and Mean Square Error (MSE). The proposed technique removes the Gaussian noise, Impulse noise and Blurredness in the images and improve the quality of images. The result shows that, the hybrid filter outperforms most of the basic algorithms for reduction of multiple noises in medical images. Finally, the results proved that the exploitation of hybrid filter gives the appropriate and consistent results on the test images and provide precision to picture while preserving its information.

An Estimation Of Human Age Group Based On Facial Edge Image Patterns

Vol. 2  Issue 4
Year: 2015
Issue:Oct-Dec
Title:An Estimation Of Human Age Group Based On Facial Edge Image PatternsTransform
Author Name:Gandu Bharat and Burusu Rajesh Kumar
Synopsis:
The present paper derives a new approach for estimating the age group of a person based on structural patterns of an edge image identified in a human face image. This approach uses canny edge operator algorithm for extracting the edges of the image because canny edge operator gives more edges. In this approach, edges are most important because, wrinkles are formed on face when age is growing. When wrinkles are formed on facial image, automatically more edge information is available. This approach uses a structural concept. The present study derived four distinct structural patterns on each 3x3 sub window of facial edge image i.e. Right Diagonal Pattern (RDP), Left Diagonal Pattern (LDP), Vertical Central Line Pattern (VCLP) and Horizontal Central Line Pattern (HCLP) pattern. The central pixel value of the 3x3 sub image is considerable in all four patterns. Based on formation of those four structural patterns, i.e. frequency of occurrences of structural patterns estimate the human age group into five age groups i.e. Child (0 to 9 years), Young (10 to 20 years), Young Adult (21-35), Adult (36 to 50 years) and Senior Age (>50 years). The efficiency of the proposed method is calculated by applying it on different huge facial databases like FgNET and Morph. The proposed method shows high rate of classification when compared with the other existing methods.

Denoising Technique For Segmentation Of Medical Images Using Biorthogonal Wavelet Transform

Vol. 2  Issue 3
Year: 2015
Issue:Jul-Sep 
Title:Denoising Technique For Segmentation Of Medical Images Using Biorthogonal Wavelet Transform
Author Name:Ritu Agrawal and Manisha Sharma
Synopsis:
The proposed paper is divided into two parts: firstly image denoising and secondly image segmentation. All medical images are corrupted by noise at the time of transmission and acquisition. The goal of denoising is to remove noise while retaining the visual quality of image. Biorthogonal wavelet transform via hard thresholding is used for denoising. The second part of the paper is designed for segmentation of Magnetic Resonance Angiography (MRA) cardio image after denoising. Image segmentation plays a significant role in medical field. The aim of image segmentation is to extract meaningful objects lying in the image. The analysis of MRA images using two segmentation methods namely region growing method and fuzzy c- means method are discussed in the presence of different noise level and comparison of two segmentation techniques based on accuracy has been performed. The experimental results shows that fuzzy cmeans method yields better segmentation result compared to the region growing method.