Browsing by Author "Geethalakshmi, S N"

Now showing 1 - 20 of 65
  • No Thumbnail Available
    Item
    Analysis o f the Application o f Bi-Orthogonal Wavelet Transform, Bayesthresholding and Independent Component Analysis (ICA) on Poisson Noise Removal from X-Ray Images
    (2011) Geethalakshmi, S N
    Medical field produces huge volume of images, which are used during disease diagnosis. X-Rays are the oldest and most frequently used form of medical imaging. These images are used in many applications with prominent use found in fracture detection. The X-Ray images are normally affected by Poisson noise, which degrades the visual quality of the image and obscures important information required for accurate diagnosis. The current need is, thus, a method that removes noise while preserving important diagnostic data. This study proposed a method that combines Multiple Wavelet Denoising (MWD) Structure with ICA to remove Poisson noise from X-Ray images. The thresholding method used is BayesShrink and both soft, hard thresholding methods are analyzed. From the experimental results, it is evident that the proposed model produces images, which are visually clean and smooth, in fast manner. At the same time, the proposed method also preserves edges and other significant details of the image.
  • No Thumbnail Available
    Item
    Artifact Removal from EEG using Spatially Constrained FastICA and Fuzzy Shrink Thresholding Technique
    (2012) Geethalakshmi, S N
    This paper presents a novel technique for removing the artifacts from the Electroencephalogram (EEG) signals. EEG signals are influenced by different characteristics, like line interference, EOG (electro-oculogram) and ECG (electrocardiogram). The elimination o f artifact from scalp EEGs is o f substantial significance for both the automated and visual examination o f underlying brainwave actions. These noise sources increase the difficulty in analysing the EEG and obtaining clinical information related to pathology. Hence it is crucial to design a procedure to decrease such artifacts in EEG records. This paper uses Spatially-Constrained Fast ICA (SCFastlCA) to separate the Independent Components (ICs) from the initial EEG signal. As the next step, Wavelet Denoising (WD) is applied to extract the brain activity from purged artifacts, where thresholding plays an important role in delineating the artifacts and hence a better thresholding technique called fuzzy Shrink thresholding is applied. Experimental results show that the proposed technique results in better removal o f artifacts.
  • No Thumbnail Available
    Item
    Artifact Removal from EEG using Spatially Constrained Independent Component Analysis and Wavelet Denoising with Otsu’s Thresholding Technique
    (2012) Geethalakshmi, S N
    This paper presents a novel technique for removing the artifacts from the ElectroEncephaloGram (EEG) signals. EEG signals are influenced by different characteristics, like line interference, EOG (electro-oculogram) and ECG (electrocardiogram). The elimination of artifact from scalp EEGs is of substantial significance for both the automated and visual examination of underlying brainwave actions. These noise sources increase the difficulty in analyzing the EEG and obtaining clinical information related to pathology. Hence it is crucial to design a procedure to decrease such artifacts in EEG records. This paper uses Spatially-Constrained Independent Component Analysis (SCICA) to separate the Independent Components (ICs) from the initial EEG signal. As the next step. Wavelet Denoising (WD) is applied to extract the brain activity from purged artifacts, and finally the artifacts are projected back and subtracted from EEG signals to get clean EEG data. Here, thresholding plays an important role in delineating the artifacts and hence a better thresholding technique called Otsu’, thresholding is applied. Experimental results show that the proposed technique results in better removal of artifacts.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Automatic Recognition System Using Preferential Image Segmentation For Leaf And Flower Images
    (2011) Geethalakshmi, S N
    Plant is one of the most important forms of life on earth. Plant recognition is very demanding in biology and agriculture as new plant discovery and the computerization of the management of plant species become more popular. The recognition is a process resulting in the assignment of each individual plant to a descending series of related plants in terms of their common characteristics. The process is very timeconsuming as it has been mainly carried out by botanists. Computer-aided plant recognition is still very challenging task in computer vision as the lack of proper models or representation schemes, a large number of variations of the plant species, and imprecise image pre-processing techniques, such as edge detection and contour e.xtraction. The focus of computerized living plant recognition is on stable feature's e.xtraction of plants. The information of leaf veins, therefore, play an important role in identifying living plants. The ultimate goal of this project is to develop a system where a user in the field can take a picture of an unknown plant, feed it to the system carried on a portable computer, and have the system classify the species and display sample images of the closest matches within a couple of seconds.
  • No Thumbnail Available
    Item
    Automatic Recognition System Using Preferential Image Segmentation For Leaf And Flower Images
    (2011) Geethalakshmi, S N
    Plan! is one of the most important forms of life on earth. Plant recognition is very demanding in biology and agriculture as new plant discovery and the computerization of the management of plant species become more popular. The recognition is a process resulting in the assignment o f each individual plant to a descending series of related plants in terms of their common characteristics. The process is very timeconsuming as it has been mainly carried out by botanists. Computer-aided plant recognition is still very challenging task in computer vision as the lack of proper models or representation schemes, a large number of variations of the plant species, and imprecise image pre-processing techniques, such as edge detection and contour extraction. The focus of computerized living plant recognition is on stable feature’s extraction of plants. The information of leaf veins, therefore, play an important role in identifying living plants. The ultimate goal of this project is to develop a system where a user in the field can take a picture of an unknown plant, feed it to the system carried on a portable computer, and have the .system classify the species and display sample images of the closest matches within a couple of .seconds.
  • No Thumbnail Available
    Item
    Bone Structure and Diaphysis Extraction Algorithm for XRay Images
    (2012) Geethalakshmi, S N
    Medical imaging systems have been used in various medical application domains like trauma centre, orthopedic, pain management and vascular and non-vascular. One of the oldest and frequently used devices to capture human bones is X-Ray. During the process of identifying fractures, a vital step is the extraction of bone structure from the x-ray image. In this paper, a model that combines multi-resolution wavelets, region growing algorithm and active contour model is proposed to segment the bone structure from the x-ray image. Further a fast Hough transformation is used to extract the diaphysis region from the segmented bone structure. Experimental results prove that the proposed algorithm is efficient both in the manner of segmentation and speed of segmentation.
  • No Thumbnail Available
    Item
    Brewing Heterogeneous Devices for Monitoring Cerebrovascuiar Oxygenation
    (2016) Geethalakshmi, S N
    Technologies encumbering Wireless Sensor Network with its effulgence and ubiquity in Sensing plays a dominant role in Health care industry and Health monitoring System. Impeccable blending of Actuators and networking them for a viable communication across varied platforms paves gateway for triumphant loT solution. loT plays a predominant role in revitalizing the healthcare sector with appendages of several smart devices deliberated to facilitate medicos, surgeons and subjects to monitor each and every aspect of their health. Customary health checkups allow patients to distinguish health issues sooner and get treatment accordingly. loT offers a cost effective solution adjunct with a timely intervention.
  • No Thumbnail Available
    Item
    Brewing Heterogeneous Devices for Monitoring Cerebrovascular Oxygenation
    (2016) Geethalakshmi, S N
    Technologies encumbering Wireless Sensor Network with its effulgence and ubiquity in Sensing plays a dominant role in Health care industry and Health monitoring System. Impeccable blending of Actuators and networking them for a viable communication across varied platforms paves gateway for triumphant loT solution. loT plays a predominant role in revitalizing the healthcare sector with appendages of several smart devices deliberated to facilitate medicos, surgeons and subjects to monitor each and every aspect of their health. Customary health checkups allow patients to distinguish health issues sooner and get treatment accordingly. loT offers a cost effective solution adjunct with a timely intervention.
  • No Thumbnail Available
    Item
    A brief study on human bone anatomy and bone fractures
    (2011) Geethalakshmi, S N
    The rapid and continuing progress in computerized medical image reconstruction and the associated developments in analysis methods and coputer- aided diagnosis have propelled medical imaging as one of the most important sub-fields in scientific imaging. One important area is the fracture detection from x-ray images, where automated toois are used to detect fractures. In order to develop an automated fracture detection system, a clear understanding of human skeletal system, bone and fractures is required. This paper provides description on each of these topics.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Classification of Chronic Kidney Disease using Data Mining Techniques
    (2019-04) Farheen, A; Geethalakshmi, S N
  • No Thumbnail Available
    Item
    Classification of Eeg Signal
    (2019-04) Lakshmi, S; Geethalakshmi, S N
  • No Thumbnail Available
    Item
    Classification Of Firewall Log Files Using Supervised Machine Learning Methods
    (2022-05) Sri Dhanalakshmi, P; Geethalakshmi, S N
  • No Thumbnail Available
    Item
    Code Free MYSQL Management Tool
    (2015-03) Nanthini, J; Geethalakshmi, S N
  • No Thumbnail Available
    Item
    A Comparative Analysis of Feature Extraction Methods for Fruit Grading Classillcations
    (2013) Geethalakshmi, S N
    Fruit plays an important role in our life. India is exporting large number o f fruits to abroad in that mosambi is one among. Before exporting the fruits, the fruits have to be graded according to their quality. This paper presents an evaluation and comparison o f the performance o f three different extraction methods for classification of defect and non defect fruits. Three different feature extraction methods are GLCM (Grey Level Co-occurrence Matrix), shape features and intensity based features. The performance of each feature extraction method is evaluated and compared based on PNN (Probabilistic Neural Network) classifier. The experimental results suggest that shape feature outperformed than other two methods.
  • No Thumbnail Available
    Item
    A Comparative Analysis of Watershed and Color based segmentation for Fruit Grading
    (2012) Geethalakshmi, S N
    In this paper, we presented two segmentation methods. Multi-scaie edge detection with watershed segmentation and color based segmentation using K-means. Color based segmentation is based on fruit color and its difference. Mostly the damage part of the fruit will be o f different color and that will be segmented by our algorithm very correctly. Second the watershed segmentation also segments the fruit based on color, shape and size o f the damage. We compared the results o f both segmentation results and the watershed segmentation outperforms the color based segmentation in all aspects.MATLAB image processing toolbox is used fo r the computation and Comparison results are shown with the segmented images.
  • No Thumbnail Available
    Item
    Compression And Decompression For FTP On LINUX Platform
    (2004-04) Sumitra Devi, R; Geethalakshmi, S N
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Customer Relationship Management
    (2012-04) Mary Steffy, K T; Geethalakshmi, S N