D. Jude Hemanth

Effective Fuzzy Clustering Algorithm for Abnormal MR Brain Image Segmentation

Clustering approach is widely used in biomedical applications particularly for brain tumor detection in abnormal magnetic resonance (MR) images. Fuzzy clustering using fuzzy C-means (FCM) algorithm proved to be superior over the other clustering approaches in terms of segmentation efficiency. But the major drawback of the FCM algorithm is the huge computational time required for convergence. The effectiveness of the FCM algorithm in terms of computational rate is improved by modifying the cluster center and membership value updation criterion. In this paper, the application of modified FCM algorithm for MR brain tumor detection is explored. Abnormal brain images from four tumor classes namely metastase, meningioma, glioma and astrocytoma are used in this work. A comprehensive feature vector space is used for the segmentation technique. Comparative analysis in terms of segmentation efficiency and convergence rate is performed between the conventional FCM and the modified FCM. Experimental results show superior results for the modified FCM algorithm in terms of the performance measures.

Performance Improved Iteration-Free Artificial Neural Networks for Abnormal Magnetic Resonance Brain Image Classification

Image classification is one of the typical computational applications widely used in the medical field especially for abnormality detection in Magnetic Resonance (MR) brain images. The automated image classification systems used for such applications must be significantly efficient in terms of accuracy since false detection may lead to fatal results. Another requirement is the high convergence rate which accounts for the practical feasibility of the system. Among the automated systems, Artificial Neural Network (ANN) is gaining significant positions for solving computational problems. Besides multiple advantages, there are also few drawbacks associated with the neural networks which are unnoticed for most of the applications. The main drawback is that the ANN which yields high accuracy requires high convergence time period and the ANN which are much quicker are usually inaccurate. Hence, there is a significant necessity for ANN which satisfies the criteria of high convergence rate and accuracy simultaneously. In this work, this drawback is tackled by proposing two novel neural networks namely Modified Counter Propagation Neural Network (MCPN) and Modified Kohonen Neural Network (MKNN). These networks are framed by performing modifications in the training methodology of conventional CPN and Kohonen networks. The main concept of this work is to make the ANN iteration-free which ultimately improves the convergence rate besides yielding accurate results. The performance of these networks are analysed in the context of abnormal brain image classification. Experimental results show promising results for the proposed networks in terms of the performance measures.

Distance metric-based time-efficient fuzzy algorithm for abnormal magnetic resonance brain image segmentation

Image segmentation is one of the significant computational applications of the biomedical field. Automated computational methodologies are highly preferred for medical image segmentation since these techniques are immune to human perception error. Artificial intelligence (AI)-based techniques are often used for this process since they are superior to other automated techniques in terms of accuracy and convergence time period. Fuzzy systems hold a significant position among the AI techniques because of their high accuracy. Even though these systems are exceptionally accurate, the time period required for convergence is exceedingly high. In this work, a novel distance metric-based fuzzy C-means (FCM) algorithm is proposed to tackle the low-convergence-rate problem of the conventional fuzzy systems. This modified approach involves the concept of distance-based dimensionality reduction of the input vector space that substantially reduces the iterative time period of the conventional FCM algorithm. The effectiveness of the modified FCM algorithm is explored in the context of magnetic resonance brain tumor image segmentation. Experimental results show promising results for the proposed approach in terms of convergence time period and segmentation efficiency. Thus, this algorithm proves to be highly feasible for time-oriented real-time applications.

Hand posture and gesture recognition techniques for virtual reality applications: a survey

Motion recognition is a topic in software engineering and dialect innovation with a goal of interpreting human signals through mathematical algorithm. Hand gesture is a strategy for nonverbal communication for individuals as it expresses more liberally than body parts. Hand gesture acknowledgment has more prominent significance in planning a proficient human computer interaction framework, utilizing signals as a characteristic interface favorable to circumstance of movements. Regardless, the distinguishing proof and acknowledgment of posture, gait, proxemics and human behaviors is furthermore the subject of motion to appreciate human nonverbal communication, thus building a richer bridge between machines and humans than primitive text user interfaces or even graphical user interfaces, which still limits the majority of input to electronics gadget. In this paper, a study on various motion recognition methodologies is given specific accentuation on available motions. A survey on hand posture and gesture is clarified with a detailed comparative analysis of hidden Markov model approach with other classifier techniques. Difficulties and future investigation bearing are also examined.

Brain signal based human emotion analysis by circular back propagation and Deep Kohonen Neural Networks

Abstract Human emotion analysis is one of the challenging tasks in todays scenario. The success rate of human emotion recognition has high implication in practical applications such as Human Machine Interaction, anomaly detection, surveillance, etc. Artificial Neural Networks (ANN) is one of the highly favored computational intelligence techniques for human emotion recognition. However, the performance of traditional ANN is not satisfactory in case of applications such as human emotion analysis. This leads to the necessity of modified ANN with better performance than the conventional systems. In this paper, we propose Circular Back Propagation Neural Network (CBPN) and Deep Kohonen Neural Network (DKNN) to overcome drawbacks of the traditional neural networks regarding computational complexity and accuracy. Performance of the proposals is explored in classifying different emotions of humans using Electroencephalography (EEG) signals. It has been validated that the proposals have better performance than the related methods.

A Hybrid Genetic Algorithm based Fuzzy Approach for Abnormal Retinal Image Classification

Fuzzy approaches are one of the widely used artificial intelligence techniques in the field of ophthalmology. These techniques are used for classifying the abnormal retinal images into different categories that assist in treatment planning. The main characteristic feature that makes the fuzzy techniques highly popular is their accuracy. But, the accuracy of these fuzzy logic techniques depends on the expertise knowledge, which indirectly relies on the input samples. Insignificant input samples may reduce the accuracy that further reduces the efficiency of the fuzzy technique. In this work, the application of Genetic Algorithm GA for optimizing the input samples is explored in the context of abnormal retinal image classification. Abnormal retinal images from four different classes are used in this work and a comprehensive feature set is extracted from these images as classification is performed with the fuzzy classifier and also with the GA optimized fuzzy classifier. Experimental results suggest highly accurate results for the GA based classifier than the conventional fuzzy classifier.

Self Organizing neural network based pathology classification in retinal images

Artificial neural networks are significantly used in the field of ophthalmology for accurate disease identification which further aids in treatment planning. In this paper, an automated system based on Self-Organizing neural network (Kohonen network) is proposed for eye disease classification. Abnormal retinal images from four different classes namely nonproliferative diabetic retinopathy (NPDR), Central retinal vein occlusion (CRVO), Choroidal neovascularisation membrane (CNVM) and Central serous retinopathy (CSR) are used in this work. A suitable feature set is extracted from the pre-processed images and fed to the classifier. Classification of the four eye diseases is performed using the unsupervised neural network. Experimental results show promising results for the Kohonen neural network as a disease classifier. The results are compared with the statistical classifier namely minimum distance classifier to justify the superior nature of neural network based classification.

Neural Computing Based Abnormality Detection in Retinal Optical Images

Automated eye disease identification systems facilitate the ophthalmologists in accurate diagnosis and treatment planning. In this paper, an automated system based on artificial neural network is proposed for eye disease classification, Abnormal retinal images from four different classes namely non-proliferative diabetic retinopathy (NPDR), Central retinal vein occlusion (CRVO), Choroidal neo-vascularisation membrane (CNVM) and Central serous retinopathy (CSR) are used in this work. A suitable feature set is extracted from the pre-processed images and fed to the classifier, Classification of the four eye diseases is performed using the supervised neural network namely back propagation neural network (BPN). Experimental results show promising results for the back propagation neural network as a disease classifier. The results are compared with the statistical classifier namely minimum distance classifier to justify the superior nature of neural network based classification.

Fuzzy Based Experimental Verification of Significance of Skull Tissue removal in Brain Tumor Image segmentation

In anatomical aspects, magnetic resonance (MR) imaging offers more accurate information for medical examination than other medical images such as X-ray, ultrasonic and CT images. Tumor segmentation from MRI data is an important but time consuming task performed manually by medical experts. Automating this process is challenging due to the high diversity in appearance of tumor tissue, among different patients and, in many cases, similarity between tumor and normal tissue. One of the reasons behind the inferior segmentation efficiency is the presence of artifacts in the MR images. One such artifact is the extracranial tissues (skull). These extracranial tissues often interfere with the normal tissues during segmentation that accounts for the inferior segmentation efficiency. In this paper, an automated segmentation and lesion detection algorithm for high segmentation efficiency is proposed for abnormal MR brain images. The proposed segmentation algorithm consists of three steps. In the first step, extracranial tissues are removed using morphological operations. In the second step, fuzzy C-means algorithm is used to segment the MR brain images into four groups: white matter, gray matter, cerebrospinal fluid and the abnormal tumor region. Finally, pseudo-colouring operation is performed on the segmented image to detect the abnormal tumor region. The proposed method has been applied to abnormal images from four different types namely metastase, meningima, glioma and astrocytoma.the superior nature of the proposed approach is justified by performing a comparative analysis on skull stripped images and non-skull stripped images. Experimental results suggest that the proposed approach provides an effective and promising method for brain tumor extraction from MR images with high accuracy.

Image Pre-processing and Feature Extraction Techniques for Magnetic Resonance Brain Image Analysis

Image pre-processing and feature extraction techniques are mandatory for any image based applications. The accuracy and convergence rate of such techniques must be significantly high in order to ensure the success of the subsequent steps. But, most of the time, the significance of these techniques remain unnoticed which results in inferior results. In this work, the importance of such approaches is highlighted in the context of Magnetic Resonance (MR) brain image classification and segmentation. In this work, suitable pre-processing techniques are developed to remove the skull portion surrounding the brain tissues. Also, texture based feature extraction techniques are also illustrated in this paper. The experimental results are analyzed in terms of segmentation efficiency for pre-processing and distance measure for feature extraction techniques. The convergence rate of these approaches is also discussed in this work. Experimental results show promising results for the proposed approaches.