Search

Glaucoma is the most common reason for permanent blindness and disability in the universe. Despite this, the vast majority of people are unaware that they have the infection, and detecting glaucoma progression with current technology continues to be a challenge in clinical research. The implementation of a machine-learning algorithm to the retinal fundus image gives a solution. In this research, 250 glaucomatous and 250 healthy retinal fundus images from the ACRIMA. For cleaning the data some pre-processing techniques are used. The feature extraction techniques such as Gray-Level Co-occurrence Matrix (GLCM), Gray Level Run-Length Matrix (GLRM), and Histogram of Oriented Gradients (HOG) are applied to the clean data. This process helps to retrieve beneficial information from the data. Finally, the retrieved features are taken as input to the machine learning classifier such as Support Vector Machine (SVM), Naive Bayes, K-Nearest Neighbor (K-NN), and Linear Discriminant Analysis (LDA) to construct the model. For assessment of feature extraction and classification, several performance metrics like accuracy, True and False Positive Rate (TPR/FPR), True and False Negative Rate (TNR/FNR), precision, and Performance Index (PI) are used. From the analysis, it is found that the GLCM feature extraction with the Naive Bayes model is the finest combination and it gives a 95% accuracy level.

In an image, if a particular part or region is copied and further pasted in another part of the image, it is a type of image forgery known as region duplication or copy-move. This technique is commonly used to either conceal an object or to overemphasize on a particular object. There are a number of detection methodologies introduced over the years to identify copy-move images. But when the image is hidden in smooth background, it proves to be difficult to identify and localize. A novel method of localization of the forgery has been proposed with the help of FQRHFM (Fast Quanternion Radial Harmonic Fourier Moments) and SIFER (Scale-invariant feature detection with error resilience). The initial step involves splitting the image into segments that can be represented as uniform superpixel and non-overlapping blocks. Based on the extraction of key points, SIFER is used by incorporating color invariance and super pixel content. The next step involves using the extracted image key points to build an image with connected Delaunay triangle such that every triangle is formulated with gradient entropy and FQRHFMs. The last step would be to use the extracted features to match with the triangles and those that do not match will be removed as duplicated regions.

AdHoc network plays an important role for critical scenario such as military services, law enforcement as well as in emergency rescue operation. In such type of request, it requires security and privacy for the underlying routing protocol. As it is a communications less and source limit network, it is very important to propose secure based energy efficient routing protocol. In order to provide a secure and energy efficient routing protocol, a Privacy Protecting Secure and Energy Efficient Routing Protocol (PPSEER) is proposed. In this protocol, first the classifications of network node take place based on their energy level. After that encryption is done based on group signature. It includes additional secure parameter such as secret key and maximum transmission power which is known only to the sender and recipient node. The advantage of the proposed routing protocol is that it increases privacy of the message as well as it maintains the energy efficiency of the node.