Evaluation of Ripplet Transform as a Texture Characterization for Iris Recognition

Khoje, Suchitra; Shinde, Sagar

doi:10.1007/s40031-023-00863-6

Cited by 7 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An RoI (Region of Interest) feature extractor can be used to extract various features from a given set of photos. For instance, it can perform object detection through boundary boxes (Khoje and Shinde 2023). The texture based and edge with shape-based feature extraction to get region of interest is shown in Figure 17 and Figure 18 The flow of results of proposed system has been shown in Figure 19 through experimental demonstration whether the currency we've analyzed is real or fake.…”

Section: Simulation Results and Discussionmentioning

confidence: 99%

Identification of fake currency using soft computing

Shinde,

Wadhwa,

Bhalke

et al. 2023

Multidiscip. Sci. J.

View full text Add to dashboard Cite

Advancements in color printing techniques have led to a surge in the creation and duplication of counterfeit currency notes, which has become prevalent in India. Although it was previously difficult to carry out this type of operation, anyone with a laser printer now has the capability to do it. This issue is considered a major problem due to the country's various problems, such as frauds, corruption and black money. It is needed to develop the system for the detection of fake currency. A system that can quickly identify counterfeit money is being developed. The proposed solution will utilize image processing to authenticate Indian currency notes. The proposed system will involve extracting different features from the notes, such as the security thread, Bleed Line, edges, shapes, textures, colors and Fluorescence. It is being developed using the software known as MATLAB. The supervised learning model of support vector machine for the extraction of the notes' features is also being used. This is utilized for analyzing the data related to classification and regression. Once the statistical features have been extracted, they were matched with the features stored in MAT file using SVM (Support Vector Machine) classifier. We have also conducted a test of other methods, such as the black box algorithm. The proposed solution is very fast and simple to implement, allowing it to identify if the notes are fake or real. The outcome of proposed system is the remarkable working of proposed system for the detection of fake currency and accuracy has been measured with the help of confusion matrix. The accuracy, precision & F- score are best by using SVM as compare to SVC (support Vector Classifier) & GBC (Genetic Bee Colony) algorithm.

show abstract

Section: Simulation Results and Discussionmentioning

confidence: 99%

Identification of fake currency using soft computing

Shinde,

Wadhwa,

Bhalke

et al. 2023

Multidiscip. Sci. J.

View full text Add to dashboard Cite

show abstract

“…This proposed compiler optimization model comprises three working phases: model training, feature extraction [24,25], as well as model exploitation (feature selection). First, the inputs were fed into the model training phase, which tries to match the right weights as well as bias to a learning algorithm [26,27] in order to minimize a loss function throughout the validation range. The retrieved characteristics, such as static, dynamic, as well as improved entropy, were then transferred to the model exploitation phase [21], where the optimal features were chosen utilizing the improved chaos game optimization.…”

Section: Proposed Compiler Optimization Prediction Modelmentioning

confidence: 99%

“…Outputs from model training phase were given to the feature extraction phase to extract the static, dynamic and improved entropy features [26,27].…”

Section: B Feature Extractionmentioning

confidence: 99%

Compiler Optimization Prediction with New Self-Improved Optimization Model

Shewale¹,

Shinde²,

Gurav³

et al. 2023

IJACSA

View full text Add to dashboard Cite

Users may now choose from a vast range of compiler optimizations. These optimizations interact in a variety of sophisticated ways with one another and with the source code. The order in which optimization steps are applied can have a considerable influence on the performance obtained. As a result, we created a revolutionary compiler optimization prediction model. Our model comprises three operational phases: model training, feature extraction, as well as model exploitation. The model training step includes initialization as well as the formation of candidate sample sets. The inputs were then sent to the feature extraction phase, which retrieved static, dynamic, and improved entropy features. These extracted features were then optimized by the feature exploitation phase, which employs an improved hunger games search algorithm to choose the best features. In this work, we used a Convolutional Neural Network to predict compiler optimization based on these selected characteristics, and the findings show that our innovative compiler optimization model surpasses previous approaches.

show abstract

“…It offers three options to choose from, and it can perform various tasks to decrease, remove, and sort the features. One of the most common issues that researchers encounter when it comes to developing machine learning systems is overfitting (Khoje and Shinde 2023). This occurs when the training model starts to learn the underlying relationships and patterns instead of learning the details of the training (Shewale et al 2023).…”

Section: Data Pre-processingmentioning

confidence: 99%

Artificial intelligence approach for terror attacks prediction through machine learning

Shinde,

Khoje,

Raj

et al. 2023

Multidiscip. Sci. J.

View full text Add to dashboard Cite

The rise of terrorism has become a global threat that affects every continent and country. Due to the complexity of the situation, and the technological developments that have occurred in the field, attacks and incidents have become more difficult to manage. To prevent these types of attacks, countries and organizations have started using various techniques such as machine learning and artificial intelligence.The goal of this paper is to create a framework that allows users to visualize the various characteristics of terrorist attacks by extracting data from the Global Terrorism database. The graph embedding process is performed by using two different methods.The coding approach was used for the non-coding model development. The data collected by the project were then fed to seven different machine learning models. These models included Random forest, KNN, adaboost, decision trees, and SVM. The classification accuracy of the two methods was estimated to be around 90%.

show abstract

Evaluation of Ripplet Transform as a Texture Characterization for Iris Recognition

Cited by 7 publications

References 11 publications

Identification of fake currency using soft computing

Identification of fake currency using soft computing

Compiler Optimization Prediction with New Self-Improved Optimization Model

Artificial intelligence approach for terror attacks prediction through machine learning

Contact Info

Product

Resources

About