Multi-Lingual Character Recognition and Extraction using Recurrent Neural Networks
A Novel Approach to Smart Autonomous Monitoring of Indoor Plant Health Based on Leaf Color
Edge Preserving Image Denoising with Deep Networks and Ensemble Convolutional Neural Network Architectures
Neural Network Approach to Detect Renal Calculi
Enhancing Fabric Quality Control: Implementing Real-Time Defect Detection with Image Processing Techniques and Arduino
Identification of Volcano Hotspots by using Resilient Back Propagation (RBP) Algorithm Via Satellite Images
Data Hiding in Encrypted Compressed Videos for Privacy Information Protection
Improved Video Watermarking using Discrete Cosine Transform
Contrast Enhancement based Brain Tumour MRI Image Segmentation and Detection with Low Power Consumption
Denoising of Images by Wavelets and Contourlets using Bi-Shrink Filter
Telugu Character Recognition (TCR) has received significant attention because of the drastic increase in technological advancements such as multimedia, smartphones and iPods, and paper documents. Offline character recognition is the process of identifying Telugu characters from the scanned image or document whereas online character recognition enables to recognition of characters by the machine while the user writes. Several researchers have attempted to design online TCR models by the use of distinct classification models and feature extraction approaches. It is still necessary to construct automated and intelligent online TCR models, even if many studies have focused on offline TCR models. The Telugu character dataset construction and validation using an Inception and ResNet-based model are presented. The collection of 645 letters in the dataset includes 18 Achus, 38 Hallus, 35 Othulu, 34*16 Guninthamulu and 10 Ankelu. The proposed technique aims to efficiently recognize and identify distinctive Telugu characters online. This model's main preprocessing steps to achieve its goals include normalization, smoothing, and interpolation. Improved recognition performance can be attained by using Stochastic Gradient Descent (SGD) to optimize the model's hyperparameters.
Breast Cancer is a highly lethal reproductive cancer that disproportionately affects women and is a leading cause of death worldwide. Cancer is characterized by the uncontrolled division and invasion of abnormal cells into the surrounding tissues. Early detection is crucial in the diagnosis of Breast Cancer, as it accounts for a significant percentage of cancer diagnoses and deaths among women. To prevent unnecessary tests, accurate classification of malignant and benign tumors is necessary. Researchers have developed numerous automated classification methods for Breast Cancer, with soft computing techniques being widely used due to their high performance in classification. Machine learning algorithms, known for their ability to identify critical features from medical datasets, are also extensively utilized in Breast Cancer prediction. Therefore, this study seeks to employ Boosting algorithms in machine learning to predict Breast Cancer accurately. Over the years, the mortality rate in Breast Cancer diagnosis has decreased due to research efforts.
Artificial Intelligence (AI) is a domain that works on various complex applications, such as E-government services. In order to provide government services to the people, an online AI-based Deep Learning (DL) model has been developed to check the availability of government schemes. However, several E-government services are not available to the citizens based on their usage. Many challenges have been identified while using E-Government services. This paper introduces the DL model, Convolutional Neural Networks (CNN), to solve the issues in E-Government services. The system focuses on maintaining E-government data resources, and CNN is primarily used to automate E-Government services. Finally, CNN has developed an innovative E-Government environment to support the design, development, and implementation of applications.
The decreased production of dopamine in the forebrain is believed to be the underlying cause of Parkinson's disease, a neurodegenerative disorder that affects the nervous system. Parkinson's disease is a chronic and progressive illness that may develop new symptoms over time (Nilashi et al., 2016). This occurs as neurons in the substantia nigra of the brain gradually die. People with Parkinson's disease may find it difficult to perform everyday tasks in the workplace. Although clinical evaluations consider a significant amount of data that includes various aspects, it is not always easy to determine whether a person has PD based on this data alone. Feature selection methods can help address this issue. Various techniques are being researched, developed, and evaluated for diagnosing Parkinson's disease, based on the relevant information. This study provides an overview of the use of machine learning algorithms to predict Parkinson's disease, as well as the various new technologies that have been developed and the accuracy that has been achieved.
Glaucoma is a progressive eye condition that causes loss of vision and cannot be restored once it has occurred. The diagnosis of glaucoma is an important issue that has to be resolved in the realm of medicine. There have only been a limited number of research efforts aimed at detecting glaucoma in its earlier stages. Nevertheless, the performance of glaucoma illness identification utilizing the various approaches that are now available was ineffective. In addition to this, the time commitment involved in traditional methods of glaucoma illness identification was significantly higher. Finding glaucoma in color fundus photos is a difficult undertaking that calls both knowledge as well as years of practice. Deep learning techniques have rapidly emerged as a method of choice for the analysis of medical pictures. In this study, we took advantage of the application of various Convolutional Neural Networks (CNN) schemes to demonstrate the influence on performance of relevant factors such as the size of the data set, architecture, and the use of transfer learning versus newly defined architectures at an early stage with higher accuracy and a lower amount of time. Specifically, we compared the two types of architectures in terms of their ability to learn from previous examples. Deep learning techniques have rapidly emerged as a method of choice for the analysis of medical pictures. This study examines the primary deep learning ideas that are applicable to medical image analysis and provides a summary of the contributions to the area. We take a look at the application of deep learning to various image processing tasks such as classification, object identification, segmentation, and registration.
