Search

Image fusions are that join medical images from many modalities like CTS (Computed Tomography Scans) and MRI (Magnetic Resonance Imaging) with the aim of presenting better clinical content to clinicians and doctorsfor planning treatments or therapies. Prior studies based on white images have showed issues in early predictions of brain tumours like inaccurate image. This study attempts to overcome this issue by comparing MUNets (Modified-UNets), MCNNs (Multi-Cascaded ConvolutionNeural Networks) with fully connected CRFs (Conditional Random Fields), MFCLs (Modified Fully Connected Layers), TA-cGANs (Tissue-Aware conditional Generative Adversarial Networks) and EL (Ensemble Learning) algorithms. Furthermore, in order to enhance image quality and enable the early diagnosis of brain tumours, novel multimodal medical image fusion techniques are being examined. Furthermore, it is suggested that the EL algorithm improve MRI brain image fusion performance. The four primary phases of the suggested system are segmentation, image synthesis, feature extraction, and noise reduction. To eliminate noises, AMFs (Adaptive Median Filters) are used for reducing noises in MRI images and thus assist in enhancing classification accuracies. These features are taken into segmentation process using RGKMC (Region Growing based K-Means Clustering). Feature extractions are performed using AFFOCNNs (Adaptive FireFly Optimization based Convolution Neural Networks) algorithm which computes necessary and prominent features. Subsequently, MCCNNs, MUNets, MFCLs, TAcGANs and EL algorithms are applied for classifications through training and testing models. They classify features more accurately using their informative features. The experimental result proves that ELalgorithms provides better classificationsthan the MCCNNs, MUNets, MFCLs and TA-cGANs when evaluated in terms of higher accuracies, precisions, recalls and reduced MSEs (Mean Square Errors), execution times [ABSTRACT FROM AUTHOR]

India is an agricultural country; wherein about 70% of the population depends on agriculture. Agriculture has changed more in the past century than it has since farming began many millennia ago. Research in agriculture is aimed towards increase of productivity and food quality at reduced expenditure and with increased profit. Current crop production practices, often called Precision Agriculture (PA), benefited from all earlier revolutions in crop production. Many times expert advice may not be affordable, majority times the availability of expert and their services may consume time. Image processing along with availability of communication network can change the situation of getting the expert advice well within time and at affordable cost since image processing was the effective tool for analysis of parameters. Image processing techniques in agriculture are mainly used for image categorization based on shape, size, color and texture for decision-making. This leads to agricultural input rationalization and environmental damage reduction by adjusting the agricultural practices like fertilizer and pesticide application to the site that demands and profit maximization. This paper intends to focus on the survey of application of image processing in agriculture field such as imaging techniques, weed detection and fruit grading. This paper presents a survey on some of the existing image processing techniques in agriculture. [ABSTRACT FROM AUTHOR]