8 August 2022 in Multimedia Tools and Applications
Convolutional neural network is widely used for image recognition in the medical area at nowadays. However, overall accuracy in predicting lung tumor is low and the processing time is high as the error occurred while reconstructing the CT image. The aim of this work is to increase the overall prediction accuracy along with reducing processing time by using multispace image in pooling layer of convolution neural network. The proposed method has the autoencoder system to improve the overall accuracy, and to predict lung cancer by using multispace image in pooling layer of convolution neural network and Adam Algorithm for optimization. First, the CT images were pre-processed by feeding image to the convolution filter and down sampled by using max pooling. Then, features are extracted using the autoencoder model based on convolutional neural network and multispace image reconstruction technique is used to reduce error while reconstructing the image which then results improved accuracy to predict lung nodule. Finally, the reconstructed images are taken as input for SoftMax classifier to classify the CT images. The state-of-art and proposed solutions were processed in Python Tensor Flow and It provides significant increase in accuracy in classification of lung cancer to 99.5 from 98.9 and decrease in processing time from 10 frames/second to 12 seconds/second. The proposed solution provides high classification accuracy along with less processing time compared to the state of art. For future research, large dataset can be implemented, and low pixel image can be processed to evaluate the classification.
5 September 2021 in Journal of Experimental & Theoretical Artificial Intelligence
Accurate classification of Magnetic Resonance Images (MRI) is essential to accurately predict Mild Cognitive Impairment (MCI) to Alzheimer’s Disease (AD) conversion. Meanwhile, deep learning has been successfully implemented to classify and predict dementia disease. However, the accuracy of MRI image classification is low. This paper aims to increase the accuracy and reduce the processing time of classification through Deep Learning Architecture by using Elastic Net Regularisation in Feature Selection. The proposed system consists of Convolutional Neural Network (CNN) to enhance the accuracy of classification and prediction by using Elastic Net Regularisation. Initially, the MRI images are fed into CNN for features extraction through convolutional layers alternate with pooling layers, and then through a fully connected layer. After that, the features extracted are subjected to Principle Component Analysis (PCA) and Elastic Net Regularisation for feature selection. Finally, the selected features are used as an input to Extreme Machine Learning (EML) for the classification of MRI images. The result shows that the accuracy of the proposed solution is better than the current system. In addition to that, the proposed method has improved the classification accuracy by 5% on average and reduced the processing time by 30 ~ 40 seconds on average. The proposed system is focused on improving the accuracy and processing time of MCI converters/non-converters classification. It consists of features extraction, feature selection, and classification using CNN, FreeSurfer, PCA, Elastic Net, and Extreme Machine Learning. Finally, this study enhances the accuracy and the processing time by using Elastic Net Regularisation, which provides important selected features for classification.
25 April 2022 in Multimedia Tools and Applications
4 November 2023 in Multimedia Tools and Applications
The aim of this research is to propose an extended mean value cloning algorithm with automatic trimap generation and accurate alpha matting. This implementation improves the visualization accuracy of the merged video by reducing the discolored and smudging artefacts of the remote surgeon’s boundary. It also makes the merge robust for the illumination changes by taking less processing time in real time surgery. The proposed system uses automatic trimap generation from the source video for accurate foreground extraction. Extended mean value cloning with gradient mixing is then applied for the cloning with optimized alpha matting for accurate and realistic video composition. The proposed system improved the visualization accuracy by providing almost 99.7% visibility of the pixels compared to the state-of-the-art solution, which provides 99.1% visibility of pixels. The overlay error was reduced from 0.93 mm to 0.63 mm. The processing time was also reduced. The proposed solution processed 8 frames per second, which is less time than the state-of-the-art solution, which processed 5 frames per second. The extended mean value cloning smooths the differences that presented in the target and source frames for seamless and realistic blending of pixels. The automatic trimap generation reduced the risk of false foreground selection and the generated optimal trimaps improved the alpha matte quality, which is optimized to reduce the smudging artefacts completely and to produce accurate visualization of the final merged image.