“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Currently, we witness the severe spread of the pandemic of the new Corona virus, COVID-19, which causes dangerous symptoms to humans and animals, its complications may lead to death. Although convolutional neural networks (CNNs) is considered the current state-of-the-art image classification technique, it needs massive computational cost for deployment and training. In this paper, we propose an improved hybrid classification approach for COVID-19 images by combining the strengths of CNNs (using a powerful architecture called Inception) to extract features and a swarm-based feature selection algorithm (Marine Predators Algorithm) to select the most relevant features. A combination of fractional-order and marine predators algorithm (FO-MPA) is considered an integration among a robust tool in mathematics named fractional-order calculus (FO). The proposed approach was evaluated on two public COVID-19 X-ray datasets which achieves both high performance and reduction of computational complexity. The two datasets consist of X-ray COVID-19 images by international Cardiothoracic radiologist, researchers and others published on Kaggle. The proposed approach selected successfully 130 and 86 out of 51 K features extracted by inception from dataset 1 and dataset 2, while improving classification accuracy at the same time. The results are the best achieved on these datasets when compared to a set of recent feature selection algorithms. By achieving 98.7%, 98.2% and 99.6%, 99% of classification accuracy and F-Score for dataset 1 and dataset 2, respectively, the proposed approach outperforms several CNNs and all recent works on COVID-19 images.

/pdf/covid-19-image-classification-using-deep-features-and-3so55ekumz.pdf

COVID-19 image classification using deep features and fractional-order marine predators algorithm.

Multimodal medical image fusion review: Theoretical background and recent advances

Attractive-and-repulsive center-symmetric local binary patterns for texture classification

Oil tank detection is a challenging task, primarily due to high time-consumption. This paper aims at further investigating this challenge and proposes a new hierarchical approach to detect oil tank...

A new approach for oil tank detection using deep learning features with control false alarm rate in high-resolution satellite imagery

Local diagonal extrema number pattern

Automated pneumonia detection on chest X-ray images: A deep learning approach with different optimizers and transfer learning architectures

In this paper, we present a novel neural network using multi scale feature fusion at various scales for accurate and efficient semantic image segmentation. We used ResNet based feature extractor, dilated convolutional layers in downsampling part, atrous convolutional layers in the upsampling part and used concat operation to merge them. A new attention module is proposed to encode more contextual information and enhance the receptive field of the network. We present an in depth theoretical analysis of our network with training and optimization details. Our network was trained and tested on the Camvid dataset and Cityscapes dataset using mean accuracy per class and Intersection Over Union (IOU) as the evaluation metrics. Our model outperforms previous state of the art methods on semantic segmentation achieving mean IOU value of 74.12 while running at >100 FPS.

Semantic Segmentation With Multi Scale Spatial Attention For Self Driving Cars

Adaptive Pedestrian Detection in Infrared Images Using Background Subtraction and Local Thresholding

Medical imaging requires capturing different aspects of a human body. To capture tissues, cartilages, bones and nerves one needs different sensors and different modalities which results in different images from each modality of the same body part. Image fusion is a process by which one can fuse such images from different modalities in a single image. In this paper, a novel DWT-type2 fuzzy method is proposed to fuse two images (CT and MRI images). In this method, initially, the source images are decomposed into low-level and high-level subbands by discrete wavelet transformation (DWT). As the second step, for fusion, Type-2 fuzzy technique is applied on a low-level subband and average fusion method is applied on the high-level subbands in order to enhance the most prominent features present in CT image and MRI image. Finally, the fused low-level subband and highlevel subbands are reconstructed to form the final fused image using inverse-DWT. To test the proposed fusion method, the experiment is carried out on the MRI-T2 image, functional MRI image and CT image. The fused images have been subjectively and objectively evaluated based on certain evaluation measures and the obtained results have been presented in the paper. From the results, one can observe that the proposed method provides an improvement over other primitive fusion methods.

Rajkumar Soundrapandiyan

Papers

Local diagonal extrema number pattern

Automated pneumonia detection on chest X-ray images: A deep learning approach with different optimizers and transfer learning architectures

Semantic Segmentation With Multi Scale Spatial Attention For Self Driving Cars

Adaptive Pedestrian Detection in Infrared Images Using Background Subtraction and Local Thresholding

CT and MRI Image Fusion Based on Discrete Wavelet Transform and Type-2 Fuzzy Logic