Iterative Convolutional Neural Network Research Articles

SF-ICNN: Spectral–Fractal Iterative Convolutional Neural Network for Classification of Hyperspectral Images

One primary concern in the field of remote-sensing image processing is the precise classification of hyperspectral images (HSIs). Lately, deep-learning models have demonstrated cutting-edge results in HSI classification. Despite this, researchers continue to study and propose simpler, more robust models. This study presents a novel deep-learning approach, the iterative convolutional neural network (ICNN), which combines spectral–fractal features and classifier probability maps iteratively, aiming to enhance the HSI classification accuracy. Experiments are conducted to prove the accuracy enhancement of the proposed method using HSI benchmark datasets of Indian pine (IP) and the University of Pavia (PU) to evaluate the performance of the proposed technique. The final results show that the proposed approach reaches overall accuracies of 99.16% and 95.5% on the IP and PU datasets, respectively, which are better than some basic methods. Additionally, the end findings demonstrate that greater accuracy levels might be achieved using a primary CNN network that employs the iteration loop than with certain current state-of-the-art spatial–spectral HSI classification techniques.

Robust Frontal Vehicle Pose Estimation Based on Structural Parameter Optimization Using Reliable Edge Point Sequences

In order to enhance the stability of vehicle pose estimation within driving videos, a novel methodology for optimizing vehicle structural parameters is introduced. This approach hinges on evaluating the reliability of edge point sequences. Firstly, a multi−task and iterative convolutional neural network (MI−CNN) is constructed, enabling the simultaneous execution of four critical tasks: vehicle detection, yaw angle prediction, edge point location, and visibility assessment. Secondly, an imperative aspect of the methodology involves establishing a local tracking search area. This region is determined by modeling the limitations of vehicle displacement between successive frames. Vehicles are matched using a maximization approach that leverages point similarity. Finally, a reliable edge point sequence plays a pivotal role in resolving structural parameters robustly. The Gaussian mixture distribution of vehicle distance change ratios, derived from two measurement models, is employed to ascertain the reliability of the edge point sequence. The experimental results showed that the mean Average Precision (mAP) achieved by the MI−CNN network stands at 89.9%. A noteworthy observation is that the proportion of estimated parameters whose errors fall below the threshold of 0.8 m consistently surpasses the 85% mark. When the error threshold is set at less than 0.12 m, the proportion of estimated parameters meeting this criterion consistently exceeds 90%. Therefore, the proposed method has better application status and estimation precision.

Noise Removal-based Thresholding framework for Arrhythmia classification

Electrocardiogram (ECG) signal analyses can enhance human life in various ways, from detecting and treating heart illness to controlling the lives of cardiac-diseased people. ECG analysis has become crucial in medical studies for accurately detecting cardiovascular diseases (CVDs). Cardiac Arrhythmia is one of the major life-threatening diseases. Analyzing ECG signals is the easiest way to detect Arrhythmia. Different noises often corrupt the ECG signals, like power line interference, electromyographic (EMG) noise, and electrode motion artifact noise. Such noises make it difficult to identify the various peaks in the ECG signal for arrhythmia classification. To overcome such problems, Noise Removal-based Thresholding (NRT) framework has been introduced to remove noises from ECG signals and accurately classify Arrhythmia. Discrete Wavelet transform reduces noise from ECG signals in the pre-processing stage. The noise-removed signal is segmented by K-means clustering for R-peak detection by finding all local maximum points from the signal. The signal features are extracted by Burg’s method to obtain good frequency resolution and quick integration for short-time signals in the form of a cumulative distribution function. All features collected from R-peak are fed to the Iterative Convolutional Neural Network (ICNN) and classified the arrhythmia types based on the alignment of a few variables to work well with the Euclidean distance metric. The NRT framework is evaluated based on the data obtained from the MIT-BIH Arrhythmia dataset and achieves the Accuracy of 99.45 %, Positive Prediction of 98.92%, F1-Score of 98.95%, SNR of 35 dB, MSE of 0.001, RMSE of 0.002

COVID-19 infection prediction from CT scan images of lungs using Iterative Convolution Neural Network model

World Health Organization has defined COVID-19 as a contagious, communicable and fast spreading disease engendered by the Corona virus, SARS-CoV-2, is a respirational microorganism. Computerized Tomography (CT) scan images of the chest helps in detecting COVID 19 infection in a fast way with much reliability. In this paper, chest CT scan images of COVID and Non-COVID categories are considered to train the supervised classifier, Iterative convolution Neural Network. The training process is done with six different training data size. The trained models are iterated for the fixed size of testing data (20 images). The same set of training and testing processes are done with two different Iterative Convolutional Neural Network architectures, one with two hidden layers (CNN1) and another with three hidden layers (CNN2). The iterations are extended up to 7, but the model performance is degraded after the 6th iteration, which makes to fix the iteration level as 5 for both CNN models. Six different training sets with five iterations have led into 30 CNN models. For two different CNN architectures, which lead to 60 different models. The model designed with 100 training sets in both CNN1 and CNN2, have produced the high accuracy in COVID classification than any other models. The better classification accuracy 89% is achieved from CNN2 model with its 5th iteration.

Multiscale segmentation- and error-guided iterative convolutional neural network for cerebral neuron segmentation in microscopic images.

This article uses microscopy images obtained from diverse anatomical regions of macaque brain for neuron semantic segmentation. The complex structure of brain, the large intra-class staining intensity difference within neuron class, the small inter-class staining intensity difference between neuron and tissue class, and the unbalanced dataset increase the difficulty of neuron semantic segmentation. To address this problem, we propose a multiscale segmentation- and error-guided iterative convolutional neural network (MSEG-iCNN) to improve the semantic segmentation performance in major anatomical regions of the macaque brain. After evaluating microscopic images from 17 anatomical regions, the semantic segmentation performance of neurons is improved by 10.6%, 4.0%, 1.5%, and 1.2% compared with Random Forest, FCN-8s, U-Net, and UNet++, respectively. Especially for neurons with brighter staining intensity in the anatomical regions such as lateral geniculate, globus pallidus and hypothalamus, the performance is improved by 66.1%, 23.9%, 11.2%, and 6.7%, respectively. Experiments show that our proposed method can efficiently segment neurons with a wide range of staining intensities. The semantic segmentation results are of great significance and can be further used for neuron instance segmentation, morphological analysis and disease diagnosis. Cell segmentation plays a critical role in extracting cerebral information, such as cell counting, cell morphometry and distribution analysis. Accurate automated neuron segmentation is challenging due to the complex structure of brain, the large intra-class staining intensity difference within neuron class, the small inter-class staining intensity difference between neuron and tissue class, and the unbalanced dataset. The proposed multiscale segmentation- and error-guided iterative convolutional neural network (MSEG-iCNN) improve the segmentation performance in 17 major anatomical regions of the macaque brain. HIGHLIGHTS: Cell segmentation plays a critical role in extracting cerebral information, such as cell counting, cell morphometry and distribution analysis. Accurate automated neuron segmentation is challenging due to the complex structure of brain, the large intra-class staining intensity difference within neuron class, the small inter-class staining intensity difference between neuron and tissue class, and the unbalanced dataset. The proposed multiscale segmentation- and error-guided iterative convolutional neural network (MSEG-iCNN) improve the segmentation performance in 17 major anatomical regions of the macaque brain.

Neural Reference Synthesis for Inter Frame Coding

This work proposes the neural reference synthesis (NRS) to generate high-fidelity reference block for motion estimation and motion compensation (MEMC) in inter frame coding. The NRS is comprised of two submodules: one for reconstruction enhancement and the other for reference generation. Although numerous methods have been developed in the past for these two submodules using either handcrafted rules or deep convolutional neural network (CNN) models, they basically deal with them separately, resulting in limited coding gains. By contrast, the NRS proposes to optimize them collaboratively. It first develops two CNN-based models, namely EnhNet and GenNet. The EnhNet only uses spatial correlations within the current frame for reconstruction enhancement and the GenNet is then augmented by further aggregating temporal correlations across multiple frames for reference synthesis. However, a direct concatenation of EnhNet and GenNet without considering the complex temporal reference dependency across inter frames would implicitly induce iterative CNN processing and cause the data overfitting problem, leading to visually-disturbing artifacts and oversmoothed pixels. To tackle this problem, the NRS applies a new training strategy to coordinate the EnhNet and GenNet for more robust and generalizable models, and also devises a lightweight multi-level R-D (rate-distortion) selection policy for the encoder to adaptively choose reference blocks generated from the proposed NRS model or conventional coding process. Our NRS not only offers state-of-the-art coding gains, e.g., >10% BD-Rate (Bjøntegaard Delta Rate) reduction against the High Efficiency Video Coding (HEVC) anchor for a variety of common test video sequences encoded at a wide bit range in both low-delay and random access settings, but also greatly reduces the complexity relative to existing learning-based methods by utilizing more lightweight DNNs. All models are made publicly accessible at https://github.com/IVC-Projects/NRS for reproducible research.

An end-to-end-trainable iterative network architecture for accelerated radial multi-coil 2D cine MR image reconstruction.

Iterative convolutional neural networks (CNNs) which resemble unrolled learned iterative schemes have shown to consistently deliver state-of-the-art results for image reconstruction problems across different imaging modalities. However, because these methods include the forward model in the architecture, their applicability is often restricted to either relatively small reconstruction problems or to problems with operators which are computationally cheap to compute. As a consequence, they have not been applied to dynamic non-Cartesian multi-coil reconstruction problems so far. In this work, we propose a CNN architecture for image reconstruction of accelerated 2D radial cine MRI with multiple receiver coils. The network is based on a computationally light CNN component and a subsequent conjugate gradient (CG) method which can be jointly trained end-to-end using an efficient training strategy. We investigate the proposed training strategy and compare our method with other well-known reconstruction techniques with learned and non-learned regularization methods. Our proposed method outperforms all other methods based on non-learned regularization. Further, it performs similar or better than a CNN-based method employing a 3D U-Net and a method using adaptive dictionary learning. In addition, we empirically demonstrate that even by training the network with only iteration, it is possible to increase the length of the network at test time and further improve the results. End-to-end training allows to highly reduce the number of trainable parameters of and stabilize the reconstruction network. Further, because it is possible to change the length of the network at the test time, the need to find a compromise between the complexity of the CNN-block and the number of iterations in each CG-block becomes irrelevant.

Image saliency detection via multi-scale iterative CNN

Salient object detection has received increasingly more attention and achieved significant progress lately due to the powerful features learned by deep convolutional neural networks (CNNs). In this work, we propose a multi-scale iterative CNN for salient object detection, which has two complementary subnetworks at different spatial scales. For each subnetwork, we augment the CNN structures with an iterative learning process to learn the saliency map, where early stages of the CNN give a rough estimate of the saliency map and the remaining errors are gradually learned to refine the saliency map. By merging predictions of the two subnetworks, the training error can be reduced significantly and the estimated saliency map becomes more accurate. Unlike some previous CNN-based methods which often rely on superpixel segmentations, the proposed model is fully CNN and hence can estimate the saliency map much more efficiently. Extensive experiments on standard benchmarks demonstrate that our method outperforms some of the state-of-the-art methods in terms of both accuracy and speed and achieves as good performance as some recent state-of-the-art end-to-end methods under fair settings.

Vehicle Detection in High-Resolution Images Using Superpixel Segmentation and CNN Iteration Strategy

This letter presents a study of vehicle detection in high-resolution images using superpixel segmentation and iterative convolutional neural network strategy. First, a novel superpixel segmentation integrated with multiple local information constraints method is proposed to improve the segmentation results with a low breakage rate. To make training and detection more efficient, we extract meaningful and nonredundant patches based on the centers of the segmented superpixels. For reducing the instability in detection performance because of manual or random selection of samples, a training sample iterative selection strategy based on convolutional neural network is proposed. After a compact training sample subset is obtained from the original entire training set, a representative feature set with high discrimination ability between vehicle and background is extracted from these selected samples for detection. To further avoid overfitting the training and promote the detection efficiency, data augment and a main direction estimation method are used. Comparative experimental results on Toronto data indicated the effectiveness of our proposed method.

Human Activity Classification With Radar: Optimization and Noise Robustness With Iterative Convolutional Neural Networks Followed With Random Forests

The accurate classification of activity patterns based on radar signatures is still an open problem and is a key to detect anomalous behavior for security and health applications. This paper presents a novel iterative convolutional neural network strategy with an autocorrelation pre-processing instead of the traditional micro-Doppler image pre-processing to classify activities or subjects accurately. The proposed strategy uses an iterative deep learning framework for the automatic definition and extraction of features. This is followed by a traditional supervised learning classifier to label different activities. Using three human subjects and their real motion captured data, 12 000 radar signatures were simulated by varying additive white Gaussian noise. In addition, 6720 experimental radar signatures were captured with a frequency-modulated continuous radar at 5.8 GHz with 400 MHz of instantaneous bandwidth from seven activities using one subject and 4800 signatures from five subjects while walking. The simulated and experimental data were both used to validate our proposed method, with signal–noise ratio varying from −20 to 20 dB and with 88.74% average accuracy at −10 dB and 100% peak accuracy at 15 dB. The proposed iterative convolutional neural networks followed with random forests not only outperform the feature-based methods using micro-Doppler images but also outperform the classification methods using other types of supervised classifiers after our proposed iterative convolutional neural network.

Zebrafish tracking using convolutional neural networks

Keeping identity for a long term after occlusion is still an open problem in the video tracking of zebrafish-like model animals, and accurate animal trajectories are the foundation of behaviour analysis. We utilize the highly accurate object recognition capability of a convolutional neural network (CNN) to distinguish fish of the same congener, even though these animals are indistinguishable to the human eye. We used data augmentation and an iterative CNN training method to optimize the accuracy for our classification task, achieving surprisingly accurate trajectories of zebrafish of different size and age zebrafish groups over different time spans. This work will make further behaviour analysis more reliable.