scholarly journals Blood Vessel Segmentation of Retinal Image Based on Dense-U-Net Network

Micromachines ◽  
2021 ◽  
Vol 12 (12) ◽  
pp. 1478
Author(s):  
Zhenwei Li ◽  
Mengli Jia ◽  
Xiaoli Yang ◽  
Mengying Xu
Keyword(s):  
Histogram Equalization ◽  
Training Data ◽  
Stochastic Gradient Descent ◽  
Practical Significance ◽  
Morphological Transformation ◽  
Small Vessels ◽  
Multi Scale ◽  
Retinal Blood Vessels ◽  
Segmentation Accuracy ◽  
Adaptive Gamma Correction

The accurate segmentation of retinal blood vessels in fundus is of great practical significance to help doctors diagnose fundus diseases. Aiming to solve the problems of serious segmentation errors and low accuracy in traditional retinal segmentation, a scheme based on the combination of U-Net and Dense-Net was proposed. Firstly, the vascular feature information was enhanced by fusion limited contrast histogram equalization, median filtering, data normalization and multi-scale morphological transformation, and the artifact was corrected by adaptive gamma correction. Secondly, the randomly extracted image blocks are used as training data to increase the data and improve the generalization ability. Thirdly, stochastic gradient descent was used to optimize the Dice loss function to improve the segmentation accuracy. Finally, the Dense-U-net model was used for segmentation. The specificity, accuracy, sensitivity and AUC of this algorithm are 0.9896, 0.9698, 0.7931, 0.8946 and 0.9738, respectively. The proposed method improves the segmentation accuracy of vessels and the segmentation of small vessels.

Cloning Safe Driving Behavior for Self-Driving Cars using Convolutional Neural Networks

2019 ◽  
Vol 12 (2) ◽  
pp. 120-127 ◽  
Author(s):  
Wael Farag
Keyword(s):  
Gradient Descent ◽  
Autonomous Driving ◽  
Driving Behavior ◽  
Training Data ◽  
Stochastic Gradient Descent ◽  
Data Set ◽  
Safe Driving ◽  
Processing Pipeline ◽  
Self Driving Cars ◽  
And Training

Background: In this paper, a Convolutional Neural Network (CNN) to learn safe driving behavior and smooth steering manoeuvring, is proposed as an empowerment of autonomous driving technologies. The training data is collected from a front-facing camera and the steering commands issued by an experienced driver driving in traffic as well as urban roads. Methods: This data is then used to train the proposed CNN to facilitate what it is called “Behavioral Cloning”. The proposed Behavior Cloning CNN is named as “BCNet”, and its deep seventeen-layer architecture has been selected after extensive trials. The BCNet got trained using Adam’s optimization algorithm as a variant of the Stochastic Gradient Descent (SGD) technique. Results: The paper goes through the development and training process in details and shows the image processing pipeline harnessed in the development. Conclusion: The proposed approach proved successful in cloning the driving behavior embedded in the training data set after extensive simulations.

A Modified Multi Scale Retinex with Color Restoration Algorithm for Automatic Enhancement of Landsat-5 Remote Sensing Image

2011 ◽  
Vol 341-342 ◽  
pp. 893-897
Author(s):  
Gui Zhou Wang ◽  
Guo Jin He
Keyword(s):  
Image Enhancement ◽  
Dynamic Range ◽  
Color Constancy ◽  
Human Perception ◽  
Histogram Equalization ◽  
Image Processing Algorithm ◽  
Multi Scale ◽  
Dynamic Range Compression ◽  
Restoration Algorithm ◽  
Color Restoration

The retinex is a human perception based image processing algorithm which provides color constancy and dynamic range compression. The multi scale retinex with color restoration (MSRCR) has shown itself to be a very versatile automatic image enhancement algorithm that simultaneously provides dynamic range compression, color constancy, and color rendition. But the MSRCR results suffer from lower global brightness and partial color distortion. In order to improve the MSRCR method, this paper presents a modified MSRCR algorithm to Landsat-5 image enhancement considering percent liner stretch and histogram adjustment. Finally, the effect of modified MSRCR method on Landsat-5 image enhancement is analyzed and the comparison with other color adjustment methods such as gamma correction and histogram equalization is reported in the experimental results.

scholarly journals Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke

2021 ◽  
Vol 2099 (1) ◽  
pp. 012021
Author(s):  
A V Dobshik ◽  
A A Tulupov ◽  
V B Berikov
Keyword(s):  
Computed Tomography ◽  
Network Architecture ◽  
Semantic Segmentation ◽  
Training Data ◽  
Neural Network Architecture ◽  
Brain Images ◽  
Tomographic Images ◽  
Computed Tomography Images ◽  
Segmentation Accuracy ◽  
Weakly Supervised

Abstract This paper presents an automatic algorithm for the segmentation of areas affected by an acute stroke in the non-contrast computed tomography brain images. The proposed algorithm is designed for learning in a weakly supervised scenario when some images are labeled accurately, and some images are labeled inaccurately. Wrong labels appear as a result of inaccuracy made by a radiologist in the process of manual annotation of computed tomography images. We propose methods for solving the segmentation problem in the case of inaccurately labeled training data. We use the U-Net neural network architecture with several modifications. Experiments on real computed tomography scans show that the proposed methods increase the segmentation accuracy.

scholarly journals An Enhanced Image Fusion Algorithm by Combined Histogram Equalization and Fast Gray Level Grouping Using Multi-Scale Decomposition and Gray-PCA

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 157005-157021
Author(s):  
Jameel Ahmed Bhutto ◽  
Tian Lianfang ◽  
Qiliang Du ◽  
Toufique Ahmed Soomro ◽  
Yu Lubin ◽  
...  
Keyword(s):  
Image Fusion ◽  
Histogram Equalization ◽  
Gray Level ◽  
Fusion Algorithm ◽  
Multi Scale

scholarly journals Segmentation of Retinal Blood Vessels Based on Cake Filter

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Xi-Rong Bao ◽  
Xin Ge ◽  
Li-Huang She ◽  
Shi Zhang
Keyword(s):  
Blood Vessel ◽  
Blood Vessels ◽  
False Positive Rate ◽  
New Method ◽  
Real Component ◽  
Low Contrast ◽  
Small Vessels ◽  
Retinal Blood Vessels ◽  
Average Accuracy ◽  
Positive Rate

Segmentation of retinal blood vessels is significant to diagnosis and evaluation of ocular diseases like glaucoma and systemic diseases such as diabetes and hypertension. The retinal blood vessel segmentation for small and low contrast vessels is still a challenging problem. To solve this problem, a new method based on cake filter is proposed. Firstly, a quadrature filter band called cake filter band is made up in Fourier field. Then the real component fusion is used to separate the blood vessel from the background. Finally, the blood vessel network is got by a self-adaption threshold. The experiments implemented on the STARE database indicate that the new method has a better performance than the traditional ones on the small vessels extraction, average accuracy rate, and true and false positive rate.

scholarly journals A Novel Feature Extraction Method for Power Transformer Vibration Signal Based on CEEMDAN and Multi-Scale Dispersion Entropy

Entropy ◽  
2021 ◽  
Vol 23 (10) ◽  
pp. 1319
Author(s):  
Haikun Shang ◽  
Junyan Xu ◽  
Yucai Li ◽  
Wei Lin ◽  
Jinjuan Wang
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Extraction Method ◽  
Vibration Signal ◽  
Practical Significance ◽  
Stable Operation ◽  
Intrinsic Mode Functions ◽  
Vibration Signals ◽  
Feature Extraction Method ◽  
Multi Scale

Effective diagnosis of vibration fault is of practical significance to ensure the safe and stable operation of power transformers. Aiming at the traditional problems of transformer vibration fault diagnosis, a novel feature extraction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and multi-scale dispersion entropy (MDE) was proposed. In this paper, CEEMDAN method is used to decompose the original transformer vibration signal. Additionally, then MDE is used to capture multi-scale fault features in the decomposed intrinsic mode functions (IMFs). Next, the principal component analysis (PCA) method is employed to reduce the feature dimension and extract the effective information in vibration signals. Finally, the simplified features are sent into density peak clustering (DPC) to get the fault diagnosis results. The experimental data analysis shows that CEEMDAN-MDE can effectively extract the information of the original vibration signals and DPC can accurately diagnose the types of transformer faults. By comparing different algorithms, the practicability and superiority of this proposed method are verified.

scholarly journals SSGD: A Safe and Efficient Method of Gradient Descent

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Jinhuan Duan ◽  
Xianxian Li ◽  
Shiqi Gao ◽  
Zili Zhong ◽  
Jinyan Wang
Keyword(s):  
Gradient Descent ◽  
Large Scale ◽  
Optimization Problems ◽  
Unit Vector ◽  
Descent Method ◽  
Stochastic Gradient ◽  
Learning System ◽  
Training Data ◽  
Stochastic Gradient Descent ◽  
Gradient Descent Method

With the vigorous development of artificial intelligence technology, various engineering technology applications have been implemented one after another. The gradient descent method plays an important role in solving various optimization problems, due to its simple structure, good stability, and easy implementation. However, in multinode machine learning system, the gradients usually need to be shared, which will cause privacy leakage, because attackers can infer training data with the gradient information. In this paper, to prevent gradient leakage while keeping the accuracy of the model, we propose the super stochastic gradient descent approach to update parameters by concealing the modulus length of gradient vectors and converting it or them into a unit vector. Furthermore, we analyze the security of super stochastic gradient descent approach and demonstrate that our algorithm can defend against the attacks on the gradient. Experiment results show that our approach is obviously superior to prevalent gradient descent approaches in terms of accuracy, robustness, and adaptability to large-scale batches. Interestingly, our algorithm can also resist model poisoning attacks to a certain extent.

scholarly journals MF-Net: Multi-Scale Information Fusion Network for CNV Segmentation in Retinal OCT Images

2021 ◽  
Vol 15 ◽  
Author(s):  
Qingquan Meng ◽  
Lianyu Wang ◽  
Tingting Wang ◽  
Meng Wang ◽  
Weifang Zhu ◽  
...  
Keyword(s):  
Information Fusion ◽  
Data Augmentation ◽  
Contextual Information ◽  
Treatment Plan ◽  
Speckle Noise ◽  
Medical Image Segmentation ◽  
Unlabeled Data ◽  
Feature Maps ◽  
Multi Scale ◽  
Segmentation Accuracy

Choroid neovascularization (CNV) is one of the blinding ophthalmologic diseases. It is mainly caused by new blood vessels growing in choroid and penetrating Bruch's membrane. Accurate segmentation of CNV is essential for ophthalmologists to analyze the condition of the patient and specify treatment plan. Although many deep learning-based methods have achieved promising results in many medical image segmentation tasks, CNV segmentation in retinal optical coherence tomography (OCT) images is still very challenging as the blur boundary of CNV, large morphological differences, speckle noise, and other similar diseases interference. In addition, the lack of pixel-level annotation data is also one of the factors that affect the further improvement of CNV segmentation accuracy. To improve the accuracy of CNV segmentation, a novel multi-scale information fusion network (MF-Net) based on U-Shape architecture is proposed for CNV segmentation in retinal OCT images. A novel multi-scale adaptive-aware deformation module (MAD) is designed and inserted into the top of the encoder path, aiming at guiding the model to focus on multi-scale deformation of the targets, and aggregates the contextual information. Meanwhile, to improve the ability of the network to learn to supplement low-level local high-resolution semantic information to high-level feature maps, a novel semantics-details aggregation module (SDA) between encoder and decoder is proposed. In addition, to leverage unlabeled data to further improve the CNV segmentation, a semi-supervised version of MF-Net is designed based on pseudo-label data augmentation strategy, which can leverage unlabeled data to further improve CNV segmentation accuracy. Finally, comprehensive experiments are conducted to validate the performance of the proposed MF-Net and SemiMF-Net. The experiment results show that both proposed MF-Net and SemiMF-Net outperforms other state-of-the-art algorithms.

scholarly journals Two-Exposure Image Fusion Based on Optimized Adaptive Gamma Correction

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 24
Author(s):  
Yan-Tsung Peng ◽  
He-Hao Liao ◽  
Ching-Fu Chen
Keyword(s):  
Image Fusion ◽  
Dynamic Range ◽  
State Of The Art ◽  
High Dynamic Range ◽  
Gamma Correction ◽  
Virtual Image ◽  
Exposure Fusion ◽  
Multi Scale ◽  
Fusion Methods ◽  
Adaptive Gamma Correction

In contrast to conventional digital images, high-dynamic-range (HDR) images have a broader range of intensity between the darkest and brightest regions to capture more details in a scene. Such images are produced by fusing images with different exposure values (EVs) for the same scene. Most existing multi-scale exposure fusion (MEF) algorithms assume that the input images are multi-exposed with small EV intervals. However, thanks to emerging spatially multiplexed exposure technology that can capture an image pair of short and long exposure simultaneously, it is essential to deal with two-exposure image fusion. To bring out more well-exposed contents, we generate a more helpful intermediate virtual image for fusion using the proposed Optimized Adaptive Gamma Correction (OAGC) to have better contrast, saturation, and well-exposedness. Fusing the input images with the enhanced virtual image works well even though both inputs are underexposed or overexposed, which other state-of-the-art fusion methods could not handle. The experimental results show that our method performs favorably against other state-of-the-art image fusion methods in generating high-quality fusion results.

scholarly journals Extended Kalman Filter In Recurrent Neural Network: USDIDR Forecasting Case Study

2019 ◽  
Vol 13 (3) ◽  
pp. 293
Author(s):  
Muhammad Asaduddin Hazazi ◽  
Agus Sihabuddin
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Extended Kalman Filter ◽  
Recurrent Neural Network ◽  
Learning Algorithm ◽  
Regularization Parameter ◽  
Training Data ◽  
Stochastic Gradient Descent ◽  
Computational Time ◽  
Currency Exchange

Artificial Neural Networks (ANN) especially Recurrent Neural Network (RNN) have been widely used to predict currency exchange rates. The learning algorithm that is commonly used in ANN is Stochastic Gradient Descent (SGD). One of the advantages of SGD is that the computational time needed is relatively short. But SGD also has weaknesses, including SGD requiring several hyperparameters such as the regularization parameter. Besides that SGD relatively requires a lot of epoch to reach convergence. Extended Kalman Filter (EKF) as a learning algorithm on RNN is used to replace SGD with the hope of a better level of accuracy and convergence rate. This study uses IDR / USD exchange rate data from 31 August 2015 to 29 August 2018 with 70% data as training data and 30% data as test data. This research shows that RNN-EKF produces better convergent speeds and better accuracy compared to RNN-SGD.

Sign in / Sign up

Export Citation Format

Share Document