Medical image scans and associated electronic medical records (EMR) could be stored locally or transmitted for use in autodiagnosis and remote healthcare in teleradiology. Hence, they require security against unauthor...
详细信息
ISBN:
(数字)9781728119908
ISBN:
(纸本)9781728119915
Medical image scans and associated electronic medical records (EMR) could be stored locally or transmitted for use in autodiagnosis and remote healthcare in teleradiology. Hence, they require security against unauthorised access and modification. Among other means of providing this security, information hiding (IH) techniques have gained relevance especially for open networks that are prone to active attacks. However, the evaluation of the suitability of these IH algorithms in terms of preserving medical image diagnostic features is currently limited to signal processing parameters. This paper re-interprets existing evaluation parameters and provides a new framework that allows dynamic selection of medical image IH (watermarking and steganography) security algorithms. Specifically, criteria that capture medical statistics used in the diagnosis and monitoring of patients were incorporated. These criteria and framework were validated on the Pneumonia Chest Xray dataset (used in a Kaggle Competition) using three selected IH algorithms that offer privacy and image tamper detection.
image segmentation and classification is more and more being of interest for computer vision and machine learning researchers. Many systems on the rise need accurate and efficient segmentation and recognition mechanis...
详细信息
ISBN:
(纸本)9783030205188;9783030205171
image segmentation and classification is more and more being of interest for computer vision and machine learning researchers. Many systems on the rise need accurate and efficient segmentation and recognition mechanisms. This demand coincides with the increase of computational capabilities of modern computer architectures and more effective algorithms for image recognition. The use of convolutional neural networks for the image classification and recognition allows building systems that enable automation in many industries. This article presents a system for classifying plastic waste, using convolutional neural networks. The problem of segregation of renewable waste is a big challenge for many countries around the world. Apart from segregating waste using human hands, there are several methods for automatic segregation. The article proposes a system for classifying waste with the following classes: polyethylene terephthalate, high-density polyethylene, polypropylene and polystyrene. The obtained results show that automatic waste classification, using imageprocessing and artificial intelligence methods, allows building effective systems that operate in the real world.
The blind image quality assessment algorithms produced every year are mostly "opinion-aware" (OA). It means that they require large numbers of subjective quality scores for regression model training. Subject...
详细信息
ISBN:
(纸本)9781510635463
The blind image quality assessment algorithms produced every year are mostly "opinion-aware" (OA). It means that they require large numbers of subjective quality scores for regression model training. Subjective quality scores are not easily available, so people are eager to design an opinion-unaware (OU) algorithm which has free subjective quality scores. Besides, the OU algorithm has greater generalization capability than the OA algorithm. Therefore, we propose an OU algorithm based on a visual codebook for multiply distorted image quality assessment. Extensive experiments conducted on the three databases demonstrate that the proposed method is superior to the existing five OU methods in terms of the coherence with the human subjective rating.
Eliminating noise from the original signal is still a demanding problem for researchers. There has been a number of published algorithms and each approach has its limitations, advantages, and constraints. Here we pres...
详细信息
ISBN:
(纸本)9781728111841
Eliminating noise from the original signal is still a demanding problem for researchers. There has been a number of published algorithms and each approach has its limitations, advantages, and constraints. Here we present our own contribution on the noise reduction problem by proposing an intermediary step between the image sensor and the post-processing software in the image capturing process. Our accelerated method, compared to other researchers, can be used either as a standalone solution or combined with an existing algorithm to further results improvement. Our solution matches the discrete samples between multiple frames and averages the pixel values. The output image maintains its structural integrity, holds better color accuracy and incurs less noise than others.
One of the challenges in the world today is the existence of a variety of diseases, some of which require the processing of medical images to diagnose and evaluate, such as images of brain tumors. One of the methods o...
详细信息
ISBN:
(数字)9781728186290
ISBN:
(纸本)9781728186306
One of the challenges in the world today is the existence of a variety of diseases, some of which require the processing of medical images to diagnose and evaluate, such as images of brain tumors. One of the methods of analyzing and evaluating patients related to the brain is magnetic resonance imaging(MRI). Data mining methods such as clustering can be used to analyze magnetic resonance images. Clustering techniques can take the area of brain tumors from brain tissue and use it to diagnose disease. Various clustering methods have been proposed so far, one of which is the fuzzy clustering or FCM method, and it has a high accuracy for clustering and segmentation of brain tissues. Fuzzy clustering is less sensitive to the noise in these images and therefore its segmentation accuracy is somewhat desirable. To improve the performance of FCM clustering, in identifying the edges and borders of tumors, it is necessary to select the optimal clustering centers. The optimal selection of cluster centers increases its accuracy in learning and segmentation. Given that the optimal selection of cluster centers is an optimization method, metaheuristic algorithms can be used for this purpose. In this research, swarm intelligence algorithms have been used to optimally select cluster centers in FCM. The analysis of the proposed method on a set of images of brain magnetic resonance shows that the proposed algorithm has the specificity, sensitivity, and accuracy of 96.87%, 88.36%, and 91.32% in the diagnosis of brain tumors, respectively. The proposed method of hybrid methods, such as the fuzzy method, better detects brain tumors.
With the appearance of Shared Autonomous Vehicles there will no longer be a driver responsible for maintaining the car interior and well-being of passengers. To counter this, it is imperative to have a system that is ...
详细信息
ISBN:
(数字)9781728175744
ISBN:
(纸本)9781728175751
With the appearance of Shared Autonomous Vehicles there will no longer be a driver responsible for maintaining the car interior and well-being of passengers. To counter this, it is imperative to have a system that is able to detect any abnormal behaviors, more specifically, violence between passengers. Traditional action recognition algorithms build models around known interactions but activities can be so diverse, that having a dataset that incorporates most use cases is unattainable. While action recognition models are normally trained on all the defined activities and directly output a score that classifies the likelihood of violence, video anomaly detection algorithms present themselves as an alternative approach to build a good discriminative model since usually only non-violent examples are needed. This work focuses on anomaly detection and action recognition algorithms trained, validated and tested on a subset of human behavior video sequences from Bosch's internal datasets. The anomaly detection network architecture defines how to properly reconstruct normal frame sequences so that during testing, each sequence can be classified as normal or abnormal based on its reconstruction error. With these errors, regularity scores are inferred showing the predicted regularity of each frame. The resulting framework is a viable addition to traditional action recognition algorithms since it can work as a tool for detecting unknown actions, strange/violent behaviors and aid in understanding the meaning of such human interactions.
image fusion and its separation is a frequently arising issue in imageprocessing field. In this paper, we have described image fusion and its Separation using Scatter graphical method and Joint Probability Density Fu...
详细信息
ISBN:
(纸本)9789811307614;9789811307607
image fusion and its separation is a frequently arising issue in imageprocessing field. In this paper, we have described image fusion and its Separation using Scatter graphical method and Joint Probability Density Function. Fused image separation using Scatter Graphical Method depend on Joint Probability density function of fused image. This technique gives batter result of other technique based on Signal Interference ratio and peak signal-to-noise ratio.
Aiming at the problem of the chinese rubbing image segmentation under a denoising algorithm based on deep convolutional neural network is proposed. Document enhancement and binarization is the main pre-processing step...
详细信息
ISBN:
(纸本)9781450363228
Aiming at the problem of the chinese rubbing image segmentation under a denoising algorithm based on deep convolutional neural network is proposed. Document enhancement and binarization is the main pre-processing step in document analysis process. At first, a feed-forward denoising convolutional neural networks as a pre-processing methods for document image has been used for denoise images of additive white Gaussian noise(AWGN). The residual learning mechanism is used to learn the mapping from the noisy image to the residual image between the noisy image and the clean image in the neural network training process. A median filtering has been employed for denoising`salt and pepper' noise. Given the learned denoising and enhanced image, we compute the adaptive threshold image using local adaptive threshold algorithm and then applies it to produce a binary output image. Experimental results show that combined those algorithms is robust in dealing with non-uniform illuminated, low contrast historic document images in terms of both accuracy and efficiency.
Many industrial machine vision problems, particularly real-time control of manufacturing processes such as laser cladding, require robust and fast imageprocessing. The inherent disturbances in images acquired during ...
详细信息
ISBN:
(纸本)9788395235788
Many industrial machine vision problems, particularly real-time control of manufacturing processes such as laser cladding, require robust and fast imageprocessing. The inherent disturbances in images acquired during these processes makes classical segmentation algorithms uncertain. Among many convolutional neural networks introduced recently to solve such difficult problems, U-Net balances simplicity with segmentation accuracy. However, it is too computationally intensive for usage in many real-time processing pipelines. In this work we present a method of identifying the most informative levels of detail in the U-Net. By only processing the image at the selected levels, we reduce the total computation time by 80%, while still preserving adequate quality of segmentation.
In order to make full use of the effective information in the video and improve the recognition rate of abnormal human behavior in complex scenes, we use a mixed Gaussian model to detect clear foreground moving target...
详细信息
In order to make full use of the effective information in the video and improve the recognition rate of abnormal human behavior in complex scenes, we use a mixed Gaussian model to detect clear foreground moving target contours and perform Gaussian filtering on them to remove the effects of noise in the scene . By calculating the center point of the foreground pixel, and drawing a bounding box based on this, the key area of human motion in the video is extracted. Then we use the Farneback dense optical flow algorithm to obtain spatiotemporal information. By combining CNN and LSTM, a CNN-LSTM hybrid two-stream network model based on the Dropout mechanism is established., input the original image and the superimposed optical flow image of the key area of the video sequence motion to learn the dynamic and static features and timing information in the spatiotemporal information. The weighted fusion method is used to perform weighted calculation on the Softmax output of the two-way network to obtain results. The tresults show that the accuracy of the behavior classification reached 91.2%, and the recognition rate of abnormal behavior was 92%. Compared with the three models in the article, the improvement was 6% 8.3%, 3.4%.
暂无评论