Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 138.149
Filtrar
1.
PLoS One ; 17(9): e0274212, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36067136

RESUMO

Age-related changes in brain structure include atrophy of the brain parenchyma and white matter changes of presumed vascular origin. Enlargement of the ventricles may occur due to atrophy or impaired cerebrospinal fluid (CSF) circulation. The co-occurrence of these changes in neurodegenerative diseases and in aging brains often requires investigators to take both into account when studying the brain, however, automated segmentation of enlarged ventricles and white matter hyperintensities (WMHs) can be a challenging task. Here, we present a hybrid multi-atlas segmentation and convolutional autoencoder approach for joint ventricle parcellation and WMH segmentation from magnetic resonance images (MRIs). Our fully automated approach uses a convolutional autoencoder to generate a standardized image of grey matter, white matter, CSF, and WMHs, which, in conjunction with labels generated by a multi-atlas segmentation approach, is then fed into a convolutional neural network to parcellate the ventricular system. Hence, our approach does not depend on manually delineated training data for new data sets. The segmentation pipeline was validated on both healthy elderly subjects and subjects with normal pressure hydrocephalus using ground truth manual labels and compared with state-of-the-art segmentation methods. We then applied the method to a cohort of 2401 elderly brains to investigate associations of ventricle volume and WMH load with various demographics and clinical biomarkers, using a multiple regression model. Our results indicate that the ventricle volume and WMH load are both highly variable in a cohort of elderly subjects and there is an independent association between the two, which highlights the importance of taking both the possibility of enlarged ventricles and WMHs into account when studying the aging brain.


Assuntos
Leucoaraiose , Substância Branca , Idoso , Envelhecimento , Atrofia/patologia , Encéfalo/diagnóstico por imagem , Encéfalo/patologia , Humanos , Processamento de Imagem Assistida por Computador , Imageamento por Ressonância Magnética/métodos , Substância Branca/diagnóstico por imagem , Substância Branca/patologia
2.
Comput Intell Neurosci ; 2022: 9231305, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36072743

RESUMO

In the field of mechanical and electrical equipment, the motor rolling bearing is a workpiece that is extremely prone to damage and failure. However, the traditional fault diagnosis methods cannot keep up with the development pace of the times because they need complex manual pretreatment or the support of specific expert experience and knowledge. As a rising star, the data-driven fault diagnosis methods are increasingly favored by scholars and experts at home and abroad. The convolutional neural network has been widely used because of its powerful feature extraction ability for all kinds of complex information and its outstanding research results in image processing, target tracking, target diagnosis, time-frequency analysis, and other scenes. Therefore, this paper introduces a convolutional neural network and applies it to motor-bearing fault diagnosis. Aiming at the shortcomings of fault signal and convolutional neural network, a large-scale maximum pooling strategy is proposed and optimized by wavelet transform to improve the fault diagnosis efficiency of motor bearing under high-voltage operation. Compared with other machine learning algorithms, the convolution neural network fault diagnosis model constructed in this paper not only has high accuracy (up to 0.9871) and low error (only 0.032) but also is simple to use. It provides a new way for motor bearing fault diagnosis and has very important economic and social value.


Assuntos
Processamento de Imagem Assistida por Computador , Redes Neurais de Computação , Algoritmos , Aprendizado de Máquina , Análise de Ondaletas
3.
Comput Intell Neurosci ; 2022: 3585506, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36072751

RESUMO

This study develops an accurate method based on the generative adversarial network (GAN) that targets the issue of the current discontinuity of micro vessel segmentation in the retinal segmentation images. The processing of images has become increasingly efficient since the advent of deep learning method. We have proposed an improved GAN combined with SE-ResNet and dilated inception block for the segmenting retinal vessels (SAD-GAN). The GAN model has been improved with respect to the following points. (1) In the generator, the original convolution block is replaced with SE-ResNet module. Furthermore, SE-Net can extract the global channel information, while concomitantly strengthening and weakening the key features and invalid features, respectively. The residual structure can alleviate the issue of gradient disappearance. (2) The inception block and dilated convolution are introduced into the discriminator, which enhance the transmission of features and expand the acceptance domain for improved extraction of the deep network features. (3) We have included the attention mechanism in the discriminator for combining the local features with the corresponding global dependencies, and for highlighting the interdependent channel mapping. SAD-GAN performs satisfactorily on public retina datasets. On DRIVE dataset, ROC_AUC and PR_AUC reach 0.9813 and 0.8928, respectively. On CHASE_DB1 dataset, ROC_AUC and PR_AUC reach 0.9839 and 0.9002, respectively. Experimental results demonstrate that the generative adversarial model, combined with deep convolutional neural network, enhances the segmentation accuracy of the retinal vessels far above that of certain state-of-the-art methods.


Assuntos
Processamento de Imagem Assistida por Computador , Vasos Retinianos , Processamento de Imagem Assistida por Computador/métodos , Redes Neurais de Computação , Retina/diagnóstico por imagem , Vasos Retinianos/diagnóstico por imagem
4.
Nat Commun ; 13(1): 5165, 2022 Sep 02.
Artigo em Inglês | MEDLINE | ID: mdl-36056020

RESUMO

Volumetric functional imaging is widely used for recording neuron activities in vivo, but there exist tradeoffs between the quality of the extracted calcium traces, imaging speed, and laser power. While deep-learning methods have recently been applied to denoise images, their applications to downstream analyses, such as recovering high-SNR calcium traces, have been limited. Further, these methods require temporally-sequential pre-registered data acquired at ultrafast rates. Here, we demonstrate a supervised deep-denoising method to circumvent these tradeoffs for several applications, including whole-brain imaging, large-field-of-view imaging in freely moving animals, and recovering complex neurite structures in C. elegans. Our framework has 30× smaller memory footprint, and is fast in training and inference (50-70 ms); it is highly accurate and generalizable, and further, trained with only small, non-temporally-sequential, independently-acquired training datasets (∼500 pairs of images). We envision that the framework will enable faster and long-term imaging experiments necessary to study neuronal mechanisms of many behaviors.


Assuntos
Aprendizado Profundo , Animais , Caenorhabditis elegans , Cálcio , Diagnóstico por Imagem , Processamento de Imagem Assistida por Computador , Razão Sinal-Ruído
5.
Sci Rep ; 12(1): 14947, 2022 Sep 02.
Artigo em Inglês | MEDLINE | ID: mdl-36056042

RESUMO

Level set models are suitable for processing topological changes in different regions of images while performing segmentation. Active contour models require an empirical setting for initial parameters, which is tedious for the end-user. This study proposes an incremental level set model with the automatic initialization of contours based on local and global fitting energies that enable it to capture image regions containing intensity corruption or other light artifacts. The region-based area and the region-based length terms use signed pressure force (SPF) to strengthen the balloon force. SPF helps to achieve a smooth version of the gradient descent flow in terms of energy minimization. The proposed model is tested on multiple synthetic and real images. Our model has four advantages: first, there is no need for the end user to initialize the parameters; instead, the model is self-initialized. Second, it is more accurate than other methods. Third, it shows lower computational complexity. Fourth, it does not depend on the starting position of the contour. Finally, we evaluated the performance of our model on microscopic cell images (Coelho et al., in: 2009 IEEE international symposium on biomedical imaging: from nano to macro, IEEE, 2009) to confirm that its performance is superior to that of other state-of-the-art models.


Assuntos
Algoritmos , Processamento de Imagem Assistida por Computador , Artefatos , Processamento de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos
6.
Sci Rep ; 12(1): 14920, 2022 Sep 02.
Artigo em Inglês | MEDLINE | ID: mdl-36056115

RESUMO

Modern biomedical image analyses workflows contain multiple computational processing tasks giving rise to problems in reproducibility. In addition, image datasets can span both spatial and temporal dimensions, with additional channels for fluorescence and other data, resulting in datasets that are too large to be processed locally on a laptop. For omics analyses, software containers have been shown to enhance reproducibility, facilitate installation and provide access to scalable computational resources on the cloud. However, most image analyses contain steps that are graphical and interactive, features that are not supported by most omics execution engines. We present the containerized and cloud-enabled Biodepot-workflow-builder platform that supports graphics from software containers and has been extended for image analyses. We demonstrate the potential of our modular approach with multi-step workflows that incorporate the popular and open-source Fiji suite for image processing. One of our examples integrates fully interactive ImageJ macros with Jupyter notebooks. Our second example illustrates how the complicated cloud setup of an computationally intensive process such as stitching 3D digital pathology datasets using BigStitcher can be automated and simplified. In both examples, users can leverage a form-based graphical interface to execute multi-step workflows with a single click, using the provided sample data and preset input parameters. Alternatively, users can interactively modify the image processing steps in the workflow, apply the workflows to their own data, change the input parameters and macros. By providing interactive graphics support to software containers, our modular platform supports reproducible image analysis workflows, simplified access to cloud resources for analysis of large datasets, and integration across different applications such as Jupyter.


Assuntos
Análise de Dados , Software , Biologia Computacional/métodos , Processamento de Imagem Assistida por Computador/métodos , Reprodutibilidade dos Testes , Fluxo de Trabalho
7.
Comput Intell Neurosci ; 2022: 7935346, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36059415

RESUMO

Recent improvements in current technology have had a significant impact on a wide range of image processing applications, including medical imaging. Classification, detection, and segmentation are all important aspects of medical imaging technology. An enormous need exists for the segmentation of diagnostic images, which can be applied to a wide variety of medical research applications. It is important to develop an effective segmentation technique based on deep learning algorithms for optimal identification of regions of interest and rapid segmentation. To cover this gap, a pipeline for image segmentation using traditional Convolutional Neural Network (CNN) as well as introduced Swarm Intelligence (SI) for optimal identification of the desired area has been proposed. Fuzzy C-means (FCM), K-means, and improvisation of FCM with Particle Swarm Optimization (PSO), improvisation of K-means with PSO, improvisation of FCM with CNN, and improvisation of K-means with CNN are the six modules examined and evaluated. Experiments are carried out on various types of images such as Magnetic Resonance Imaging (MRI) for brain data analysis, dermoscopic for skin, microscopic for blood leukemia, and computed tomography (CT) scan images for lungs. After combining all of the datasets, we have constructed five subsets of data, each of which had a different number of images: 50, 100, 500, 1000, and 2000. Each of the models was executed and trained on the selected subset of the datasets. From the experimental analysis, it is observed that the performance of K-means with CNN is better than others and achieved 96.45% segmentation accuracy with an average time of 9.09 seconds.


Assuntos
Processamento de Imagem Assistida por Computador , Redes Neurais de Computação , Algoritmos , Processamento de Imagem Assistida por Computador/métodos , Inteligência , Imageamento por Ressonância Magnética/métodos
8.
Comput Intell Neurosci ; 2022: 7316133, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36045976

RESUMO

The necessity of predicting and estimating river velocity motivates the development of a prediction method based on GAN image enhancement and multifeature fusion. In this method, in order to improve the image quality of river velocity, GAN network is used to enhance the image, so as to improve the integrity of image data set. In order to improve the accuracy of prediction, the image is extracted and fused with multiple features, and the extracted multiple features are taken as the input of CNN, so as to improve the prediction accuracy of convolution neural network. The results show that when the velocity is 0.25 m/s, 0.50 m/s, and 0.75 m/s, the accuracy of improved method can reach 85%, 90%, and 92%, which are higher than SVM, VGG-16, and BPNET algorithms. The above results indicate that the improvement has certain positive value and practical application value.


Assuntos
Redes Neurais de Computação , Rios , Algoritmos , Processamento de Imagem Assistida por Computador/métodos
9.
Comput Intell Neurosci ; 2022: 3844770, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36045978

RESUMO

This study uses the video image information in sports video image analysis to realize scientific sports training. In recent years, game video image analysis has referenced athletes' sports training. The sports video analysis is a widely used and effective method. First, the you only look once (YOLO) method is explored in lightweight object detection. Second, a sports motion analysis system based on the YOLO-OSA (you only look once-one-shot aggregation) target detection network is built based on the dense convolutional network (DenseNet) target detection network established by the one-shot aggregation (OSA) connection. Finally, object detection evaluation principles are used to analyze network performance and object detection in sports video. The results show that the more obvious the target feature, the larger the size, and the more motion information contained in the sports category feature, the more obvious the effect of the detected target. The higher the resolution of the sports video image, the higher the model detection accuracy of the YOLO-OSA target detection network, and the richer the visual video information. In sports video analysis, video images of the appropriate resolution are fed into the system. The YOLO-OSA network achieved 21.70% precision and 54.90% recall. In general, the YOLO-OSA network has certain pertinence for sports video image analysis, and it improves the detection speed of video analysis. The research and analysis of video in sports under the lightweight target detection network have certain reference significance.


Assuntos
Redes Neurais de Computação , Apneia Obstrutiva do Sono , Humanos , Processamento de Imagem Assistida por Computador/métodos
10.
J Environ Public Health ; 2022: 6440464, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36046079

RESUMO

The art of music, which is a necessary component of daily life and an ideology older than language, reflects the emotions of human reality. Many new elements have been introduced into music as a result of the quick development of technology, gradually altering how people create, perform, and enjoy music. It is incredible to see how actively AI has been used in music applications and music education over the past few years and how significantly it has advanced. AI technology can efficiently pull in the course, stratify complex large-scale music or sections, simplify teaching, improve student understanding of music, solve challenging student problems in class, and simplify the tasks of teachers. The traditional music education model has been modified, and the music education model's audacious innovation has been made possible by reducing the distance between the teacher and the student. A classification algorithm based on spectrogram and NNS is proposed in light of the advantages in image processing. The abstract features on the spectrogram are automatically extracted using the NNS, which completes the end-to-end learning and avoids the tediousness and inaccuracy of manual feature extraction. This study, which uses experimental analysis to support its findings, demonstrates that different music teaching genres can be accurately classified at a rate of over 90%, which has a positive impact on recognition.


Assuntos
Aprendizado Profundo , Música , Humanos , Processamento de Imagem Assistida por Computador , Modelos Teóricos , Música/psicologia , Estudantes
11.
Biomed Res Int ; 2022: 5061112, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36046444

RESUMO

Weighted MR images of 421 patients with nasopharyngeal cancer were obtained at the head and neck level, and the tumors in the images were assessed by two expert doctors. 346 patients' multimodal pictures and labels served as training sets, whereas the remaining 75 patients' multimodal images and labels served as independent test sets. Convolutional neural network (CNN) for modal multidimensional information fusion and multimodal multidimensional information fusion (MMMDF) was used. The three models' performance is compared, and the findings reveal that the multimodal multidimensional fusion model performs best, while the two-modal multidimensional information fusion model performs second. The single-modal multidimensional information fusion model has the poorest performance. In MR images of nasopharyngeal cancer, a convolutional network can precisely and efficiently segment tumors.


Assuntos
Processamento de Imagem Assistida por Computador , Neoplasias Nasofaríngeas , Humanos , Processamento de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos , Carcinoma Nasofaríngeo , Neoplasias Nasofaríngeas/diagnóstico por imagem , Redes Neurais de Computação , Tomografia Computadorizada por Raios X/métodos
12.
Biomed Res Int ; 2022: 8007713, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36046446

RESUMO

Applying machine learning technology to automatic image analysis and auxiliary diagnosis of whole slide image (WSI) may help to improve the efficiency, objectivity, and consistency of pathological diagnosis. Due to its extremely high resolution, it is still a great challenge to directly process WSI through deep neural networks. In this paper, we propose a novel model for the task of classification of WSIs. The model is composed of two parts. The first part is a self-supervised encoding network with a UNet-like architecture. Each patch from a WSI is encoded as a compressed latent representation. These features are placed according to their corresponding patch's original location in WSI, forming a feature cube. The second part is a classification network fused by 4 famous network blocks with heterogeneous architectures, with feature cube as input. Our model effectively expresses the feature and preserves location information of each patch. The fused network integrates heterogeneous features generated by different networks which yields robust classification results. The model is evaluated on two public datasets with comparison to baseline models. The evaluation results show the effectiveness of the proposed model.


Assuntos
Aprendizado de Máquina , Redes Neurais de Computação , Processamento de Imagem Assistida por Computador/métodos
13.
Biomed Res Int ; 2022: 1755460, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36046454

RESUMO

Lung cancer is a potentially lethal illness. Cancer detection continues to be a challenge for medical professionals. The true cause of cancer and its complete treatment have still not been discovered. Cancer that is caught early enough can be treated. Image processing methods such as noise reduction, feature extraction, identification of damaged regions, and maybe a comparison with data on the medical history of lung cancer are used to locate portions of the lung that have been impacted by cancer. This research shows an accurate classification and prediction of lung cancer using technology that is enabled by machine learning and image processing. To begin, photos need to be gathered. In the experimental investigation, 83 CT scans from 70 distinct patients were utilized as the dataset. The geometric mean filter is used during picture preprocessing. As a consequence, image quality is enhanced. The K-means technique is then used to segment the images. The part of the image may be found using this segmentation. Then, classification methods using machine learning are used. For the classification, ANN, KNN, and RF are some of the machine learning techniques that were used. It is found that the ANN model is producing more accurate results for predicting lung cancer.


Assuntos
Algoritmos , Neoplasias Pulmonares , Humanos , Processamento de Imagem Assistida por Computador/métodos , Pulmão , Neoplasias Pulmonares/diagnóstico por imagem , Aprendizado de Máquina
14.
Sci Rep ; 12(1): 14888, 2022 Sep 01.
Artigo em Inglês | MEDLINE | ID: mdl-36050364

RESUMO

Deep learning methods have enabled a fast, accurate and automated approach for retinal layer segmentation in posterior segment OCT images. Due to the success of semantic segmentation methods adopting the U-Net, a wide range of variants and improvements have been developed and applied to OCT segmentation. Unfortunately, the relative performance of these methods is difficult to ascertain for OCT retinal layer segmentation due to a lack of comprehensive comparative studies, and a lack of proper matching between networks in previous comparisons, as well as the use of different OCT datasets between studies. In this paper, a detailed and unbiased comparison is performed between eight U-Net architecture variants across four different OCT datasets from a range of different populations, ocular pathologies, acquisition parameters, instruments and segmentation tasks. The U-Net architecture variants evaluated include some which have not been previously explored for OCT segmentation. Using the Dice coefficient to evaluate segmentation performance, minimal differences were noted between most of the tested architectures across the four datasets. Using an extra convolutional layer per pooling block gave a small improvement in segmentation performance for all architectures across all four datasets. This finding highlights the importance of careful architecture comparison (e.g. ensuring networks are matched using an equivalent number of layers) to obtain a true and unbiased performance assessment of fully semantic models. Overall, this study demonstrates that the vanilla U-Net is sufficient for OCT retinal layer segmentation and that state-of-the-art methods and other architectural changes are potentially unnecessary for this particular task, especially given the associated increased complexity and slower speed for the marginal performance gains observed. Given the U-Net model and its variants represent one of the most commonly applied image segmentation methods, the consistent findings across several datasets here are likely to translate to many other OCT datasets and studies. This will provide significant value by saving time and cost in experimentation and model development as well as reduced inference time in practice by selecting simpler models.


Assuntos
Aprendizado Profundo , Processamento de Imagem Assistida por Computador , Processamento de Imagem Assistida por Computador/métodos , Retina/diagnóstico por imagem
15.
Int J Lab Hematol ; 44 Suppl 1: 37-44, 2022 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-36074713

RESUMO

Hematological diagnostics is based on increasingly precise techniques of cellular and molecular analysis. The correct interpretation of the blood and bone marrow smears observed under an optical microscope still represents a cornerstone. Precise quantitative and qualitative cytomorphological criteria have recently been codified by up-to-date guidelines for diagnosing hematopoietic neoplasms. Morphological analysis has found formidable support in digital reproduction techniques, which have simplified the circulation of images for educational or consultation purposes. From 2007 to 2019, the Working Group WP10 of European LeukemiaNet (ELN) used, in annual exercises, digital images to support training in cytomorphology and verify harmonization and comparability in the interpretation of blood and bone marrow smears. We describe the design, development, and results of this program, which had 741 participants in-person or remotely, to which 2055 questions were submitted regarding the interpretation of cytomorphological images. We initially used circulation and presentation of digital microphotographs and then introduced a virtual microscopy (VM). Virtual slides were obtained using a whole slide imaging technique, similar to the one largely used in histopathology, to produce digitized scans of consecutive microscopic fields and reassembles them to obtain a complete virtual smear by stitching. Participants were required to identify cells in labeled fields of view of the virtual slides to obtain a morphological diagnosis. This work has demonstrated substantial improvements in diagnostic accuracy and harmonization with the VM technique. Between-observer concordance increased from 62.5% to 83.0%. The integrity of the digitalized film image, which provides a general context for cell abnormalities, was the main factor for this outcome.


Assuntos
Hematologia , Processamento de Imagem Assistida por Computador , Humanos , Processamento de Imagem Assistida por Computador/métodos , Microscopia/métodos
17.
Sensors (Basel) ; 22(17)2022 Aug 23.
Artigo em Inglês | MEDLINE | ID: mdl-36080793

RESUMO

The analysis and segmentation of articular cartilage magnetic resonance (MR) images belongs to one of the most commonly routine tasks in diagnostics of the musculoskeletal system of the knee area. Conventional regional segmentation methods, which are based either on the histogram partitioning (e.g., Otsu method) or clustering methods (e.g., K-means), have been frequently used for the task of regional segmentation. Such methods are well known as fast and well working in the environment, where cartilage image features are reliably recognizable. The well-known fact is that the performance of these methods is prone to the image noise and artefacts. In this context, regional segmentation strategies, driven by either genetic algorithms or selected evolutionary computing strategies, have the potential to overcome these traditional methods such as Otsu thresholding or K-means in the context of their performance. These optimization strategies consecutively generate a pyramid of a possible set of histogram thresholds, of which the quality is evaluated by using the fitness function based on Kapur's entropy maximization to find the most optimal combination of thresholds for articular cartilage segmentation. On the other hand, such optimization strategies are often computationally demanding, which is a limitation of using such methods for a stack of MR images. In this study, we publish a comprehensive analysis of the optimization methods based on fuzzy soft segmentation, driven by artificial bee colony (ABC), particle swarm optimization (PSO), Darwinian particle swarm optimization (DPSO), and a genetic algorithm for an optimal thresholding selection against the routine segmentations Otsu and K-means for analysis and the features extraction of articular cartilage from MR images. This study objectively analyzes the performance of the segmentation strategies upon variable noise with dynamic intensities to report a segmentation's robustness in various image conditions for a various number of segmentation classes (4, 7, and 10), cartilage features (area, perimeter, and skeleton) extraction preciseness against the routine segmentation strategies, and lastly the computing time, which represents an important factor of segmentation performance. We use the same settings on individual optimization strategies: 100 iterations and 50 population. This study suggests that the combination of fuzzy thresholding with an ABC algorithm gives the best performance in the comparison with other methods as from the view of the segmentation influence of additive dynamic noise influence, also for cartilage features extraction. On the other hand, using genetic algorithms for cartilage segmentation in some cases does not give a good performance. In most cases, the analyzed optimization strategies significantly overcome the routine segmentation methods except for the computing time, which is normally lower for the routine algorithms. We also publish statistical tests of significance, showing differences in the performance of individual optimization strategies against Otsu and K-means method. Lastly, as a part of this study, we publish a software environment, integrating all the methods from this study.


Assuntos
Cartilagem Articular , Algoritmos , Artefatos , Cartilagem Articular/diagnóstico por imagem , Análise por Conglomerados , Processamento de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos
18.
Sensors (Basel) ; 22(17)2022 Aug 24.
Artigo em Inglês | MEDLINE | ID: mdl-36080807

RESUMO

A wireless vision sensor network (WVSN) is built by using multiple image sensors connected wirelessly to a central server node performing video analysis, ultimately automating different tasks such as video surveillance. In such applications, a large deployment of sensors in the same way as Internet-of-Things (IoT) devices is required, leading to extreme requirements in terms of sensor cost, communication bandwidth and power consumption. To achieve the best possible trade-off, we propose in this paper a new concept that attempts to achieve image compression and early image recognition leading to lower bandwidth and smart image processing integrated at the sensing node. A WVSN implementation is proposed to save power consumption and bandwidth utilization by processing only part of the acquired image at the sensor node. A convolutional neural network is deployed at the central server node for the purpose of progressive image recognition. The proposed implementation is capable of achieving an average recognition accuracy of 88% with an average confidence probability of 83% for five subimages, while minimizing the overall power consumption at the sensor node as well as the bandwidth utilization between the sensor node and the central server node by 43% and 86%, respectively, compared to the traditional sensor node.


Assuntos
Compressão de Dados , Processamento de Imagem Assistida por Computador , Redes Neurais de Computação
19.
Sensors (Basel) ; 22(17)2022 Aug 24.
Artigo em Inglês | MEDLINE | ID: mdl-36080813

RESUMO

Binary object segmentation is a sub-area of semantic segmentation that could be used for a variety of applications. Semantic segmentation models could be applied to solve binary segmentation problems by introducing only two classes, but the models to solve this problem are more complex than actually required. This leads to very long training times, since there are usually tens of millions of parameters to learn in this category of convolutional neural networks (CNNs). This article introduces a novel abridged VGG-16 and SegNet-inspired reflected architecture adapted for binary segmentation tasks. The architecture has 27 times fewer parameters than SegNet but yields 86% segmentation cross-intersection accuracy and 93% binary accuracy. The proposed architecture is evaluated on a large dataset of depth images collected using the Kinect device, achieving an accuracy of 99.25% in human body shape segmentation and 87% in gender recognition tasks.


Assuntos
Processamento de Imagem Assistida por Computador , Redes Neurais de Computação , Humanos , Processamento de Imagem Assistida por Computador/métodos , Semântica
20.
Sensors (Basel) ; 22(17)2022 Aug 25.
Artigo em Inglês | MEDLINE | ID: mdl-36080849

RESUMO

The purpose of infrared and visible image fusion is to generate images with prominent targets and rich information which provides the basis for target detection and recognition. Among the existing image fusion methods, the traditional method is easy to produce artifacts, and the information of the visible target and texture details are not fully preserved, especially for the image fusion under dark scenes and smoke conditions. Therefore, an infrared and visible image fusion method is proposed based on visual saliency image and image contrast enhancement processing. Aiming at the problem that low image contrast brings difficulty to fusion, an improved gamma correction and local mean method is used to enhance the input image contrast. To suppress artifacts that are prone to occur in the process of image fusion, a differential rolling guidance filter (DRGF) method is adopted to decompose the input image into the basic layer and the detail layer. Compared with the traditional multi-scale decomposition method, this method can retain specific edge information and reduce the occurrence of artifacts. In order to solve the problem that the salient object of the fused image is not prominent and the texture detail information is not fully preserved, the salient map extraction method is used to extract the infrared image salient map to guide the fusion image target weight, and on the other hand, it is used to control the fusion weight of the basic layer to improve the shortcomings of the traditional 'average' fusion method to weaken the contrast information. In addition, a method based on pixel intensity and gradient is proposed to fuse the detail layer and retain the edge and detail information to the greatest extent. Experimental results show that the proposed method is superior to other fusion algorithms in both subjective and objective aspects.


Assuntos
Algoritmos , Aumento da Imagem , Artefatos , Aumento da Imagem/métodos , Processamento de Imagem Assistida por Computador/métodos
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...