It is important and necessary to obtain high-frequency information and texture details in the image reconstruction applications, such as image super-resolution. Hence, it is proposed the multi-scale fusion network (MC...
详细信息
ISBN:
(纸本)9789811365041;9789811365034
It is important and necessary to obtain high-frequency information and texture details in the image reconstruction applications, such as image super-resolution. Hence, it is proposed the multi-scale fusion network (MCFN) in this paper. In the network, three pathways are designed for different receptive fields and scales, which are expected to obtain more texture details. Meanwhile, the local and global residual learning strategies are employed to prevent overfitting and to improve reconstruction quality. Compared with the classic convolutional neural network-based algorithms, the proposed method achieves better numerical and visual effects.
Over the years, Steganography and Cryptography have been complementary techniques for enforcing security of digital data. The need for the development of robust multi-layered schemes to counter the exponential grow in...
详细信息
Over the years, Steganography and Cryptography have been complementary techniques for enforcing security of digital data. The need for the development of robust multi-layered schemes to counter the exponential grow in the power of computing devices that can compromise security is critical in the design and implementation of security systems. Therefore, we propose a new combined steganographic and cryptographic scheme using the operators of genetic algorithm (GA) such selection, crossover and mutation, and some properties of the residue number system (RNS) with an appropriate fusing technique in order to embed encrypted text within images. The proposed scheme was tested using MatLab((R)) R2017b and a CORE (TM) i7 processor. Simulation results show that the proposed scheme can be deployed at one level with only the stego image containing the encrypted hidden message and at another level where the stego message is further encrypted. An analysis based on standard key metrics such as visual perception and statistical methods on steganalysis and cryptanalysis show that the proposed scheme is robust, is not complex with reduced runtime and will consume less power due to the use of residue numbers when compared to similar existing schemes.
The legibility of traffic signs has been considered from the beginning of design, and traffic signs are easy to identify for humans. For computer systems, however, identifying traffic signs still poses a challenging p...
详细信息
The legibility of traffic signs has been considered from the beginning of design, and traffic signs are easy to identify for humans. For computer systems, however, identifying traffic signs still poses a challenging problem. Both image-processing and machine-learning algorithms are constantly improving, aimed at better solving this problem. However, with a dramatic increase in the number of traffic signs, labelling a large amount of training data means high cost. Therefore, how to use a small number of labelled traffic sign data reasonably to build an efficient and high-quality traffic sign recognition (TSR) model in the Internet-of-things-based (IOT-based) transport system has been an urgent research goal. Here, the authors propose a novel semi-supervised learning approach combining global and local features for TSR in an IOT-based transport system. In their approach, histograms of oriented gradient, colour histograms (CH), and edge features (EF) are used to build different feature spaces. Meanwhile, on the unlabelled samples, a fusion feature space is found to alleviate the differences between different feature spaces. Extensive evaluations on a collection of signs from the German Traffic Sign Recognition Benchmark (GTSRB) dataset shows that the proposed approach outperforms the others and provides a potential solution for practical applications.
The video-based separation of foreground (FG) and background (BG) has been widely studied due to its vital role in many applications, including intelligent transportation and video surveillance. Most of the existing a...
详细信息
The video-based separation of foreground (FG) and background (BG) has been widely studied due to its vital role in many applications, including intelligent transportation and video surveillance. Most of the existing algorithms are based on traditional computer vision techniques that perform pixel-level processing assuming that FG and BG possess distinct visual characteristics. Recently, state-of-the-art solutions exploit deep learning models targeted originally for image classification. Major drawbacks of such a strategy are the lacking delineation of FG regions due to missing temporal information as they segment the FG based on a single frame object detection strategy. To grapple with this issue, we excogitate a 3D convolutional neural network (3D CNN) with long short-term memory (LSTM) pipelines that harness seminal ideas, viz., fully convolutional networking, 3D transpose convolution, and residual feature flows. Thence, an FG-BG segmenter is implemented in an encoder-decoder fashion and trained on representative FG-BG segments. The model devises a strategy called double encoding and slow decoding, which fuses the learned spatio-temporal cues with appropriate feature maps both in the down-sampling and up-sampling paths for achieving well generalized FG object representation. Finally, from the Sigmoid confidence map generated by the 3D CNN-LSTM model, the FG is identified automatically by using Nobuyuki Otsu's method and an empirical global threshold. The analysis of experimental results via standard quantitative metrics on 16 benchmark datasets including both indoor and outdoor scenes validates that the proposed 3D CNN-LSTM achieves competitive performance in terms of figure of merit evaluated against prior and state-of-the-art methods. Besides, a failure analysis is conducted on 20 video sequences from the DAVIS 2016 dataset.
The data quality of the satellite-retrieved water-leaving reflectance (Rrs) depends on the accuracy of radiometric calibration and the performance of atmospheric correction. A radiometric calibration scheme (RCS) has ...
详细信息
With the continuous development of deep learning in computer vision, object detection technology is constantly employed for processing remote sensing images. Especially, ship detection has become a significant and cha...
详细信息
ISBN:
(纸本)9781450385084
With the continuous development of deep learning in computer vision, object detection technology is constantly employed for processing remote sensing images. Especially, ship detection has become a significant and challenging task due to complex environmental factors (strong waves, clouds interference, etc.) and object issues (orientation, scale variety, density, etc.). Current detection methods pay more attention to the detection accuracy while ignoring the detection speed. In contrast with accuracy, detection speed is more important in some cases such as marine rescue and vessel tracking. Aiming at addressing these problems, we propose an enhanced YOLOv4(C-YOLOv4) which contains the feature fusion attention module (FAM) with a channel correlation loss(C-loss). C-loss is proposed to constrain the relations between object classes and channels while maintaining the intra-class and the inter-class separability. To evaluate the effectiveness of the proposed approach, comprehensive experiments are conducted on a public dataset HRSC2016. According to the experimental results, our proposed approach outperforms the baselines.
Today, medical imaging suffers from serious issues such as malicious tampering and privacy leakage. Encryption is an effective way to protect these images from security threats. Chaos has been widely used in image enc...
详细信息
Today, medical imaging suffers from serious issues such as malicious tampering and privacy leakage. Encryption is an effective way to protect these images from security threats. Chaos has been widely used in image encryption, the majority of these algorithms are based on classical chaotic systems. For now, these systems are easy to analyze and predict, which are not sufficient for image encryption proposes. In this paper, a novel fourth order chaotic system is proposed, accompanied by analysis of Lyapunov exponent and bifurcations. Finally, the application of this system with medical image encryption is proposed. As this system could have six control parameters and four initial conditions, the key space is far greater than 5.1 x 2(18191), which is large enough to resist brute force attack. Correlation analysis and differential attack analysis further demonstrate that this scheme has a strong resistance against statistical attacks and differential attack.
Due to the defects of optical systems, image sensors, and imperfect algorithms for image acquisition, compression, and restoration, color artifacts often appear in images obtained by imaging devices such as digital ca...
详细信息
Due to the defects of optical systems, image sensors, and imperfect algorithms for image acquisition, compression, and restoration, color artifacts often appear in images obtained by imaging devices such as digital cameras and scanners. Moreover, color artifacts are difficult to eliminate because of technical limitations, even in some mature commercial cameras. On the basis of red, green, and blue (RGB) intersection (RGBI), a correction method for color artifacts is proposed in this paper, where the RGB intersection-based method can effectively detect various types of color artifacts. Also, by combining the object information with weighted bilinear interpolation, the continuity of the image is kept while restoring the real color. Experiments demonstrate that the RGBI method, which is applicable to all color images, can eliminate various types of color artifacts with accurate detection and less artifact residue, even if the image has severe color distortion or the areas of the color artifacts are small and discrete. (C) 2019 Optical Society of America
A turnout, a device to guide tracks, is critical to the safety of high-speed railways. Detecting gaps in switch machines can monitor a turnout's working performance. Existing gap-detection systems, however, can ba...
详细信息
A turnout, a device to guide tracks, is critical to the safety of high-speed railways. Detecting gaps in switch machines can monitor a turnout's working performance. Existing gap-detection systems, however, can barely perform at high accuracy and with a low false alarm rate for a long time due to the complex operating conditions of switch machines. This study proposes an approach combining YOLO-based object detection architecture with imageprocessingalgorithms, of which YOLO is a deep learning network for object detection. First, YOLO detects target areas in gap images, and then image-processingalgorithms identify gaps and calculate gap sizes. This approach targets various types of switch machines and particularly complicated situations. Experiments on gap images of S700K switch machines demonstrate that the accuracy of detecting gaps is 100%, and the accuracy of calculating gap sizes is higher than 99%. Additionally, the proposed approach can exhibit the same high performance on complex images, like overexposed and tilted ones.
Esophageal cancer is one of the diseases afflicting human beings. Automatic segmentation of esophagus and esophageal tumor from computed tomography (CT) images is a challenging problem, which can assist in the diagnos...
详细信息
ISBN:
(纸本)9781450388627
Esophageal cancer is one of the diseases afflicting human beings. Automatic segmentation of esophagus and esophageal tumor from computed tomography (CT) images is a challenging problem, which can assist in the diagnosis of esophageal cancer. In this paper, DB M-Net is proposed for the segmentation of esophagus and esophageal tumor from CT images, which combines M-Net modified from U-Net with an approximate function for binarization called differentiable binarization (DB). We construct the multi-scale input layers and the multi-level output layers in the network to facilitate features fusion, and DB is performed to enhance the robustness. Fewer parameters are applied in our DB M-Net but the network achieves a better performance. The experiments are based on the dataset of 2,219 slices from 16 CT scans, which show our DB M-Net outperforms other existing algorithms.
暂无评论