关键词:
Deformation;Windows;Object detection;Education and training;Image processing;Feature extraction;Cameras;Distortion;Head;Data modeling
摘要:
Retail product detection in fisheye camera capture scenes frequently suffers from excessive object occlusion and deformation, as well as difficulty in distinguishing products with small fine-grained differences, so accurately classifying and localizing products in these images presents a challenge for computer vision. We propose an efficient product detection network called EPformer by fusing a visual transformer and convolutional neural network to reliably detect retail products in fisheye images. We employ a shifted window strategy for feature information interaction across windows to more precisely detect products due to the issue of dense occlusion of products. To address the issue of excessive product deformation brought on by fisheye cameras, we develop a deformation image processing module without explicit correction and embed it into the path aggregation network structure. This enables the model to efficiently capture product geometric changes and conduct feature fusion. To address the issue of differentiating fine-grained products, we design an effective coordinate squeeze-excitation (ECSE) attention module that can capture the fine-grained texture and boundary information differences between individuals in terms of spatial and channel relationships. The inability to differentiate fine-grained products can be solved by training the ECSE module in tandem with the decoupled head. The experimental results demonstrate that EPformer is a potent product detection model with a 4.9% higher mean average precision than the state-of-the-art method (YOLOX) on the fisheye product image dataset. In addition, the EPformer model can effectively detect products in fisheye images on the Jeston Xavier NX embedded device to meet the application requirements in realistic scenarios.
通讯机构:
[Lang Li] C;College of Computer Science and Technology, Hengyang Normal University, Hengyang, China<&wdkj&>Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang Normal University, Hengyang, China
关键词:
internet of things;5G;dynamic S-box;bit-slice technology;lightweight block cipher
关键词:
Internet of Things (IoT);involutive;lightweight block cipher;permutation;S-box;security
摘要:
Nowadays, the use of the Internet of Things has reached a commanding height in a new round of economic and technological upsurge. Its data transmission security has attracted much attention. It is well known that substitution permutation networks (SPNs) ciphers with high diffusion are not advantageous in unified encryption and decryption circuits with extremely resources constrained. Although some research has been carried out to address this issue, there are still insufficiencies. In this article, we propose a new 64-bit lightweight block cipher based on SPN named IVLBC, whose key allows 80 and 128 bits. The components of IVLBC are involutions. In particular, we propose a Feistel with tree structure to obtain a compact and involutive S-box. Also, the nibble-based involutive permutation is proposed to obtain the involutive permutation. Decryption can reuse encrypted code and circuitry in both software and hardware implementations. We prove that the costs of IVLBC are less than PRESENT, PRINCE, Midori, I-PRESENTTM, CRAFT, etc., in unified encryption and decryption circuits. In addition, we conduct other performance tests on IVLBC such as the differential attack, linear attack, integral attack, algebraic attack, invariant attacks, etc.
摘要:
In this paper, a lossless image compression and encryption algorithm combining JPEG-LS, neural networks and hyperchaotic mapping is proposed to protect the privacy of digital images and reduce data storage space. Firstly, we design a new 2-Dimensional Logistic-Like Hyperchaotic Map (2DLLHM), which has more complex dynamics than some existing known chaotic systems, and can be used to build a good pseudorandom sequence generator. Secondly, to compress images efficiently, we design a new pixel predictor by combining the MED (Median Edge Detector) of JPEG-LS with MLP (Multilayer Perceptron). This predictor is called MMP. The MMP can effectively improve the prediction effect of edge texture area. On this basis, a threshold segmentation method is proposed. The method combined with MMP, run-length coding and Huffman coding can further improve the image compression ratio. Finally, to avoid some of the existing weak encryption designs, we construct a multi-round nonlinear diffusion structure with more excellent diffusion performance. Experiments show that the algorithm achieves a good compression ratio and can resist brute force attacks, statistical attacks, chosen-plaintext attacks and chosen-ciphertext attacks.
通讯机构:
[Li, L ] H;Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421002, Peoples R China.
关键词:
area-optimized;high throughput;Internet of Things;lightweight;LILLIPUT block cipher
摘要:
The relationship between encryption algorithm and key scheduling algorithm is utilized to achieve optimal sharing among components, which significantly reduces hardware area. The number of XOR gates and S‐boxes required for low area optimization is reduced by 52 and 8, respectively. Summary The widespread use of Internet of Things devices has increased the demand for lower cost and more efficient lightweight ciphers. However, there is a difficult trade‐off between cost and efficiency for lightweight block ciphers. The optimizations of area and throughput are important for some constrained environments. This paper proposes two novel hardware architectures for the LILLIPUT cipher. In the novel low area structure, a new permutation layer is provided for LILLIPUT. The relationship between encryption algorithm and key scheduling algorithm is utilized to achieve optimal sharing among components, which significantly reduces hardware area. The experimental results show that the number of XOR gates and S‐boxes required for low area optimization is reduced by 52 and 8, respectively. The total area is reduced by about 18%. For high throughput structure, this paper provides 2‐round, 5‐round, and 15‐round loop unrolling designs for LILLIPUT to improve throughput. The experimental results show that the throughput of the 5‐round loop unrolling structure reaches a good level, which is relatively the most cost‐effective. In practical application, ciphers can be unrolled implementations according to the needs of devices to improve the execution speed, which can greatly reduce the execution time and complexity of the algorithm.
摘要:
The number of industrial Internet of Things (IoT) users is increasing rapidly. Lightweight block ciphers have started to be used to protect the privacy of users. Hardware-oriented security design should fully consider the use of fewer hardware devices when the function is fully realized. Thus, this paper designs a lightweight block cipher IIoTBC for industrial IoT security. IIoTBC system structure is variable and flexibly adapts to nodes with different security requirements. This paper proposes a 4x4 S-box that achieves a good balance between area overhead and cryptographic properties. In addition, this paper proposes a preprocessing method for 4x4 S-box logic gate expressions, which makes it easier to obtain better area, running time, and power data in ASIC implementation. Applying it to 14 classic lightweight block cipher S-boxes, the results show that is feasible. A series of performance tests and security evaluations were performed on the IIoTBC. As shown by experiments and data comparisons, IIoTBC is compact and secure in industrial IoT sensor nodes. Finally, IIoTBC has been implemented on a temperature state acquisition platform to simulate encrypted transmission of temperature in an industrial environment.
通讯机构:
[Li, QP ] H;Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421002, Peoples R China.;Hunan Prov Key Lab Intelligent Informat Proc & App, Hengyang 421002, Peoples R China.
摘要:
The graph G of order n is an L-borderenergetic graph which means it has the same Laplacian energy as the complete graph Kn. In this paper, we find that the combination of complete bi-partite graphs and stars can construct infinite numbers of infinite classes L-borderenergetic graphs. We give two infinite numbers of infinite classes L-borderenergetic graphs and two infinite classes L-borderenergetic graphs under the operators union, join and their mixed. This research could provide experience for further study the structural characteristics of L-borderenergetic graphs.
通讯机构:
[Lang Li] C;College of Computer Science and Technology, Hengyang Normal University, Hengyang 421002, China<&wdkj&>Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang Normal University, Hengyang 421002, China
关键词:
ARX-Based lightweight block cipher;High-diffusion architecture;Mixed integer linear programming;SAND
通讯机构:
[Huihuang Zhao] C;College of Computer Science and Technology, Hengyang Normal University, Hengyang, 421002, China<&wdkj&>Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang, 421002, China
通讯机构:
[Mugang Lin] C;College of Computer Science and Technology, Hengyang Normal University, Hengyang 421002, China<&wdkj&>Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang 421002, China<&wdkj&>Author to whom correspondence should be addressed.
关键词:
style transfer;generative adversarial networks;deformable convolutional networks;artistic font generation
摘要:
The essence of font style transfer is to move the style features of an image into a font while maintaining the font’s glyph structure. At present, generative adversarial networks based on convolutional neural networks play an important role in font style generation. However, traditional convolutional neural networks that recognize font images suffer from poor adaptability to unknown image changes, weak generalization abilities, and poor texture feature extractions. When the glyph structure is very complex, stylized font images cannot be effectively recognized. In this paper, a deep deformable style transfer network is proposed for artistic font style transfer, which can adjust the degree of font deformation according to the style and realize the multiscale artistic style transfer of text. The new model consists of a sketch module for learning glyph mapping, a glyph module for learning style features, and a transfer module for a fusion of style textures. In the glyph module, the Deform-Resblock encoder is designed to extract glyph features, in which a deformable convolution is introduced and the size of the residual module is changed to achieve a fusion of feature information at different scales, preserve the font structure better, and enhance the controllability of text deformation. Therefore, our network has greater control over text, processes image feature information better, and can produce more exquisite artistic fonts.
摘要:
Researches have demonstrated that microorganisms are indispensable for the nutrition transportation, growth and development of human bodies, and disorder and imbalance of microbiota may lead to the occurrence of diseases. Therefore, it is crucial to study relationships between microbes and diseases. In this manuscript, we proposed a novel prediction model named MADGAN to infer potential microbe-disease associations by combining biological information of microbes and diseases with the generative adversarial networks. To our knowledge, it is the first attempt to use the generative adversarial network to complete this important task. In MADGAN, we firstly constructed different features for microbes and diseases based on multiple similarity metrics. And then, we further adopted graph convolution neural network (GCN) to derive different features for microbes and diseases automatically. Finally, we trained MADGAN to identify latent microbe-disease associations by games between the generation network and the decision network. Especially, in order to prevent over-smoothing during the model training process, we introduced the cross-level weight distribution structure to enhance the depth of the network based on the idea of residual network. Moreover, in order to validate the performance of MADGAN, we conducted comprehensive experiments and case studies based on databases of HMDAD and Disbiome respectively, and experimental results demonstrated that MADGAN not only achieved satisfactory prediction performances, but also outperformed existing state-of-the-art prediction models.
作者机构:
[Zhu, Xianyou; Hu, Weixin] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.
通讯机构:
[Zhu, XY ] H;Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.
摘要:
With the development of computer technology, speech synthesis techniques are becoming increasingly sophisticated. Speech cloning can be performed as a subtask of speech synthesis technology by using deep learning techniques to extract acoustic information from human voices and combine it with text to output a natural human voice. However, traditional speech cloning technology still has certain limitations; excessively large text inputs cannot be adequately processed, and the synthesized audio may include noise artifacts like breaks and unclear phrases. In this study, we add a text determination module to a synthesizer module to process words the model has not included. The original model uses fuzzy pronunciation for such words, which is not only meaningless but also affects the entire sentence. Thus, we improve the model by splitting the letters and pronouncing them separately. Finally, we also improved the preprocessing and waveform conversion modules of the synthesizer. We replace the pre-net module of the synthesizer and use an upgraded noise reduction algorithm combined with the SV2TTS framework to achieve a system with superior speech synthesis performance. Here, we focus on improving the performance of the synthesizer module to achieve higher-quality speech synthesis audio output.
摘要:
Recently, there has been renewed interest in the combination of deep learning and side-channel analysis (SCA). Many previous studies have transformed the traditional SCA into a classification problem in deep learning. This paper considers it as a regression problem based on the principle that the changes of some circuit states are related to the special operation in cipher. We proposed a regression model which consists of an initial layer, a deep feature mining dense layer, and a regression layer. In the term of dataset, there are two sources of data: the raw ASCAD power traces and the data sampled from FPGA implementation of AES and PRESENT. The mainly advantages of this model and regression task processing method is that it can adapt to different cryptographic algorithms on the same hardware device. Moreover, the experimental result that the model can significantly improve the attack accuracy of SCA. In ASCAD, its prediction accuracy achieves 2.90% and 3.63% for two different intermediate values, and their correlation coefficient evaluation 0.873, 0.840. In FPGA power dataset, their prediction and correlation coefficient are 3%, 4%, and 0.963, 0.987 respectively.