检索结果-内蒙古大学图书馆

quaternion convolutional neural network for Color Image Classification and Forensics

IEEE ACCESS 2019年 7卷 20293-20301页

作者： Yin, Qilin Wang, Jinwei Luo, Xiangyang Zhai, Jiangtao Jha, Sunil Kr. Shi, Yun-Qing Nanjing Univ Informat Sci & Technol Dept Comp & Software Nanjing 210044 Jiangsu Peoples R China Nanjing Univ Informat Sci & Technol Jiangsu Collaborat Innovat Ctr Atmospher Environm Nanjing 210044 Jiangsu Peoples R China State Key Lab Math Engn & Adv Comp Zhengzhou 450001 Henan Peoples R China New Jersey Inst Technol Dept Elect Comp Engn Newark NJ 07102 USA

The convolutional neural network is widely popular for solving the problems of color image feature extraction. However, in the general network, the interrelationship of the color image channels is neglected. Therefore, a novel quaternion convolutional neural network (QCNN) is proposed in this paper, which always treats color triples as a whole to avoid information loss. The original quaternion convolution operation is presented and constructed to fully mix the information of color channels. The quaternion batch normalization and pooling operations are derived and designed in quaternion domain to further ensure the integrity of color information. Meanwhile, the knowledge of the attention mechanism is incorporated to boost the performance of the proposed QCNN. The experiments demonstrate that the proposed model is more efficient than the traditional convolutional neural network and another QCNN with the same structure, and has better performance in color image classification and color image forensics.

关键词： quaternion convolutional neural network quaternion based layers color image classification color image forensics attention mechanism

来源：评论

学校读者我要写书评

暂无评论

quaternion matrix completion using untrained quaternion convolutional neural network for color image inpainting

引用

SIGNAL PROCESSING 2024年 221卷

作者： Miao, Jifei Kou, Kit Ian Yang, Ying Yang, Liqiao Han, Juan Yunnan Univ Sch Math & Stat Kunming 650091 Yunnan Peoples R China Univ Macau Fac Sci & Technol Dept Math Macau 999078 Peoples R China Southwestern Univ Finance & Econ Sch Comp & Artificial Intelligence Chengdu 611130 Peoples R China

The use of quaternions as a novel tool for color image representation has yielded impressive results in color image processing. By considering the color image as a unified entity rather than separate color space components, quaternions can effectively exploit the strong correlation among the RGB channels, leading to enhanced performance. Especially, color image inpainting tasks are highly beneficial from the application of quaternion matrix completion techniques, in recent years. However, existing quaternion matrix completion methods suffer from two major drawbacks. First, it can be difficult to choose a regularizer that captures the common characteristics of natural images, and sometimes the regularizer that is chosen based on empirical evidence may not be the optimal or efficient option. Second, the optimization process of quaternion matrix completion models is quite challenging because of the non-commutativity of quaternion multiplication. To address the two drawbacks of the existing quaternion matrix completion approaches mentioned above, this paper tends to use an untrained quaternion convolutional neural network (QCNN) to directly generate the completed quaternion matrix. This approach replaces the explicit regularization term in the quaternion matrix completion model with an implicit prior that is learned by the QCNN. Extensive quantitative and qualitative evaluations demonstrate the superiority of the proposed method for color image inpainting compared with some existing quaternion-based and tensor -based methods.

关键词： Color image inpainting quaternion convolutional neural network (QCNN) quaternion matrix completion

来源：评论

学校读者我要写书评

暂无评论

quaternion discrete orthogonal Hahn moments convolutional neural network for color image classification and face recognition

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第21期82卷 32827-32853页

作者： El Alami, Abdelmajid Mesbah, Abderrahim Berrahou, Nadia Lakhili, Zouhir Berrahou, Aissam Qjidaa, Hassan Sidi Mohamed Ben Abdellah Univ Fes Morocco Mohammed V Univ Rabat Morocco

Color image recognition has recently attracted more researchers' attention. Many methods based on quaternions have been developed to improve the classification accuracies. Some approaches have currently used quaternions with convolutional neural network (CNN). Despite the obtained results, these approaches have some weakness such as the computational complexity. In fact, the large size of the input color images necessitates a high number of layers and parameters during the learning process which can generate errors calculation and hence influence the recognition rate. In this paper, a new architecture called quaternion discrete orthogonal Hahn moments convolutional neural network (QHMCNN) for color image classification and face recognition is proposed to reduce the computational complexity of CNN while improving the classification rate. The quaternion Hahn moments are used to extract pertinent and compact features from images and introduced them in quaternion convolutional neural network. Experimental simulations conducted on various databases are demonstrated the performance of the proposed architecture QHMCNN against other relevant methods in state-of-the-art and the robustness under different noise conditions.

关键词： quaternion representation quaternion Hahn moments quaternion convolutional neural network Noise condition Color image classification Face recognition Complexity

来源：评论

学校读者我要写书评

暂无评论

quaternion convolutional neural networks 15th

Quaternion Convolutional Neural Networks

引用

15th European Conference on Computer Vision (ECCV)

作者： Zhu, Xuanyu Xu, Yi Xu, Hongteng Chen, Changjian Shanghai Jiao Tong Univ Shanghai Peoples R China Infinia ML Inc Durham NC USA Duke Univ Durham NC USA

ISBN: (纸本)9783030012373;9783030012366

neural networks in the real domain have been studied for a long time and achieved promising results in many vision tasks for recent years. However, the extensions of the neural network models in other number fields and their potential applications are not fully-investigated yet. Focusing on color images, which can be naturally represented as quaternion matrices, we propose a quaternion convolutional neural network (QCNN) model to obtain more representative features. In particular, we re-design the basic modules like convolution layer and fully-connected layer in the quaternion domain, which can be used to establish fully-quaternion convolutional neural networks. Moreover, these modules are compatible with almost all deep learning techniques and can be plugged into traditional CNNs easily. We test our QCNN models in both color image classification and denoising tasks. Experimental results show that they outperform the real-valued CNNs with same structures.

关键词： quaternion convolutional neural network quaternion-based layers Color image denoising Color image classification

来源：评论

学校读者我要写书评

暂无评论

Near-infrared spectroscopy analysis of compound fertilizer based on GAF and quaternion convolution neural network

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2023年 240卷

作者： Tan, Ailing Wang, Bolin Zhao, Yong Wang, Yunxin Zhao, Jing Wang, Alan X. Yanshan Univ Sch Informat & Sci Engn Key Lab Special Fiber & Fiber Sensor Hebei Prov Qinhuangdao 066004 Peoples R China Yanshan Univ Sch Elect Engn Key Lab Measurement Technol & Instrumentat Hebei P Qinhuangdao 066004 Peoples R China Baylor Univ Dept Elect & Comp Engn Waco TX 76706 USA Yanshan Univ Sch Elect Engn Qinhuangdao Hebei Peoples R China

This paper combines near infrared spectroscopy with deep learning theory to propose a rapid identification method for compound fertilizer based on gramian angular field (GAF) image coding and quaternion convolutional neural network (QCNN). First, the near-infrared (NIR) spectra of 200 samples of two types of compound with and without polyglutamic acid (& gamma;-PGA) were collected and pretreated by multivariate scattering correction (MSC) and first derivative methods. Then, the one-dimensional (1D) NIR spectra were transformed into twodimensional (2D) images by GAF coding method to express the spectral information more intuitively. Finally, three images of Gramian angular difference field (GADF), Gramian angular summation field (GASF) and their average images were formed into a pure quaternion matrix for parallel representation and were analyzed by the designed QCNN. The peak features and minor features were mined based on the automatic learning function of multi-layer structure of QCNN to establish a high-performance, qualitative model for identifying compound fertilizer. The experimental results show that the classification accuracy, sensitivity, and specificity of the identification model were 95.84%, 95.96% and 94.25%, respectively. Compared with the classification results based on traditional partial least square discrimination analysis(PLS-DA), principal component analysis combing with support vector machine classification(PCA-SVM), 1D convolution neural network (1DCNN) and GAF-CNN methods, the classification accuracy and adaptability of the model based on the proposed GAF-QCNN method have been significantly improved. The combination of GAF image of NIR spectra and QCNN developed in this study provides a novel approach for the intelligent modeling algorithm of NIR spectroscopy technology.

关键词： Near infrared spectroscopy Gramian angle field quaternion convolutional neural network Compound fertilizer

来源：评论

学校读者我要写书评

暂无评论

Detection of Triple JPEG Compressed Color Images

引用

IEEE ACCESS 2019年 7卷 113094-113102页

作者： Wang, Hao Wang, Jinwei Zhai, Jiangtao Luo, Xiangyang Nanjing Univ Informat Sci & Technol Dept Comp & Software Nanjing 210044 Jiangsu Peoples R China Nanjing Univ Informat Sci & Technol Jiangsu Collaborat Innovat Ctr Atmospher Environm Nanjing 210044 Jiangsu Peoples R China State Key Lab Math Engn & Adv Comp Zhengzhou 450001 Henan Peoples R China Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing 100093 Peoples R China Xidian Univ Shaanxi Key Lab Network & Syst Secur Xian 710071 Shaanxi Peoples R China

In order to extend the detection of JPEG compressed color images to solve the real-life problem, three-class classification forensics of JPEG compressed color images with the same quantization matrix is proposed. Since the previous methods treat detection of JPEG compressed color images as binary classification and JPEG compression with the same quantization matrix leaves slight tracks, three-class classification forensics of JPEG compressed color images with the same quantization matrix is a new and challenging problem. In this paper, two aspects are considered to solve this problem. First, if images are compressed, rounding and truncation error will occur. Thus, preprocessing of images is performed to extract error to highlight statistical difference which can help to classify. Second, the support vector machine (SVM) algorithm is originally designed for the binary classification problem, so dealing with a three-class problem, it is necessary to reconstruct a suitable three-class classifier. Besides, convolutional neural network (CNN) parallelly deal with three channels of the color image. The relationship of the three channels is terminated. However, quaternion convolutional neural network (QCNN) which utilizes quaternion algebra not only is directly used to three-class classification but also retain the relationship between three channels. Experimental results demonstrate that the proposed method achieves good performance and is better than the state-of-the-art approaches investigated.

关键词： Three-class classification the color image same quantization matrix rounding and truncation error quaternion convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Revisiting representation learning of color information: Color medical image segmentation incorporating quaternion

引用

KNOWLEDGE-BASED SYSTEMS 2024年 306卷

作者： Xia, Bicheng Zhan, Bangcheng Shen, Mingkui Yang, Hejun Third Peoples Hosp Henan Prov Zhengzhou Peoples R China Huazhong Univ Sci & Technol Sch Comp Sci & Technol Wuhan 430074 Hubei Peoples R China

Currently, color medical image segmentation methods commonly extract color and texture features mixed together by default, however, the distribution of color information and texture information is different: color information is represented differently in different color channels of a color image, while the distribution of texture information remains the same. Such a simple and brute-force feature extraction pattern will inevitably result in a partial bias in the model's semantics understanding. In this paper, we decouple the representation learning for color-texture information, and propose a novel network for color medical image segmentation, named CTNet. Specifically, CTNet introduces the quaternion CNN (QCNN) module to capture the correlation among different color channels of color medical images to generate color features, and uses a designed localglobal texture feature integrator (LoG) to mine the textural features from local to global. Moreover, a multistage features interaction strategy is proposed to minimize the semantic understanding gap of color and texture features in CTNet, so that they can be subsequently fused to generate a unified and robust feature representation. Comparative experiments on four different color medical image segmentation benchmark datasets show that CTNet strikes an optimal trade-off between segmentation accuracy and computational overhead when compared to current state-of-the-art methods. We also conduct extensive ablation experiments to verify the effectiveness of the proposed components. Our code will be available at https://***/Notmezhan/CTNet.

关键词： Color features quaternion convolutional neural network Deep learning Color medical image segmentation Feature fusion

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based traffic sign recognition for unmanned autonomous vehicles

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING 2018年第5期232卷 497-505页

作者： Zang, Di Wei, Zhihua Bao, Maomao Cheng, Jiujun Zhang, Dongdong Tang, Keshuang Li, Xin Tongji Univ Dept Comp Sci & Technol 4800 Caoan Rd Shanghai 201804 Peoples R China Tongji Univ Dept Transportat Informat & Control Engn Shanghai Peoples R China Shanghai Lujie Elect Technol Co Ltd Shanghai Peoples R China

Being one of the key techniques for unmanned autonomous vehicle, traffic sign recognition is applied to assist autopilot. Colors are very important clues to identify traffic signs;however, color-based methods suffer performance degradation in the case of light variation. convolutional neural network, as one of the deep learning methods, is able to hierarchically learn high-level features from the raw input. It has been proved that convolutional neural network-based approaches outperform the color-based ones. At present, inputs of convolutional neural networks are processed either as gray images or as three independent color channels;the learned color features are still not enough to represent traffic signs. Apart from colors, temporal constraint is also crucial to recognize video-based traffic signs. The characteristics of traffic signs in the time domain require further exploration. quaternion numbers are able to encode multi-dimensional information, and they have been employed to describe color images. In this article, we are inspired to present a quaternion convolutional neural network-based approach to recognize traffic signs by fusing spatial and temporal features in a single framework. Experimental results illustrate that the proposed method can yield correct recognition results and obtain better performance when compared with the state-of-the-art work.

关键词： Traffic sign recognition quaternion convolutional neural network unmanned autonomous vehicle

来源：评论

学校读者我要写书评

暂无评论

Color Random Valued Impulse Noise Removal Based on quaternion convolutional Attention Denoising network

引用

IEEE SIGNAL PROCESSING LETTERS 2022年 29卷 369-373页

作者： Cao, Yiqin Fu, Yangyi Zhu, Zhiliang Rao, Zhechu East China Jiaotong Univ Sch Software Nanchang 330013 Jiangxi Peoples R China Chinese Acad Sci Inst Software State Key Lab Comp Sci Beijing 100190 Peoples R China

A new quaternion convolutional attention denoising network known as DeQCANet for color random-valued impulse noise removal is proposed in this paper. First, a structural information extraction block based on a dilated convolution operation is designed to extract the structure and detail feature map. Subsequently, a quaternion convolutional neural network with a new quaternion map construction strategy is implemented to gain the color features across channels further. Finally, to integrate the global and local features, a feature enhancement block based on the attention mechanism is proposed to guide the network for impulse noise denoising. The experimental results demonstrate that the proposed denoising technique exhibits competitive performance compared to other well-known color image denoising methods.

关键词： quaternions Convolution Image color analysis Feature extraction Noise reduction Colored noise Kernel Color impulse noise quaternion deep learning quaternion convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Quatemion CNN-Based Diagnosis of Potato Leaf Diseases in India: Enhancing Accuracy and Reducing Crop Production Costs 3

Quatemion CNN-Based Diagnosis of Potato Leaf Diseases in Ind...

引用

3rd International Conference on Technological Advancements in Computational Sciences, ICTACS 2023

作者： Tripathi, Bharat Srivastava, Nidhi Tiwari, Amod Kumar Aiit Amity University Uttar Pradesh Lucknow India Rajkiya Engineering College Department of Computer Science Uttar Pradesh Sonbhadra India

ISBN: (纸本)9798350342338

Potato is one of India's main agricultural crops. In recent years, potato farms have become increasingly popular in India. However, a variety of ailments are driving up farmers' costs in the production of potatoes. Nevertheless, a number of diseases that are harming the crop are mostly to blame for the high cost of potato production. What is disrupting the farmer's schedule? Automation has been used to modernize the potato business and expedite illness diagnosis. Despite assertions, but potato leaf disease is a severe problem that has the potential to significantly lower crop production. Infected potato plants will exhibit on their leaves, the diseases early blight, Septoria blight, late blight, and others can be seen. If such outbreaks are detected early and sufficient intervention is carried out, farmers won't be at risk of suffering significant financial losses. A new model is released for precisely recognizing and diagnosing diseases in potato leaf stands in light of the experiment's findings. Making use of quaternion neural networks. While a variety of techniques, including the CNN model may be used in machine learning. For the purpose of identifying the disease in photographs of potato leaves, we developed an improved CNN model. In order to forecast the illness of potato leaves, this study adopts a sequential model based on quaternion CNN. On this model, this study's model accuracy was 96.2%. To differentiate between the two, the proposed model was checked on both healthy and sick potato leaves. The potato tree leaf is categorized as healthy and sick after the algorithm has been applied to the photos. © 2023 IEEE.

关键词： convolutionnal neural network deep learning quaternion algebra quaternion convolutional neural network support vector machine

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：