检索结果-内蒙古大学图书馆

A shift-insensitive full reference image quality assessment model based on quadratic sum of gradient magnitude and LOG signals

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Congmin Mou, Xuanqin The Institute of Image Processing and Pattern Recognition Xi’an Jiaotong University Xi’an710049 China

image quality assessment that aims at estimating the subject quality of images, builds models to evaluate the perceptual quality of the image in different applications. Based on the fact that the human visual system (HVS) is highly sensitive to structural information, the edge information extraction is widely applied in different IQA metrics. According to previous studies, the image gradient magnitude (GM) and the Laplacian of Gaussian (LOG) operator are two efficient structural features in IQA tasks. However, most of the IQA metrics achieve good performance only when the distorted image is totally registered with the reference image, but fail to perform on images with small translations. In this paper, we propose an FR-IQA model with the quadratic sum of the GM and the LOG signals, which obtains good performance in image quality estimation considering shift-insensitive property for not well-registered reference and distortion image pairs. Experimental results show that the proposed model works robustly on three large scale subjective IQA databases which contain a variety of distortion types and levels, and stays in the state-of-the-art FR-IQA models no matter for single distortion type or across whole database. Furthermore, we validated that the proposed metric performs better with shift-insensitive property compared with the CW-SSIM metric that is considered to be shift-insensitive IQA so far. Meanwhile, the proposed model is much simple than the CW-SSIM, which is efficient for *** Codes 94A08 Copyright © 2020, The Authors. All rights reserved.

关键词： Laplace transforms

Multi-object tracking with pre-classified detection 5th

学校读者我要写书评

暂无评论

Multi-object tracking with pre-classified detection

5th International Conference on Robot Intelligence Technology and Applications, RiTA 2017

作者： Ren, Siqi Zhou, Yue He, Liming Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9783319784519

Tracking-by-detection is a popular tracking framework nowadays. The paradigm determines that detections will bring huge impact on the final tracking result. Based on the idea, to improve the tracking precision, we propose a novel algorithm which will first divide the detections into false ones, high uncertainty and low uncertainty ones. After that, we first penalize the false detection boundingboxes and then we construct low and high uncertainty tree for different types of detections. For low uncertainty detections, we construct their tracking trees once, for high uncertainty detections, we adopt an improved MHT to delay the data association decision till the end of the sliding windows and make the decision with all the information in the sliding window. Experiments demonstrate that our algorithm can achieved competitive results with state-of-the-art trackers on some challenging datasets such as MOTChallenge2016 [11]. © Springer International Publishing AG, part of Springer Nature 2019.

关键词： Object detection

SSIM-based CTU-level joint optimal bit allocation and rate distortion optimization

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Yang Mou, Xuanqin Institute of Image Processing and Pattern Recognition Xi'an Jiaotong University Xi'an710049 China

Structural similarity (SSIM)-based distortion DSSIM is more consistent with human perception than the traditional mean squared error DMSE. To achieve better video quality, many studies on optimal bit allocation (OBA) and rate-distortion optimization (RDO) used DSSIM as the distortion metric. However, many of them failed to optimize OBA and RDO jointly based on SSIM, thus causing a non-optimal R-DSSIM performance. This problem is due to the lack of an accurate R-DSSIM model that can be used uniformly in both OBA and RDO. To solve this problem, we propose a DSSIM-DMSE model first. Based on this model, the complex R-DSSIM cost in RDO can be calculated as simpler RDMSE cost with a new SSIM-related Lagrange multiplier. This not only reduces the computation burden of SSIM-based RDO, but also enables the R-DSSIM model to be uniformly used in OBA and RDO. Moreover, with the new SSIM-related Lagrange multiplier in hand, the joint relationship of R-DSSIM-λSSIM (the negative derivative of R-DSSIM) can be built, based on which the R-DSSIM model parameters can be calculated accurately. With accurate and unified R-DSSIM model, SSIM-based OBA and SSIM-based RDO are unified together in our scheme, called SOSR. Compared with the HEVC reference encoder HM16.20, SOSR saves 4%, 10%, and 14% bitrate under the same SSIM in all-intra, hierarchical and non-hierarchical low-delay-B configurations, which is superior to other state-of-the-art schemes. An improved version of this manuscript has been accepted by IEEE Transactions on Broadcasting DOI 10.1109/TBC.2021.3068871. The project page is located at http://***/web/xqmou/sosr. Copyright © 2020, The Authors. All rights reserved.

关键词： Signal distortion

Synergetic Learning Systems: Concept, Architecture, and Algorithms

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Guo, Ping Yin, Qian Image Processing & Pattern Recognition Lab Beijing Normal University Beijing100875 China

Drawing on the idea that brain development is a Darwinian process of "evolution + selection" and the idea that the current state is a local equilibrium state of many bodies with self-organization and evolution processes driven by the temperature and gravity in our universe, in this work, we describe an artificial intelligence system called the "Synergetic Learning Systems". The system is composed of two or more subsystems (models, agents or virtual bodies), and it is an open complex giant system. Inspired by natural intelligence, the system achieves intelligent information processing and decision-making in a given environment through cooperative/competitive synergetic learning. The intelligence evolved by the natural law of "it is not the strongest of the species that survives, but the one most responsive to change," while an artificial intelligence system should adopt the law of "human selection" in the evolution process. Therefore, we expect that the proposed system architecture can also be adapted in human-machine synergy or multi-agent synergetic systems. It is also expected that under our design criteria, the proposed system will eventually achieve artificial general intelligence through long term coevolution. Copyright © 2020, The Authors. All rights reserved.

关键词： Learning systems

End-To-End Graph-Based Deep Semi-Supervised Learning with Extended Graph Laplacian

学校读者我要写书评

暂无评论

End-To-End Graph-Based Deep Semi-Supervised Learning with Ex...

Chinese Automation Congress (CAC)

作者： Zihao Wang Enmei Tu Meng Zhou Jie Yang Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

The process of labeling samples costs time and resources but unlabeled samples are easier to obtain. Recently, graph-based deep semi-supervised learning (GDSSL) training a deep network using a small number of labeled samples and the abundant unlabeled samples has been demonstrated to be promising on image classification tasks. These methods construct a graph to represent the structure of the input data (or hidden features). The successes of these GDSSL algorithms depend upon the structure of the similarity graph. However, existing GDSSL approaches construct the graph using predefined rules (such as knn graph) or fixed similarity measures (such as Gaussian kernel), which may limit the potential of GDSSL. In this paper, we move further in this direction to propose a novel end-to-end GDSSL approach which fully optimizes the whole graph without such limitations. To this end, we concatenate two neural networks (feature network and similarity network) together to learn the categorical label and semantic similarity, respectively, and train the networks with a new regularization term, the extended graph Laplacian, to minimize a unified objective function. Extensive experiments on several benchmark datasets demonstrate that our approach could outperform existing approaches on image classification. Furthermore, as a side-product, the similarity network could give faithful semantic similarity measure of samples, which is not possessed by other GDSSL approaches.

关键词： Semantics Training Laplace equations Semisupervised learning Task analysis Neural networks Linear programming

Implications of neuroimaging findings in addiction

学校读者我要写书评

暂无评论

Psychoradiology 2023年第1期3卷 18-23页

作者： Xinwen Wen Lirong Yue Zhe Du Linling Li Yuanqiang Zhu Dahua Yu Kai Yuan School of Life Science and Technology Xidian UniversityXi’an 710126China School of Biomedical Engineering Medical SchoolShenzhen UniversityShenzhen 518060China Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging Shenzhen UniversityShenzhen 518060China Department of Radiology Xijing HospitalFourth Military Medical UniversityXi’an 710032China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing School of Information EngineeringInner Mongolia University of Science and TechnologyBaotou 014010China Engineering Research Center of Molecular and Neuro Imaging Ministry of Education Xidian UniversityXi’an 710126China Xi’an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information School of Life Science and TechnologyXidian UniversityXi’an 710126China

Addiction is a chronic and often relapsing brain disorder characterized by drug abuse and withdrawal symptoms and compulsive drug seeking(Koob and Volkow,2010)when access to the drug is *** leads to structural and fun... 详细信息

关键词： motivation finding seeking

image recognition Based on Combined Filters with Pseudoinverse Learning Algorithm 15th

学校读者我要写书评

暂无评论

Image Recognition Based on Combined Filters with Pseudoinver...

15th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2019

作者： Deng, Xiaodan Sun, Xiaoxuan Guo, Ping Yin, Qian Image Processing and Pattern Recognition Laboratory School of Systems Science Beijing Normal University Beijing100875 China Image Processing and Pattern Recognition Laboratory College of Information Science and Technology Beijing Normal University Beijing China

ISBN: (纸本)9783030198220

Deep convolution neural network (CNN) is one of the most popular Deep neural networks (DNN). It has won state-of-the-art performance in many computer vision tasks. The most used method to train DNN is Gradient descent-based algorithm such as Backpropagation. However, backpropagation algorithm usually has the problem of gradient vanishing or gradient explosion, and it relies on repeated iteration to get the optimal result. Moreover, with the need to learn many convolutional kernels, the traditional convolutional layer is the main computational bottleneck of deep CNNs. Consequently, the current deep CNN is inefficient on computing resource and computing time. To solve these problems, we proposed a method which combines Gabor kernel, random kernel and pseudoinverse kernel, incorporating with pseudoinverse learning (PIL) algorithm to speed up DNN training processing. With the multiple fixed convolution kernels and pseudoinverse learning algorithm, it is simple and efficient to use the proposed method. The performance of the proposed model is tested on MNIST and CIFAR-10 datasets without using GPU. Experimental results show that our model is better than existing benchmark methods in speed, at the same time it has the comparative recognition accuracy. © 2019, IFIP International Federation for Information processing.

关键词： image recognition

Hierarchical correlation stereo matching network 2nd

学校读者我要写书评

暂无评论

Hierarchical correlation stereo matching network

2nd Chinese Conference on pattern recognition and Computer Vision, PRCV 2019

作者： Chen, Xuliang Zhou, Yue Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9783030317256

Recently, stereo matching from a pair of rectified images has been cast as a supervised learning task using the powerful representation of convolutional neural networks. However, existing methods only utilize last feature maps output from Siamese Networks to compute similarity measurement, which are lack of multi-levels similarity information to construct an informative cost volume. To solve this problem, we propose a hierarchical correlation operation to compute similarity of stereo pairs at multiple levels. In addition, to yield accurate disparity in illposed region, we propose a stacked hourglass feature network with dense connections to effectively incorporate context information. Then, hybrid matching cost volume is built leveraging hierarchical correlation features and concatenation features of left and right. 3D CNN encoder-decoder architecture is utilized to regularize the cost volume and regress disparity. Experiments demonstrate that our network achieves competitive performance with state-of-the-art methods on Scene Flow, KITTI 2012, and KITTI 2015 datasets. © Springer Nature Switzerland AG 2019.

关键词： Neural networks

BREAK: BRONCHI RECONSTRUCTION BY GEODESIC TRANSFORMATION AND SKELETON EMBEDDING

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yu, Weihao Zheng, Hao Zhang, Minghui Zhang, Hanxiao Sun, Jiayuan Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Department of Respiratory and Critical Care Medicine Department of Respiratory Endoscopy Shanghai Chest Hospital Shanghai Engineering Research Center of Respiratory Endoscopy China

Airway segmentation is critical for virtual bronchoscopy and computer-aided pulmonary disease analysis. In recent years, convolutional neural networks (CNNs) have been widely used to delineate the bronchial tree. However, the segmentation results of the CNN-based methods usually include many discontinuous branches, which need manual repair in clinical use. A major reason for the breakages is that the appearance of the airway wall can be affected by the lung disease as well as the adjacency of the vessels, while the network tends to overfit these special patterns in the training set. To learn robust features for these areas, we design a multi-stage framework that adopts the geodesic distance transform to capture the intensity changes between airway lumen and wall. Another reason for the breakages is the intra-class imbalance. Since the volume of the peripheral bronchi may be much smaller than the large branches in an input patch, the common segmentation loss is not sensitive to the breakages among the distal branches. Therefore, in this paper, a breakage-sensitive regularization term is designed and can be easily combined with other loss functions. Extensive experiments are conducted on publicly available datasets. Compared with state-of-the-art methods, our framework can detect more branches while maintaining competitive segmentation performance. Copyright © 2022, The Authors. All rights reserved.

关键词： Computer aided analysis