检索结果-内蒙古大学图书馆

19th International Conference on Neural Information processing, ICONIP 2012

作者： Ma, Jin Duan, Fuqing Guo, Ping Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing 100875 China

ISBN: (纸本)9783642344992

In the study of object recognition, image texture segmentation has being a hot and difficult aspect in computer vision. Feature extraction and texture segmentation algorithm are two key steps in texture segmentation. An effective texture description is the important factor of texture segmentation. In this paper, the neuronal activation degree (NAD) of visual model is exploited as the texture description of image patches. By processing the length and direction of NAD, we develop an effective segmentation strategy. First, the length of the NAD are used to partition blank area and non-blank area, then the mark index of neuron is used, which is maximally activated to identify the label of each segment unit to get an initial segmentation. Finally, region merging steps is exerted to get a desired result. © 2012 Springer-Verlag.

关键词： Image texture

来源：评论

学校读者我要写书评

暂无评论

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

Image Recognition Based on Combined Filters with Pseudoinver...

引用

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

来源：评论

学校读者我要写书评

暂无评论

Optimal stopping condition for iterative deconvolution method by the measurement of image texture

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2012年第15期6卷 109-119页

作者： Wang, Ze Yan, Luxin Jin, Mingzhi State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

The non-regularized iterative image restoration algorithms have been widely investigated in the literature. In this work, we focus on a common issue of non-regularized iterative methods, the stopping condition. A no-reference criterion of optimal stopping condition for non-regularized iterative deconvolution called Total Local Binary patterns (TLBP), which is based on the measurement of varying image texture during the deblurring procedure, is proposed. The metric utilizes the minimum of TLBP that is computed according to the LBP map of the blurred image to obtain the optimal restored image. We applied the Richardson-Lucy (RL) method to test the blurred version of the synthetic images and real images in experiments. Deconvolution experiments for Gaussian and out-offocus blur validate the effectiveness of the proposed method.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A novel and fast method for precise license plate location from digital images based on fusion of salient features

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2012年第19期6卷 511-519页

作者： Wang, Ran Wang, Guoyou Liu, Jianguo Chen, Zhong Shi, Yu Image Processing and Intelligent Key Laboratory of Ministry of Education of China Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 730074 China

The license plate location technique is an important image processing step in license plate recognition system. Vehicle license plates are distinguished from backgrounds using features proposed in existing literatures. However, the effect of location is quite affected by feature selection. In this paper, we propose a method of precise license plate location fusing salient features. The method is mainly divided into three steps. First, candidate license plate regions are detected using improved Harris corner feature with much less time than traditional method. Then, candidates are sifted to only retain license plates based on two salient features named color combination and mean difference which are first proposed in this paper. Finally, the license plates are located precisely according to the projection feature. In experiment, the proposed algorithm was tested with 1942 real images captured in different environment and the license plates are successfully located as 97.6% in average with only 109ms. The experiment results demonstrates the effectiveness and efficient of our algorithm.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Empirically validating software metrics for risk prediction based on intelligent methods

Journal of Digital Information Management

引用

Journal of Digital Information Management 2007年第3期5卷 99-106页

作者： Xu, Zhihong Zheng, Xin Guo, Ping Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing 100875 China School of Computer Science Beijing Institute of Technology Beijing 100081 China

The software systems which are related to national science and technology projects are very crucial. This kind of systems always involves high technical factors and has to spend a large amount of money, so the quality and reliability of the software deserve to be further studied. Hence, we propose to apply four intelligent classification techniques most used in data mining fields, including Bayesian belief networks (BBN), nearest neighbor (NN), rough set (RS) and decision tree (DT), to validate the usefulness of software metrics for risk prediction. Results show that comparing with metrics such as Lines of code (LOC) and Cyclomatic complexity (V(G)) which are traditionally used for risk prediction, Halstead program difficulty (D), Number of executable statements (EXEC) and Halstead program volume (V) are the more effective metrics as risk predictors. By analyzing obtained results we also found that BBN was more effective than the other three methods in risk prediction.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Mallat fusion for multi-source remote sensing classification

Mallat fusion for multi-source remote sensing classification

引用

ISDA 2006: Sixth International Conference on Intelligent Systems Design and Applications

作者： Dongdong, Cao Qian, Yin Ping, Guo IEEE Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing 100875 China

ISBN: (纸本)0769525288

The fusion of multi-source remote sensing data is to offer improved accuracies in land cover classification. The conventional fusion methods such as HIS and PCA can not enhance information and simultaneously preserve high fidelity. Thus, the fused image is not preferable for classification. In this paper, the multi-source remote sensing data fusion based on Mallat algorithm for classification is proposed. The purpose of fusion is to create a new image that is more suitable for recognition. The topic focuses on the pyramid decomposition and choosing coefficients in the fusion process. The performance of proposed method is assessed by statistical methods and its effectiveness also testified by classification accuracies. © 2006 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

PupilFace: A Cascaded Face Detection and Location Network Fusing Attention 18th

PupilFace: A Cascaded Face Detection and Location Network Fu...

引用

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Li, Xiang Zou, Jiancheng Image Processing and Pattern Recognition Laboratory North China University of Technology Beijing100000 China

ISBN: (纸本)9783030893699

Although the development of uncontrolled face detection and location technology have made great progress, there are some problems needing to be solved in more complicated situation, such as massive occlusion and pose variation. In this paper, we propose a robust one-stage face detection and location network named PupilFace. It can locate faces of different sizes at the pixel level in complex scenarios. Specifically, we have made contributions in the following three aspects: (1) Using a lightweight backbone, we can not only detect images of dense faces, but also mark facial landmarks in pictures of various scale. In this paper, the pictures are difficult to detect because of massive occlusion or tiny faces. On the WIDER FACE hard test set, PupilFace performs better than other state-of-the-art networks. (2) The addition of the attention module–Hard Efficient Channel Attention (HECA), proposed by us, enhances the connection between the feature channels and improves the detection performance without reducing the dimension. The parameters and computations of HECA, against the parameters and computations of MobileNetV2 are 9 vs. 3.34M and 5.1e−4 GFLOPs vs. 0.32 GFLOPs. (3) We can employ varying-depths backbones accordingly to different detection and location tasks, so the model can be popularized in different fields. Extra annotations and code have been made available at: https://***/Ideal-maths/PupilFace. © 2021, Springer Nature Switzerland AG.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Smart electric valve controller based on all digital phase-locked loop

引用

Sensors and Transducers 2014年第2期165卷 89-95页

作者： Xiaoling, Li School of Computer Science and Technology Chengdu University Chengdu 610106 China University Key Laboratory of Pattern Recognition and Intelligent information Processing Chengdu 610106 China

Electric valve has been applied to various occasions and domains. In some adverse environments where such defects of traditional control system as low efficiency and poor safety have been exposed, optical encoder is adopted to detect the motor's angular speed and displacement and ADPLL is used for generating control logic, so as to regulate switching frequency and duty ratio of pulse wavelength modulation (PWM), alter the motor's input voltage and current and achieve the open and close control of Electric valve. The system can automatically regulate the rotating speed and the dragging torque of motor based on the open and close position, rotating speed and torque of the valve to make sure that the motor can achieve the best rotating speed and torque. The results of the test by motor 90ZY24-200 prove that the system has prompt response, high accuracy, little harmonic and ripple range;it can also automatically adapt to the torque alteration to realize the protective function of direct current (DC) motor. Electric valve control based on ADPLL can not only realize functions of the whole system, but also enjoys a stable and reliable performance. It can reduce the harmonic and ripple, and help the whole system achieve real-time remote control, data collection and transmission, and display the motor torque in LED, so as to control the valve flow stably and accurately through DC motor. © 2014 IFSA Publishing, S. L.

关键词： Locks (fasteners)

来源：评论

学校读者我要写书评

暂无评论

Cost reference particle filter based on adaptive particle swarm optimization in observation uncertainty

Cost reference particle filter based on adaptive particle sw...

引用

作者： Hu, Zhen-Tao Liu, Xian-Xing Jin, Yong Laboratory of Image Processing and Pattern Recognition Henan University Kaifeng 475001 China

ISBN: (纸本)9789881725592

Aiming at the effective approximation of sampling particle set relative to system state in observation uncertainty, a novel cost reference particle filter based on adaptive particle swarm optimization is proposed. In the new algorithm, the cost function and the risk function are firstly introduced to realize reasonable utilization of the latest observation. In addition, according to the prior modeling information, a new adaptive method is given to solve the selection of limit velocity. And then the movement of particle set towards the region of high weight particle is completed by particle swarm optimization strategy. The algorithm realizes the dynamic combination of the cost reference particle filter and the adaptive particle swarm optimization, and the reliability and stabilize of sampling particle set relative to system state are improved. The theoretical analysis and experimental results show the efficiency of the proposed algorithm. © 2011 Chinese Assoc of Automati.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Research on a novel restoration algorithm of turbulence-degraded images with alternant iterations

引用

Journal of Systems Engineering and Electronics 2006年第3期17卷 477-482页

作者： Liu Chunsheng Hong Hanyu Zhang Tianxu Inst. for Pattern Recognition and AI State Key Laboratory of Image Processing and Intelligent Control Huazhong Univ. of Science and Technology Wuhan 430074 P. R. China

A new restoration algorithm based on double loops and alternant iterations is proposed to restore the object image effectively from a few frames of turbulence-degraded images, Based on the double loops, the iterative relations for estimating the turbulent point spread function PSF and object image alternately are derived. The restoration experiments have been made on computers, showing that the proposed algorithm can obtain the optimal estimations of the object and the point spread function, with the feasibility and practicality of the proposed algorithm being convincing.

关键词： turbulence-degraded image image restoration double loops alternant iterations.

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：