检索结果-内蒙古大学图书馆

CNN-RNN based method for license plate recognition

CAAI Transactions on Intelligence Technology 2018年第3期3卷 169-175页

作者： Palaiahnakote Shivakumara Dongqi Tang Maryam Asadzadehkaljahi Tong Lu Umapada Pal Mohammad Hossein Anisi Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia National Key Laboratory for Novel Software Technology Nanjing Universiry Nanjing People's Republic of China Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India School of Computer Science and Electronic Engineering University of Essex CO4 3SQ Colchester UK

Achieving good recognition results for License plates is challenging due to multiple adverse factors. For instance, in Malaysia, where private vehicle （e.g., cars） have numbers with dark background, while public vehicle （taxis/cabs） have numbers with white background. To reduce the complexity of the problem, we propose to classify the above two types of images such that one can choose an appropriate method to achieve better results. Therefore, in this work, we explore the combination of Convolutional Neural Networks （CNN） and Recurrent Neural Networks namely, BLSTM （Bi-Directional Long Short Term Memory）, for recognition. The CNN has been used for feature extraction as it has high discriminative ability, at the same time, BLSTM has the ability to extract context information based on the past information. For classification, we propose Dense Cluster based Voting （DCV）, which separates foreground and background for successful classification of private and public. Experimental results on live data given by MIMOS, which is funded by Malaysian Government and the standard dataset UCSD show that the proposed classification outperforms the existing methods. In addition, the recognition results show that the recognition performance improves significantly after classification compared to before classification.

关键词：车牌识别识别率发展现状人工智能

来源：评论

学校读者我要写书评

暂无评论

Exploring Joint Information of Multi-Scales for Vehicle Re-Identification 22

Exploring Joint Information of Multi-Scales for Vehicle Re-I...

引用

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Zhou, Yongjie Wang, Dahan School of Computer and Information Engineering Xiamen University of Technology Xiamen Chinese Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China

ISBN: (纸本)9781450396110

Vehicle re-identification (re-ID) is an essential component of intelligent video surveillance, which attempts to solve the problem of retrieving specific vehicle instances. The technical challenge is mainly the requirement that the algorithm be robust under different viewing angles, resolutions, occlusions, and lighting conditions, yet different conditions can arise where the appearance of the exact vehicle varies dramatically. In contrast, the appearance of two different vehicles is exceptionally similar. To overcome this enormous challenge: we adopt a novel multi-scales attention network architecture, which will feature representation for feature maps at different scales to enhance the recognition of intricate parts, and introduce an inter-coordinate attention module to build interdependencies between component positions, making it possible to build a more robust vehicle model feature representation, and finally this paper also proposes a camera-based vehicle re localization method that enables the model to calculate the vehicle occurrence probability using the potential information among road network cameras as a post-processing step to re-correct the confidence level of the re-identification ranking. Experimental results show that the method outperforms the reference method in all indexes even without post-processing. At the same time, the camera confidence correction can be used in overlay with the reordering clustering correction method, which can improve the results by four percentage points and MAP up to 81.4%. © 2022 ACM.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Complexity optimization of adaptive RBF networks

Complexity optimization of adaptive RBF networks

引用

13th International Conference on pattern recognition, ICPR 1996

作者： Leonardis, Aleš Bischof, Horst Department for Pattern Recognition and Image Processing Technical University Vienna Treitlstraße 3/1832 A -1040 Vienna Austria University of Ljubljana Faculty of Computer and Information Science Computer Vision Laboratory Ljubljana Slovenia

ISBN: (纸本)081867282X

We propose an extension of RBF networks which includes a mechanism for optimizing the complexity of the network. The approach involves two procedures: adaptation (training) and selection. The first procedure adaptively changes the locations and the width of the centers of the basis functions and trains the linear weights. The selection procedure performs the elimination of some of the basis functions using an objective function. By iteratively combining these two procedures we achieve a controlled way of training and modifying RBF networks, which balances accuracy, learning time, and complexity of the resulting network. © 1996 IEEE.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

A New Deep Fuzzy Based MSER Model for Multiple Document Images Classification 3rd

A New Deep Fuzzy Based MSER Model for Multiple Document Imag...

引用

3rd International Conference on pattern recognition and Artificial Intelligence, ICPRAI 2022

作者： Biswas, Kunal Shivakumara, Palaiahnakote Sivanthi, Sittravell Pal, Umapada Lu, Yue Liu, Cheng-Lin Ayub, Mohamad Nizam Bin Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China National Laboratory of Pattern Recognition Institute of Automation of Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy Beijing China

ISBN: (纸本)9783031090363

Understanding document images uploaded on social media is challenging because of multiple types like handwritten, printed and scene text images. This study presents a new model called Deep Fuzzy based MSER for classification of multiple document images (like handwritten, printed and scene text). The proposed model detects candidate components that represent dominant information irrespective of the type of document images by combining fuzzy and MSER in a novel way. For every candidate component, the proposed model extracts distance-based features which result in proximity matrix (feature matrix). Further, the deep learning model is proposed for classification by feeding input images and feature matrix as input. To evaluate the proposed model, we create our own dataset and to show effectiveness, the proposed model is tested on standard datasets. The results show that the proposed approach outperforms the existing methods in terms of average classification rate. © 2022, Springer Nature Switzerland AG.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

CDE-Net: A semi-supervised nucleus instance segmentation method based on center deviation estimation 22

CDE-Net: A semi-supervised nucleus instance segmentation met...

引用

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Yan, Yi Wang, Da-Han Ye, Haili Zhu, Shunzhi Li, Jianmin School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China

ISBN: (纸本)9781450396110

Cell nucleus segmentation is an important step in the diagnosis of tumor malignancy. In the case of out-of-focus, the cell nucleus boundary tends to be blurred, which increases the difficulty of cell segmentation and marking. Therefore, in the case of marking only some core instances, it is very important to realize the segmentation of core instances. In this paper, we propose a semi-supervised nucleus instance segmentation method based on anchor bias prediction that is achieved by our proposed center deviation estimation network (CDE-Net). By introducing the CDE branch to predict the offset degree of the anchor frame, and weighting the confidence of the anchor frame, more accurate prediction results can be obtained. The model adopts the semi-supervised training method to progressively learn the CDE-Net model, which alleviates the problem of imbalance between positive and negative samples caused by only marking part of the nuclear samples. The experimental results show that CDE-Net is superior to Mask R-CNN in many evaluation indicators, and achieves SOTA on the partially labelled MoNuSeg data set. © 2022 Association for Computing Machinery. All rights reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Handwritten mathematical expression recognition with self-attention 4

Handwritten mathematical expression recognition with self-at...

引用

4th International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2021

作者： Chi, Xueke Wang, Da-Han Wu, Yuefeng Wu, Yun Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China

ISBN: (纸本)9781450385053

Attention-based encoder-decoder models have made great success on handwritten mathematical expression recognition in recent years. However, this kind of method has the problem of attention drift, because under the local attention mechanism based on RNN, the high similarity between coding features can cause attention confusion. To settle this problem, we propose an encoder-decoder model with self-attention, which captures the global information of the feature map and fuses the local information of the CNN as complementary features. Experiments are conducted on the CROHME2014 and CROHME 2016 competition datasets. The experimental results show that, when only using the official training dataset, the proposed method achieves recognition accuracies of 51.98% and 50.74% on the CROHME2014 and CROHME2016 competition datasets, respectively, which outperforms the other methods significantly. The improvements demonstrate the effectiveness of the self-attention module. © 2021 ACM.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Online Discriminative Semantic-Preserving Hashing for Large-Scale Cross-Modal Retrieval 18th

Online Discriminative Semantic-Preserving Hashing for Large-...

引用

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

作者： Yi, Jinhan He, Yi Liu, Xin Department of Computer Science and Technology Huaqiao University Xiamen361021 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing210094 China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Xiamen China Fujian Key Laboratory of Big Data Intelligence and Security Xiamen China

ISBN: (纸本)9783030891879

Cross-modal hashing has drawn increasing attentions for efficient retrieval across different modalities, and existing methods primarily learn the hash functions in a batch based mode, i.e., offline methods. Nevertheless, the multimedia data often comes in a streaming fashion, which makes the batch based learning methods uncompetitive for large-scale streaming data due to the large memory consumption and calculation. To address this problem, we present an Online Discriminative Semantic-Preserving Hashing (ODSPH) method for large-scale cross-modal retrieval, featuring on fast training speed, low memory consumption and high retrieval accuracy. Within the proposed ODSPH framework, we utilize the newly coming data points to learn the hash codes and update hash functions in a stream manner. When new data comes, the corresponding hash codes are obtained by regressing the class label of the training examples. For hash function, we update it with the accumulated information from each round. Besides, we design a novel momentum updating method to adaptively update the hash function and reduce quantization loss, which can produce discriminative hash codes for high retrieval precision. Extensive experiments on three benchmark datasets show that the proposed ODSPH method improves the retrieval performance over the state-of-the-arts. © 2021, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Dynamic Updating of Partial Feature Maps for Image-based Real-Time recognition of Online Handwritten Chinese Text 22

Dynamic Updating of Partial Feature Maps for Image-based Rea...

引用

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Wu, Yuefeng Zhong, Ying Wang, Da-Han Chi, Xueke School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China

ISBN: (纸本)9781450396110

Online handwritten Chinese text recognition (OHCTR) has made certain progress in recent years. Most methods currently used are image-based text recognition which has achieved some success. However, it should be noticed that, it is difficult to smoothly recognize online handwritten texts in real-time, especially for long text lines. For real-time recognition of OHCT, the feature extraction of ever-extending text lines will be time-consuming and make the system un-humanization. Moreover, the feature extraction of the non-written part will be performed repeatedly, which is not suitable and has not been addressed by previous works. In this paper, we propose a method to dynamically update partial feature maps of the newly written part for real-time OHCTR. The basic idea is to update the feature maps according to the newly written stroke, which can avoid repeated convolutional computations and thus improve the recognition speed. The proposed method can handle the case of delayed strokes, and can greatly improve the speed of real-time recognition without any loss of accuracy. Experiments on the CASIA-OLHWDB and the ICDAR-2013 competition database demonstrate that our real-time recognition speed are multiplier increased compared with traditional text line recognition methods. © 2022 Association for Computing Machinery. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Attention-based Deep Learning Methods for Document Layout Analysis 22

Attention-based Deep Learning Methods for Document Layout An...

引用

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Sun, Hao-Yue Zhong, Ying Wang, Da-Han School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China

ISBN: (纸本)9781450396110

Deep learning has unique advantages in document layout analysis. In this paper, we propose to use the attention mechanism to improve the deep learning based methods for document layout analysis, and conducted comprehensive experiments to evaluate the effects of different models/modules/backbones. Firstly, the evaluated backbones include ResNet-50 and ResNet-101 for their high performance, and the popularly used Fast RCNN and Faster RCNN based methods. Secondly, for the loss function, the Focal loss function is also adopted to improve the performance of document layout analysis. Most importantly, we propose to integrate the attention mechanism into the deep learning-based methods to improve the performance. Specifically, when calculating the residual using this ResNet network, we use the attention to perform a dot product operation on the degraded accuracy to correct the residual error of the network calculation, which obtains a higher detection accuracy. We conducted experiments on the PubLayNet, DocBank and ICDAR-2013 datasets for evaluation. Experimental results show that, with the attention mechanism, the basic deep learning-based methods has been significantly improved in the task of document layout analysis, demonstrating the effectiveness of the proposed method. The focal loss that is designed to overcome the problem of imbalance number of training samples is also effective for document layout analysis. © 2022 Association for Computing Machinery. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Computational Intelligence Techniques in Diagnosis of Brain Diseases 1

引用

丛书名： SpringerBriefs in Applied Sciences and Technology

1000年

作者： Sasikumar Gurumoorthy Naresh Babu Muppalaneni Xiao-Zhi Gao

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：