检索结果-内蒙古大学图书馆

Air Writing: Recognizing Multi-Digit Numeral String Traced in Air Using RNN-LSTM Architecture

SN computer Science 2021年第1期2卷 1-13页

作者： Rahman, Adil Roy, Prasun Pal, Umapada Department of Information Technology Heritage Institute of Technology Kolkata India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

Air writing provides a more natural and immersive way of interacting with devices, with the potential of having significant application in fields like augmented reality and education. However, such systems often rely on expensive hardware, making them less accessible for general purposes. In this study, we propose a robust and inexpensive system for the recognition of multi-digit numerals traced in an air-writing environment which uses only a generic device camera for input. We employ a sliding window-based algorithm to isolate a small segment of the input for processing. A dual network configuration consisting of RNN-LSTM networks are used for noise elimination and digit recognition. We conduct our experiments on English numerals using the MNIST dataset as the baseline model to allow easy adaptability of our method. Our results are further improved by the use of Pendigits and ISI-Air online datasets. We observed a drop in accuracy with increase in the number of digits owing to the accumulation of transition noise. However, bi-directional scanning considerably reduces the impact of such noise on the recognition accuracy. Under standard conditions, our system produced an accuracy of 98.75% and 85.27% for single and multi-digit English numerals, respectively. Incorporation of selective frame skipping in the sliding window algorithm resulted in a 60% reduction in computational time, significantly improving the system performance. We provide a link to the source code of our system at the end of this paper. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Air writing Handwritten character recognition Human–computer interaction Long short-term memory Recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes

arXiv

引用

arXiv 2023年

作者： Das, Alloy Biswas, Sanket Pal, Umapada Lladós, Josep Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India The Computer Vision Center Computer Science Department Universitat Autónoma de Barcelona Barcelona Spain

When used in a real-world noisy environment, the capacity to generalize to multiple domains is essential for any autonomous scene text spotting system. However, existing state-of-the-art methods employ pretraining and fine-tuning strategies on natural scene datasets, which do not exploit the feature interaction across other complex domains. In this work, we explore and investigate the problem of domain-agnostic scene text spotting, i.e., training a model on multi-domain source data such that it can directly generalize to target domains rather than being specialized for a specific domain or scenario. In this regard, we present the community a text spotting validation benchmark called Under-Water Text (UWT) for noisy underwater scenes to establish an important case study. Moreover, we also design an efficient super-resolution based end-to-end transformer baseline called DA-TextSpotter which achieves comparable or superior performance over existing text spotting architectures for both regular and arbitrary-shaped scene text spotting benchmarks in terms of both accuracy and model efficiency. The dataset, code and pre-trained models will be released upon acceptance. © 2023, CC BY-SA.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Finding discriminative filters for specific degradations in blind super-resolution 21

Finding discriminative filters for specific degradations in ...

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Liangbin Xie Xintao Wang Chao Dong Zhongang Qi Ying Shan Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences and ARC Lab Tencent PCG ARC Lab Tencent PCG Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences and Shanghai AI Laboratory Shanghai China

ISBN: (纸本)9781713845393

Recent blind super-resolution (SR) methods typically consist of two branches, one for degradation prediction and the other for conditional restoration. However, our experiments show that a one-branch network can achieve comparable performance to the two-branch scheme. Then we wonder: how can one-branch networks automatically learn to distinguish degradations? To find the answer, we propose a new diagnostic tool – Filter Attribution method based on Integral Gradient (FAIG). Unlike previous integral gradient methods, our FAIG aims at finding the most discriminative filters instead of input pixels/features for degradation removal in blind SR networks. With the discovered filters, we further develop a simple yet effective method to predict the degradation of an input image. Based on FAIG, we show that, in one-branch blind SR networks, 1) we are able to find a very small number of (1%) discriminative filters for each specific degradation; 2) The weights, locations and connections of the discovered filters are all important to determine the specific network function. 3) The task of degradation prediction can be implicitly realized by these discriminative filters without explicit supervised learning. Our findings can not only help us better understand network behaviors inside one-branch blind SR networks, but also provide guidance on designing more efficient architectures and diagnosing networks for blind SR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-Uniform Illumination Attack for Fooling Convolutional Neural Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Jain, Akshay Dubey, Shiv Ram Singh, Satish Kumar Santosh, K.C. Chaudhuri, Bidyut Baran Indian Institute of Information Technology Allahabad Computer Vision and Biometrics Lab Department of Information Technology Uttar Pradesh Prayagraj211015 India University of South Dakota AI Research Lab Department of Computer Science VermillionSD57069 United States Indian Statistical Institute Computer Vision and Pattern Recognition Unit Kolkata700108 India

Convolutional Neural Networks (CNNs) have made remarkable strides;however, they remain susceptible to vulnerabilities, particularly to image perturbations that humans can easily recognize. This weakness, often termed as 'attacks,' underscores the limited robustness of CNNs and the need for research into fortifying their resistance against such manipulations. This study introduces a novel Non-Uniform Illumination (NUI) attack technique, where images are subtly altered using varying NUI masks. Extensive experiments are conducted on widely-accepted datasets including CIFAR10, TinyImageNet, CalTech256 and NWPU-RESISC45 focusing on image classification with 12 different NUI masks. The resilience of VGG, ResNet, MobilenetV3-small, InceptionV3 and efficientNet b0 models against NUI attacks are evaluated. Our results show a substantial decline in the CNN models' classification accuracy when subjected to NUI attacks, due to changes in the image pixel value distribution, indicating their vulnerability under non-uniform illumination. To mitigate this, a defense strategy is proposed, including NUI-attacked images, generated through the new NUI transformation, into the training set. The results demonstrate a significant enhancement in CNN model performance when confronted with perturbed images affected by NUI attacks. This strategy seeks to bolster CNN models' resilience against NUI attacks. A comparative study with other attack techniques shows the effectiveness of the NUI attack and defense technique. © 2020 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deformation Robust Text Spotting with Geometric Prior

Deformation Robust Text Spotting with Geometric Prior

引用

IEEE International Conference on Image Processing

作者： Xixuan Hao Aozhong Zhang Xianze Meng Bin Fu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences The University of Hong Kong

The goal of text spotting is to perform text detection and recognition simultaneously. Although the diversity of luminosity and orientation in scene texts has been widely studied, the font diversity and shape variance of the same character are ignored in recent works, since most characters in natural images are rendered in standard fonts. To solve this problem, we present a Chinese Artistic Dataset, termed as ARText, which contains 33, 000 artistic images with rich shape deformation and font diversity. Based on this database, we develop a deformation robust text spotting method (DR TextSpotter) to solve the recognition problem of complex deformation of characters in different fonts. Specifically, we propose a geometric prior module to highlight the important features based on the unsupervised landmark detection sub-network. A graph convolution network is further constructed to fuse the character features and landmark features, and then performs semantic reasoning to enhance the discrimination for different characters. The experiments are conducted on ARText and IC19-ReCTS datasets. Our results demonstrate the effectiveness of our proposed method. The datasets and models will become publicly available after publication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks Exploiting Attributes of Biological Neurons

arXiv

引用

arXiv 2023年

作者： Singh, Neeraj Kumar Pal, Nikhil R. Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Electronics and Communication Sciences Unit Indian Statistical Institute Kolkata India

In this era of artificial intelligence, deep neural networks like Convolutional Neural Networks (CNNs) have emerged as front-runners, often surpassing human capabilities. These deep networks are often perceived as the panacea for all challenges. Unfortunately, a common downside of these networks is their"black-box" character, which does not necessarily mirror the operation of biological neural systems. Some even have millions/billions of learnable (tunable) parameters, and their training demands extensive data and time. Here, we integrate the principles of biological neurons in certain layer(s) of CNNs. Specifically, we explore the use of neuro-science-inspired computational models of the Lateral Geniculate Nucleus (LGN) and simple cells of the primary visual cortex. By leveraging such models, we aim to extract image features to use as input to CNNs, hoping to enhance training efficiency and achieve better accuracy. We aspire to enable shallow networks with a Push-Pull Combination of Receptive Fields (PP-CORF) model of simple cells as the foundation layer of CNNs to enhance their learning process and performance. To achieve this, we propose a two-tower CNN, one shallow tower and the other as ResNet 18. Rather than extracting the features blindly, it seeks to mimic how the brain perceives and extracts features. The proposed system exhibits a noticeable improvement in the performance (on an average of 5% − 10%) on CIFAR-10, CIFAR-100, and ImageNet-100 datasets compared to ResNet-18. We also check the efficiency of only the Push-Pull tower of the network. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolutional neural 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

Neural Transformation Fields for Arbitrary-Styled Font Generation

Neural Transformation Fields for Arbitrary-Styled Font Gener...

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Bin Fu Junjun He Jianjun Wang Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory

Few-shot font generation (FFG), aiming at generating font images with a few samples, is an emerging topic in recent years due to the academic and commercial values. Typically, the FFG approaches follow the style-content disentanglement paradigm, which transfers the target font styles to characters by combining the content representations of source characters and the style codes of reference samples. Most existing methods attempt to increase font generation ability via exploring powerful style representations, which may be a sub-optimal solution for the FFG task due to the lack of modeling spatial transformation in transferring font styles. In this paper, we model font generation as a continuous transformation process from the source character image to the target font image via the creation and dissipation of font pixels, and embed the corresponding transformations into a neural transformation field. With the estimated transformation path, the neural transformation field generates a set of intermediate transformation results via the sampling process, and a font rendering formula is developed to accumulate them into the target font image. Extensive experiments show that our method achieves state-of-the-art performance on few-shot font generation task, which demonstrates the effectiveness of our proposed model. Our implementation is available at: https://***/fubinfb/NTF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-label learning on principles of reverse k-nearest neighbourhood

Multi-label learning on principles of reverse k-nearest neig...

引用

作者： Sadhukhan, Payel Palit, Sarbani Machine Intelligence Unit Indian Statistical Institute Kolkata India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

In this article, we present a novel neighbourhood based multi-label classifier, Multi-label Learning on principles of Reverse k-Nearest Neighbourhood (ML-RkNN) where we estimate the neighbourhood of the points on the basis of their reverse k-nearest neighbourhood (RkNN). Through RkNN, for the same value of k, we get different number of neighbours for different instances and this happens adaptively according to the neighbourhood configuration of the points. The automatically adaptive neighbourhood helps us in better learning of the local configurations around the points. Our scheme also facilitates implicit handling of the local imbalances prevailing in the datasets by comparing the class distributions of the test points and their reverse nearest neighbours. This implicit and adaptive handling is particularly useful for multi-label label datasets, whose labels are differentially imbalanced. Empirical study is performed on 10 real-world multi-label datasets considering five neighbourhood based multi-label learners. Macro F1 is used as the evaluating metric. The proposed method has given statistically superior and statistically comparable performances with respect to three and two comparing methods respectively. Additionally, we have explored the use of two different distance metrics, Euclidean and Jaccard in our scheme for nominal datasets. © 2020 John Wiley & Sons, Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

NLP-IISERB@Simpletext2022: To Explore the Performance of BM25 and Transformer Based Frameworks for Automatic Simplification of Scientific Texts

NLP-IISERB@Simpletext2022: To Explore the Performance of BM2...

引用

2022 Conference and Labs of the Evaluation Forum, CLEF 2022

作者： Saha, Sourav Roy, Dwaipayan Goud, B. Yuvaraj Reddy, Chethan S. Basu, Tanmay Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Department of Computational and Data Sciences Indian Institute of Science Education and Research Kolkata India Department of Data Science and Engineering Indian Institute of Science Education and Research Bhopal India

CLEF SimpleText 2022 lab focuses on developing effective systems to identify relevant passages from a given set of scientific articles. The lab has organized three tasks this year. Task 1 is focused on passage retrieval from the given data for a query text. These passages can be complex and hence require further simplification to be carried out in tasks 2 and 3. The BioNLP research group at the Indian institute of Science Education and Research Bhopal (IISERB) in collaboration with two different information retrieval research groups at IISER Kolkata and ISI Kolkata participated only in Task 1 of this challenge and submitted three runs using three different retrieval models. The paper explores the performance of these retrieval models for the given task. We used a standard BM25 model as our first run to identify 1000 relevant passages for each query. Moreover, the passages for each query were ranked based on their similarity scores generated by the BM25 model. For our second run, we used a BERT (Bidirectional Encoder Representations from Transformers) based re-ranking method, called as Mono-BERT to further rank the 1000 passages retrieved by our first run for each query. A pre-trained sequence to sequence model based re-ranking method, called MonoT5 was used as our third run to reorder the 1000 passages retrieved by the Mono-BERT model for each query. As the official results of this task are not yet announced, we cannot explore the performance of our submissions. However, we have manually checked the retrieved results of many queries for each run, which indicate that the performance improved from run 1 to run 2 and further to run 3. © 2022 Copyright for this paper by its authors.

关键词： Information retrieval

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：