检索结果-内蒙古大学图书馆

8th IAPR Workshop on Graphics recognition, GREC 2009

作者： Roy, Partha Pratim Pal, Umapada Lladós, Josep 08193 Spain Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata 108 India

ISBN: (纸本)364213727X

Interpretation of graphical document images is a challenging task as it requires proper understanding of text/graphics symbols present in such documents. Difficulties arise in graphical document recognition when text and symbol overlapped/touched. Intersection of text and symbols with graphical lines and curves occur frequently in graphical documents and hence separation of such symbols is very difficult. Several pattern recognition and classification techniques exist to recognize isolated text/symbol. But, the touching/overlapping text and symbol recognition has not yet been dealt successfully. An interesting technique, Scale Invariant Feature Transform (SIFT), originally devised for object recognition can take care of overlapping problems. Even if SIFT features have emerged as a very powerful object descriptors, their employment in graphical documents context has not been investigated much. In this paper we present the adaptation of the SIFT approach in the context of text character localization (spotting) in graphical documents. We evaluate the applicability of this technique in such documents and discuss the scope of improvement by combining some state-of-the-art approaches. © 2010 Springer-Verlag.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Segmentation of co-articulated basic units in isolated Bangla words using multifactorial analysis

Segmentation of co-articulated basic units in isolated Bangl...

引用

IEEE INDICON 2004 - 1st India Annual Conference

作者： Chattopadhyay, Tanushyam Chaudhuri, B.B. Systems TCS Kolkata Computer Vision and Pattern Recognition Unit Indian Statistical Institute Jawaharlal Nehru

ISBN: (纸本)0780389093

One of the major challenges in speech synthesis and recognition is co-articulated unit segmentation. In this paper we present a novel technique for segmenting the basic co-articulated units using multifactorial analysis based approach. The proposed algorithm is applied on isolated spoken words in Bangla. The results obtained from a considerably large database show the strength of the approach. ©2004 IEEE.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Skeletal shape extraction from dot patterns by self-organization

Skeletal shape extraction from dot patterns by self-organiza...

引用

13th International Conference on pattern recognition, ICPR 1996

作者： Datta, A. Parui, S.K. Chaudhuri, B.B. Computer and Statistical Service Centre Indian Statistical Institute Calcutta 700035 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Calcutta 700035 India

ISBN: (纸本)081867282X

Extraction of skeletal shape from a 2D dot pattern is discussed. We use a self-organizing neural network model to get a piecewise linear approximation of a skeleton of the pattern. It is found that even without a proper definition of a skeleton, the proposed algorithm is able to produce skeletons that are quite close to what we intuitively feel it should be. In Kohonen's self-organizing model, the set of processors and their neighbourhoods are fixed. We suggest here some modifications of it in which the set of processors and their neighbourhoods change adaptively. © 1996 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Low Resource Degraded Quality Document Image Binarization - Domain Adaptation is the Way 13

Low Resource Degraded Quality Document Image Binarization - ...

引用

13th indian Conference on computer vision, Graphics, and Image Processing, ICVGIP 2022

作者： Kundu, Ahana Bhattacharya, Ujjwal Computer Vision and Pattern Recognition Indian Statistical Institute West Bengal Kolkata India

ISBN: (纸本)9781450398237

Usually, image binarization plays a crucial role in automatic analysis of degraded documents from their captured images. However, this binarization task is often difficult due to a number of reasons including the high similarity between noisy background and faded foreground pixels. The study presented here is particularly focused on binarization of images of low-resource degraded quality documents based on a set of recently collected image samples of several rare, ancient and severely degraded quality printed documents of Bangla, the 2nd and 5th most popular script of India and the world respectively. This new collection of degraded document image samples will henceforth be referred as 'ISIDDI2' and it consists of 139 images of Bangla old document pages. Samples of 'ISIDDI', another existing database of degraded Bangla document image samples, have also been used in the present study. A novel deep architecture based on attention UNET++ with dilated convolution operation is proposed for this binarization task. The model is optimized using human vision perceptible distance reciprocal distortion (DRD) loss. Since the binarization ground truth of samples of both 'ISIDDI2' and 'ISIDDI' are not available, the proposed network has been trained using samples of DIBCO and H-DIBCO datasets and an unsupervised domain adaptation (DA) module is employed for adaptation of the proposed architecture to the degradation patterns of 'ISIDDI2' or 'ISIDDI' samples. The proposed binarization strategy includes certain post-processing operation based on a modified k-neighbourhood based approach for recovery of broken characters. Results of our extensive experimentation show that the proposed binarization strategy has improved the binarization output of state-of-the-art methods on both ISIDDI2 and ISIDDI datasets. Also, its performance on well-known DIBCO samples is satisfactory. © 2022 ACM.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

ClueNet: A deep framework for occluded pedestrian pose estimation 30

ClueNet: A deep framework for occluded pedestrian pose estim...

引用

30th British Machine vision Conference, BMVC 2019

作者： Kishore, Perla Sai Raj Das, Sudip Mukherjee, Partha Sarathi Bhattacharya, Ujjwal Institute of Engineering and Management Kolkata India Indian Statistical Institute Computer Vision and Pattern Recognition Unit Kolkata India

Pose estimation of a pedestrian helps to gather information about the current activity or the instant behaviour of the subject. Such information is useful for autonomous vehicles, augmented reality, video surveillance, etc. Although a large volume of pedestrian detection studies are available in the literature, detection of the same in situations of significant occlusions still remains a challenging task. In this work, we take a step further to propose a novel deep learning framework, called ClueNet, to detect as well as estimate the entire pose of occluded pedestrians in an unsupervised manner. ClueNet is a two stage framework where the first stage generates visual clues for the second stage to accurately estimate the pose of occluded pedestrians. The first stage employs a multi-task network to segment the visible parts and predict a bounding box enclosing the visible and occluded regions for each pedestrian. The second stage uses these predictions from the first stage for pose estimation. Here we propose a novel strategy, called Mask and Predict, to train our ClueNet to estimate the pose even for occluded regions. Additionally, we make use of various other training strategies to further improve our results. The proposed work is first of its kind and the experimental results on CityPersons and MS COCO datasets show the superior performance of our approach over existing methods. © 2019. The copyright of this document resides with its authors.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Distance Metric Learned Collaborative Representation Classifier(DML-CRC)

IEEE Letters of the Computer Society

引用

IEEE Letters of the computer Society 2020年第2期3卷 34-37页

作者： Chakraborti, Tapabrata McCane, Brendan Mills, Steven Pal, Umapada Department of Computer Science University of Otago Dunedin9016 New Zealand Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India

Any generic deep machine learning algorithm is essentially a function fitting exercise, where the network tunes its weights and parameters to learn discriminatory features by minimizing some cost function. Though the network tries to learn the optimal feature space, it seldom tries to learn an optimal distance metric in the cost function, and hence misses out on an additional layer of abstraction. We present a simple effective way of achieving this by learning a generic Mahalanabis distance in a collaborative loss function in an end-to-end fashion with any standard convolutional network as the feature learner. The proposed method DML-CRC gives state-of-the-art performance on benchmark fine-grained classification datasets CUB Birds, Oxford Flowers and Oxford-IIIT Pets using the VGG-19 deep network. The method is network agnostic and can be used for other similar classification tasks. © 2018 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A corpus for OCR research on mathematical expressions

引用

International Journal on Document Analysis and recognition 2005年第4期7卷 241-259页

作者： Garain, Utpal Chaudhuri, B.B. Computer Vision and Pattern Recognition Unit Indian Statistical Institute Calcutta-700 035 203 B.T. Road India

This paper is concerned with research on OCR (optical character recognition) of printed mathematical expressions. Construction of a representative corpus of technical and scientific documents containing expressions is discussed. A statistical investigation of the corpus is presented, and usefulness of this analysis is demonstrated in the related research problems, namely, (i) identification and segmentation of expression zones from the rest of the document, (ii) recognition of expression symbols, (iii) interpretation of expression structures, and (iv) performance evaluation of a mathematical expression recognition system. Moreover, a groundtruthing format has been proposed to facilitate automatic evaluation of expression recognition techniques. © Springer-Verlag Berlin/Heidelberg 2005.

关键词： Database Groundtruthing Mathematical expressions OCR Performance evaluation statistical learning

来源：评论

学校读者我要写书评

暂无评论

Recent advances in video based document processing: A review

Recent advances in video based document processing: A review

引用

10th IAPR International Workshop on Document Analysis Systems, DAS 2012

作者： Sharma, Nabin Pal, Umapada Blumenstein, Michael Griffith University QLD Australia Computer Vision and Pattern Recognition Unit Indian Statistical Unit Kolkata India

ISBN: (纸本)9780769546612

Extraction and recognition of text present in video has become a very popular research area in the last decade. Generally, text present in video frames is of different size, orientation, style, etc. with complex backgrounds, noise, low resolution and contrast. These factors make the automatic text extraction and recognition in video frames a challenging task. A large number of techniques have been proposed by various researchers in the recent past to address the problem. This paper presents a review of various state-of-the-art techniques proposed towards different stages (e.g. detection, localization, extraction, etc.) of text information processing in video frames. Looking at the growing popularity and the recent developments in the processing of text in video frames, this review imparts details of current trends and potential directions for further research activities to assist researchers. © 2012 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A Wide Learning Approach for Interpretable Feature Recommendation for 1-D Sensor Data in IoT Analytics

引用

International Journal of Automation and computing 2019年第6期16卷 800-811页

作者： Snehasis Banerjee Tanushyam Chattopadhyay Utpal Garain TCS Research&Innovation Tata Consultancy ServicesEcospaceKolkata 700160India Computer Vision&Pattern Recognition Unit Indian Statistical Institute203 B.T.RoadKolkata 700108India

This paper presents a state of the art machine learning-based approach for automation of a varied class of Internet of things(Io T) analytics problems targeted on 1-dimensional(1-D) sensor data. As feature recommendation is a major bottleneck for general Io Tbased applications, this paper shows how this step can be successfully automated based on a Wide Learning architecture without sacrificing the decision-making accuracy, and thereby reducing the development time and the cost of hiring expensive resources for specific problems. Interpretation of meaningful features is another contribution of this research. Several data sets from different real-world applications are considered to realize the proof-of-concept. Results show that the interpretable feature recommendation techniques are quite effective for the problems at hand in terms of performance and drastic reduction in development time.

关键词： Feature engineering sensor data analysis Internet of things(IoT)analytics interpretable learning automation

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：