Multivalued type dissimilarity measure and concept of mutual dissimilarity value for clustering symbolic patterns

A successful attempt in exploring a dissimilarity measure which captures the reality is made in this paper. The proposed measure unlike other measures (Pattern Recognition 24(6) (1991) 567; Pattern Recognition Lett. 16 (1995) 647; Pattern Recognition 28(8) (1995) 1277; IEEE Trans. Syst. Man Cybern. 24(4) (1994)) is multivalued and non-symmetric. The concept of mutual dissimilarity value is introduced to make the existing conventional clustering algorithms work on the proposed unconventional dissimilarity measure.     

More than twenty years of advancements on Frontiers in handwriting recognition

In this paper the results of the research in handwriting/handwritten character recognition in about the last quarter of a century are reported, illustrating the results presented during the International Workshop on Frontiers in Handwriting Recognition (IWFHR) and the International Conference on Frontiers in Handwriting Recognition (ICFHR).     

Semantic speech recognition in the Basque context Part II: language identification for under-resourced languages

This paper describes the development of a Language Identification (LID) system oriented to robust Multilingual Speech Recognition in the Basque context where coexist three languages: Basque, Spanish and French. The LID system is integrated in GorUP, a Semantic Speech Recognition system for industrial complex environments described in Part I. The work presents hybrid strategies for LID, based on the selection of system elements by several classifiers (Support Vector Machines and Multilayer Perceptron) and Discriminant Analysis improved with robust regularized covariance matrix estimation methods oriented to under-resourced languages and stochastic methods for speech recognition tasks (Hidden Markov Models and n-grams). The LID tool manages the main elements of the Automatic Speech Recognition system (Acoustic Phonetic Decoder, Language Model and Lexicons).     

基于依存分析的事件识别

事件抽取是信息抽取的重要组成部分,事件识别是事件抽取的基础,事件识别的效果直接影响了事件抽取的结果.基于机器学习的方法识别事件需要从词汇中发掘更多的特征.针对当前事件识别方法中存在的不足,提出了一种基于依存分析的事件识别方法.用依存分析发掘触发词与其它词之间的句法关系,以此为特征在SVM分类器上对事件进行分类,最终实现事件识别.实验表明,基于依存分析的事件识别优于传统的事件识别方法,而融合多特征的事件识别F值可提高到69.3%.     

基于小波变换和数学形态法的车牌定位方法研究

随着智能交通技术的发展,车牌识别系统已成为其中的一个重要环节,一般来说,车牌识别系统分为车牌定位、字符分割和字符识别三个部分。车牌定位作为字符切分和字符识别的前提,在车牌识别中起着关键的作用。在前人研究的基础上提出了一种基于小波变换域和数学形态法相结合的定位方法。首先利用小波变换后垂直细节图像的水平投影进行行定位,然后再对候选区域进行垂直投影,结合车牌自身的特点去除伪车牌区域,最后结合数学形态学知识实现车牌的精确定位。实验证明,该方法在背景较为复杂或存在干扰的情况下具有很好的效果。     

Further results on the subspace distance

In previous papers [L. Wang, X. Wang, J. Feng, Subspace distance analysis with application to adaptive Bayesian algorithm for face recognition, Pattern Recognition 39(3) (2006) 456-464, L. Wang, X. Wang, J. Feng, Intrapersonal subspace analysis with application to adaptive Bayesian algorithm for face recognition, Pattern Recognition 38(4) (2005) 617-621], we proposed a subspace distance. However, whether the subspace distance satisfies the triangle inequality was left open. In this note, we give positive answer to the open problem and prove our assertion.     

Combining pixel selection with covariance similarity approach in hyperspectral face recognition based on convolution neural network

A Hyperspectral camera provides discriminating features for capturing human faces that cannot be obtained by any other imaging technique. Nevertheless, it has new issues comprising curse of dimensionality, physical parameter retrieval, fast computing and inter band misalignment. As a result of, the literature of Hyperspectral Face Recognition is more scanty and confined to improvised dimensionality reduction and minimization of wide-ranging bands, and thus the objective can be obtained by the use of the Convolution Neural Network (ConvNet). Since ConvNet is of great attention in recent times, it can offer outstanding performance in face recognition systems, where the quantity of training data is amply large. We propose a Hyperspectral Face Recognition system using Firefly algorithm for band fusion and the Convolution Neural Network for classification. In addition to this, the present work is extended 11 exiting face recognition methods to perform Hyperspectral Face Recognition task. Thus the work has been framed as Hyperspectral Face Recognition problem to an image-set classification problem and assessment of the performance has been done on six state-of-the-art image-set problem techniques, and similarly it was examined on five state-of-the-art RGB and gray scale face recognition system, subsequently applied improved Firefly band selection algorithm on Hyperspectral Images to get appropriate band. Assessment with the eleven extended and five existing HSI Face Recognition system on two benchmark datasets (CMU-HSFD & UWA-HSFD) demonstrates that the proposed system overtakes all by a noteworthy margin. Lastly, we execute the band selection demonstration to get the novelty for most informative bands in Visible Near Infrared (VNIR).     

Tampering with a watermarking-based image authentication scheme

We analyse a recent image authentication scheme designed by Chang et al. [A watermarking-based image ownership and tampering authentication scheme, Pattern Recognition Lett. 27 (5) (2006) 439-446] whose first step is based on a watermarking scheme of Maniccam and Bourbakis [Lossless compression and information hiding in images, Pattern Recognition 37 (3) (2004) 475-486]. We show how the Chang et al. scheme still allows pixels to be tampered, and furthermore discuss why its ownership cannot be uniquely binding. Our results indicate that the scheme does not achieve its designed objectives of tamper detection and image ownership.     

多文种环境下汉字内码识别算法的研究

汉字内码向ISO/IEC 10646过渡是实现计算机用文字编码统一的必然趋势,但目前在一段时间内仍将存在多种汉字内码并存的情况,所以实现汉字内码的自动识别是保证汉字多内码并存的关键。本文主要探讨了如何在多内码并存的多文种环境中实现汉字内码自动识别的问题,并提供了多种汉字内码识别算法,包括基于内码分布、标点符号特征、字频特征和语义特征的识别算法等。在此基础上,本文对不同的识别算法进行分析和评估。在对目标样本的测试中,以上算法的识别率最高可以达到99.9%以上。     

基于语义角色标注的新闻领域复述句识别方法

复述(Paraphrase)句的识别可看作文本蕴含(Text Entailment)识别的一个子问题,传统的解决方法是通过词频或句法上的相似度来判断。即使用相同的文字书写的句子其含义也可能差别很大,而相同句法结构也不能保证意义一致。该文根据新闻语料的特点,提出了一种通过引入深层的语义角色标注来帮助识别新闻领域复述句的方法。该方法通过在语义角色这种结构化的含义表达形式中提取的特征来弥补传统方法的不足 先识别待判断的两个句子中所有谓词的语义角色,然后计算两个句子间对应语义角色的相似度,最后结合传统的句子相似度计算方法来进行相似性计算。实验证明,该文提出的方法能有效地提高复述语句的识别效果。     

Automatic speech recognition performance in different room acoustic environments with and without dereverberation preprocessing

The performance of recent dereverberation methods for reverberant speech preprocessing prior to Automatic Speech Recognition (ASR) is compared for an extensive range of room and source-receiver configurations. It is shown that room acoustic parameters such as the clarity (C50) and the definition (D50) correlate well with the ASR results. When available, such room acoustic parameters can provide insight into reverberant speech ASR performance and potential improvement via dereverberation preprocessing. It is also shown that the application of a recent dereverberation method based on perceptual modelling can be used in the above context and achieve significant Phone Recognition (PR) improvement, especially under highly reverberant conditions.     

一种改进的PRSVM语种识别方法

传统的PRSVM方法存在以下问题:音素识别器的符号化结果与原语音存在不一致;向量空间维数高,稀疏.针对以上问题,先改用更适合噪声环境下连续电话语音的音素识别器,并采用词图结构改善解码效果,再分别用全局和局部两种隐含语义分析策略改进区分性训练问题.实验表明,本方法不但有效,而且大大减少了运算量.在NIST2007语种识别评测30秒、10秒和3秒任务中,本方法比基线系统性能有显著提高,等错误率分别相对降低了22.3%、14.7%和12.2%.     

Deep learning for graphics recognition: document understanding and beyond

International Journal on Document Analysis and Recognition (IJDAR) -     

A thresholding method based on two-dimensional Renyi's entropy

In this paper, we present a new thresholding technique based on two-dimensional Renyi's entropy. The two-dimensional Renyi's entropy was obtained from the two-dimensional histogram which was determined by using the gray value of the pixels and the local average gray value of the pixels. This new method extends a method due to Sahoo et al. (Pattern Recognition 30 (1997) 71) and includes a previously proposed global thresholding method due to Abutaleb (Pattern Recognition 47 (1989) 22). Further, our method extends a global thresholding method due to Chang et al. (IEEE Trans. Image Process. 4 (1995) 370) to the two-dimensional setting. The effectiveness of the proposed method is demonstrated by using examples from the real-world and synthetic images.     

Editorial for special issue on “Advanced Topics in Document Analysis and Recognition”

International Journal on Document Analysis and Recognition (IJDAR) -     

Text recognition for Vietnamese identity card based on deep features network

International Journal on Document Analysis and Recognition (IJDAR) - Optical character recognition (OCR) is a technology for converting text automatically on images into data strings for editing,...     

Correction to: Radical-based extract and recognition networks for Oracle character recognition

International Journal on Document Analysis and Recognition (IJDAR) -     

Retraction Note: Offline scripting-free author identification based on speeded-up robust features

International Journal on Document Analysis and Recognition (IJDAR) -