Segmentation of connected handwritten numeral strings

A new approach to separating single touching handwritten digit strings is presented. The image of the connected numerals is normalized, preprocessed and then thinned before feature points are detected. Potential segmentation points are determined based on decision line that is estimated from the deepest/highest valley/hill in the image. The partitioning path is determined precisely and then the numerals are separated before restoration is applied. Experimental results on the NIST Database 19, CEDAR CD-ROM and our own collection of images show that our algorithm can get a successful recognition rate of 96%, which compares favorably with those reported in the literature.     

基于识别的手写数字串分割

手写数字串的分割与字符识别密切相关.采用基于识别的分割方法,在分割过程中引入识别机制识别分割碎片,将识别结果经过差值运算后置为每个识别对象的识别可信度,利用动态规划找到最佳分割路径.在训练分类器时,使用反例样本估计分类器参数,得到了性能良好的分类器.实验数据表明,利用正例和反例样本结合训练的分类器比只经过正例样本训练的分类器的识别率要高很多.     

一种图象前背景分离的方法及实现

本文提出一种有效的图像的前背景分离算法及其实现。本文的基本思想是利用Meanshift算法对图象进行预分割,然后利用图论的观点对图象进行分割,最后利用matting算法对处理结果的局部进行优化,得到最终结果。实验结果表明,这种方法在仅需要少量用户输入情况之下,能够得到较好的分割效果。     

A handwritten numeral character classification using tolerant roughset

Proposes a data classification method based on the tolerant rough set that extends the existing equivalent rough set. A similarity measure between two data is described by a distance function of all constituent attributes and they are defined to be tolerant when their similarity measure exceeds a similarity threshold value. The determination of optimal similarity threshold value is very important for accurate classification. So, we determine it optimally by using the genetic algorithm (GA), where the goal of evolution is to balance two requirements such that: 1) some tolerant objects are required to be included in the same class as many as possible; and 2) some objects in the same class are required to be tolerant as much as possible. After finding the optimal similarity threshold value, a tolerant set of each object is obtained and the data set is grouped into the lower and upper approximation set depending on the coincidence of their classes. We propose a two-stage classification method such that all data are classified by using the lower approximation at the first stage and then the nonclassified data at the first stage are classified again by using the rough membership functions obtained from the upper approximation set. We apply the proposed classification method to the handwritten numeral character classification problem and compare its classification performance and learning time with those of the feedforward neural network's backpropagation algorithm     

The recognition of handwritten numeral strings using a two-stage HMM-based method

In this paper, a two-stage HMM-based recognition method allows us to compensate for the possible loss in terms of recognition performance caused by the necessary trade-off between segmentation and recognition in an implicit segmentation-based strategy. The first stage consists of an implicit segmentation process that takes into account some contextual information to provide multiple segmentation-recognition hypotheses for a given preprocessed string. These hypotheses are verified and re-ranked in a second stage by using an isolated digit classifier. This method enables the use of two sets of features and numeral models: one taking into account both the segmentation and recognition aspects in an implicit segmentation-based strategy, and the other considering just the recognition aspects of isolated digits. These two stages have been shown to be complementary, in the sense that the verification stage compensates for the loss in terms of recognition performance brought about by the necessary tradeoff between segmentation and recognition carried out in the first stage. The experiments on 12,802 handwritten numeral strings of different lengths have shown that the use of a two-stage recognition strategy is a promising idea. The verification stage brought about an average improvement of 9.9% on the string recognition rates. On touching digit pairs, the method achieved a recognition rate of 89.6%. Received June 28, 2002 / Revised July 03, 2002     

Segmentation of connected handwritten digits using Self-Organizing Maps

Segmentation is an important issue in document image processing systems as it can break a sequence of characters into its components. Its application over digits is common in bank checks, mail and historical document processing, among others. This paper presents an algorithm for segmentation of connected handwritten digits based on the selection of feature points, through a skeletonization process, and the clustering of the touching region via Self-Organizing Maps. The segmentation points are then found, leading to the final segmentation. The method can deal with several types of connection between the digits, having also the ability to map multiple touching. The proposed algorithm achieved encouraging results, both relating to other state-of-the-art algorithms and to possible improvements.     

A genetic framework using contextual knowledge for segmentation and recognition of handwritten numeral strings

For the first time, a genetic framework using contextual knowledge is proposed for segmentation and recognition of unconstrained handwritten numeral strings. New algorithms have been developed to locate feature points on the string image, and to generate possible segmentation hypotheses. A genetic representation scheme is utilized to show the space of all segmentation hypotheses (chromosomes). For the evaluation of segmentation hypotheses, a novel evaluation scheme is introduced, in order to improve the outlier resistance of the system. Our genetic algorithm tries to search and evolve the population of segmentation hypotheses, and to find the one with the highest segmentation/recognition confidence. The NIST NSTRING SD19 and CENPARMI databases were used to evaluate the performance of our proposed method. Our experiments showed that proper use of contextual knowledge in segmentation, evaluation and search greatly improves the overall performance of the system. On average, our system was able to obtain correct recognition rates of 95.28% and 96.42% on handwritten numeral strings using neural network and support vector classifiers, respectively. These results compare favorably with the ones reported in the literature.     

Integration of structural and statistical information forunconstrained handwritten numeral recognition

In this paper, we propose an approach that integrates the statistical and structural information for unconstrained handwritten numeral recognition. This approach uses state-duration adapted transition probability to improve the modeling of state-duration in conventional HMMs and uses macro-states to overcome the difficulty in modeling pattern structures by HMMs. The proposed method is superior to conventional approaches in many aspects. In the statistical and structural models, the orientations are encoded into discrete codebooks and the distributions of locations are modeled by joint Gaussian distribution functions. The experimental results show that the proposed approach can achieve high performance in terms of speed and accuracy     

结合Fisher判别的手写数字特征提取方法

在手写数字图像的特征提取中,提出一种结合Fisher线性判别的多分辨率Gabor滤波方法,在所有特征点上寻求特定滤波方向上的局部最优滤波频率,以获得最佳滤波效果,同时压缩不相关特征.在MNIST手写数字图像库上的识别实验表明:在小样本情况下,该方法能更准确地抽取手写数字图像特征,识别效果明显优于直接进行Gabor特征提取.     

基于统计和结构特征的手写数字识别研究

针对目前手写数字识别精度不高的问题,通过对手写数字图像的研究,提出了基于手写数字图像的空间、旋转、层次和结构特性的特征提取方法.该方法把手写数字的统计和结构特征结合起来,以特征提取方法为基础,利用LibSVM算法对手写数字特征进行了训练和识别.通过实验给出了各个参数的推荐值,利用推荐参数值,手写数字MNIST字体库的识别率高达99.3333％.实验结果表明了该算法在识别手写数字上的有效性和准确性.     

Text line extraction in graphical documents using background and foreground information

In graphical documents (e.g., maps, engineering drawings), artistic documents etc., the text lines are annotated in multiple orientations or curvilinear way to illustrate different locations or symbols. For the optical character recognition of such documents, individual text lines from the documents need to be extracted. In this paper, we propose a novel method to segment such text lines and the method is based on the foreground and background information of the text components. To effectively utilize the background information, a water reservoir concept is used here. In the proposed scheme, at first, individual components are detected and grouped into character clusters in a hierarchical way using size and positional information. Next, the clusters are extended in two extreme sides to determine potential candidate regions. Finally, with the help of these candidate regions, individual lines are extracted. The experimental results are presented on different datasets of graphical documents, camera-based warped documents, noisy images containing seals, etc. The results demonstrate that our approach is robust and invariant to size and orientation of the text lines present in the document.     

A hybrid multiple classifier system of unconstrained handwritten numeral recognition

o raise the reliability, a hybrid multiple classifier system is proposed by integrating the cooperation and combination of three classifiers: SVM [1], MQDF [3], and leNet5 [2]. In combination, we apply the total probability theorem to the classifiers at the rank level. Meanwhile, differential measurement and probability measurement are defined for the rejection option on different types of classifiers. Considerable improvement has been observed, and the final recognition rate of this system ranges from 95.54 to 99.11% with a reliability of 99.54 to 99.11%. The text was submitted by the authors in English. Chun Lei He received an MS and BS degree in applied mathematics from Jilin University, China, in 2000 and 1998, respectively. Currently, she is a research assistant and graduate student at the Center for Pattern Recognition and Machine Intelligence (CENPARMI) at Concordia University, Canada. Her research interest is handwriting recognition using expert systems techniques. Ching Y. Suen received an MS degree in engineering from the University of Hong Kong and a PhD degree from the University of British Columbia, Canada. In 1972, he joined the Department of Computer Science of Concordia University, where he became a professor in 1979 and served as chairman from 1980 to 1984 and as associate dean for research of the Faculty of Engineering and Computer Science from 1993 to 1997. He has guided/hosted 65 visiting scientists and professors and supervised 60 doctoral and master’s graduates. Currently he holds the distinguished Concordia Research Chair in Artificial Intelligence and Pattern Recognition, and is the director of CENPARMI, the center for PR and MI. Prof. Suen is the author/editor of 11 books and more than 400 papers on subjects ranging from computer vision and handwriting recognition to expert systems and computational linguistics. A Google search of “Ching Y. Suen” will show some of his publications. He is the founder of The International Journal of Computer Processing of Oriental Languages and served as its first editor-in-chief for 10 years. Presently he is an associate editor of several journals related to pattern recognition. A fellow of the IEEE, IAPR, and the Academy of Sciences of the Royal Society of Canada, he has served several professional societies as president, vice-president, or governor. He is also the founder and chair of several conference series including ICDAR, IWFHR, and VI. He had been the general chair of numerous international conferences, including the International Conference on Computer Processing of Chinese and Oriental Languages in August 1988 held in Toronto, International Conference on Document Analysis and Recognition held in Montreal in August 1995, and the International Conference on Pattern Recognition held in Quebec City in August 2002. Dr. Suen has given 150 seminars at major computer industries and various government and academic institutions around the world. He has been the principal investigator of 25 industrial/government research contracts and is a grant holder and recipient of prestigious awards, including an ITAC/NSERC cash + grant award from the Information Technology Association of Canada and the Natural Sciences and Engineering Research Council of Canada in 1992 and the Concordia “Research Fellow” award in 1998.     

Rotation, scale and translation invariant handwritten Devanagari numeral character recognition using general fuzzy neural network

In this paper a general fuzzy hyperline segment neural network is proposed [P.M. Patil, Pattern classification and clustering using fuzzy neural networks, Ph.D. Thesis, SRTMU, Nanded, India, January 2003]. It combines supervised and unsupervised learning in a single algorithm so that it can be used for pure classification, pure clustering and hybrid classification/clustering. The method is applied to handwritten Devanagari numeral character recognition and also to the Fisher Iris database. High recognition rates are achieved with less training and recall time per pattern. The algorithm is rotation, scale and translation invariant. The recognition rate with ring data features is found to be 99.5%.     

Dynamic texture as foreground and background

Depending on application, temporal texture can be viewed as either foreground or background. We address two related problems: finding regions of dynamic texture in a video and detecting moving targets in a dynamic texture. We propose efficient and fast methods for both cases. The methods can be potentially used in real-time applications of machine vision. First, we show how the optical flow residual can be used to find dynamic texture in video. The algorithm is a practical, real-time simplification of the sophisticated and powerful but time-consuming method (Fazekas et?al. in Int J Comput Vis 82:48?C63, 2009). We give numerous examples of detecting and segmenting fire, smoke, water and other dynamic textures in real-world videos acquired by static and moving cameras. Then we apply the singular value decomposition (SVD) to a temporal data window in a video to detect targets in dynamic texture via the residual of the largest singular value. For a dynamic background of low-temporal periodicity, such as water, no temporal periodicity analysis is needed. For a highly periodic background such as an escalator, we show that periodicity analysis can improve detection results. Applying the method proposed in Chetverikov and Fazekas (Proceedings of British machine vision conference, vol 1, pp 167?C176, 2006), we find the temporal period and use the resonant SVD to detect moving targets against a time-periodic background.     

A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters

The recognition of Indian and Arabic handwriting is drawing increasing attention in recent years. To test the promise of existing handwritten numeral recognition methods and provide new benchmarks for future research, this paper presents some results of handwritten Bangla and Farsi numeral recognition on binary and gray-scale images. For recognition on gray-scale images, we propose a process with proper image pre-processing and feature extraction. In experiments on three databases, ISI Bangla numerals, CENPARMI Farsi numerals, and IFHCDB Farsi numerals, we have achieved very high accuracies using various recognition methods. The highest test accuracies on the three databases are 99.40%, 99.16%, and 99.73%, respectively. We justified the benefit of recognition on gray-scale images against binary images, compared some implementation choices of gradient direction feature extraction, some advanced normalization and classification methods.     

结合背景和前景先验的显著性检测

目的 显著性检测已成为图像处理过程中的一个重要步骤,已被应用到许多计算机视觉任务中。虽然显著性检测已被研究多年并取得了较大的进展,但仍存在一些不足,例如在复杂场景中的检测不准确或检测结果夹带着背景噪声等。因此,针对已有图像显著性检测方法存在的不能有效抑制背景区域,或不能清晰突显出完整的目标区域的缺点,提出一种结合背景先验和前景先验信息的图像显著性检测算法。方法 首先选取图像的边界超像素作为背景区域,从而根据每个区域与背景区域的差异度来建立背景先验显著图;然后通过计算特征点来构建一个能够粗略包围目标区域的凸包,并结合背景先验显著图来选取前景目标区域,从而根据每个区域与前景目标区域的相似度来生成前景先验显著图;最后融合这两个显著图并对其结果进一步优化得到更加平滑和准确的显著图。结果 利用本文算法对MSRA10K数据库内图像进行显著性检测,并与主流的算法进行对比。本文算法的检测效果更接近人工标注,而且精确率和效率都优于所对比的算法,其中平均精确率为87.9%,平均召回率为79.17%,F值为0.852 6,平均绝对误差（MAE）值为0.113,以及平均运行时间为0.723 s。结论 本文提出了一种结合两类先验信息的显著性检测算法,检测结果既能够有效地抑制背景区域,又能清晰地突显目标区域,从而提高了检测的准确性。     

基于结构聚类和笔画分析的粘连手写汉字切分

粘连手写汉字的切分是手写汉字切分中亟待解决的问题之一。因此,针对粘连手写汉字提出一种新的切分算法。该算法首先通过寻找分界线的方法来提取粘连笔段,分界线的位置是通过粘连汉字骨架图像的聚类和笔段端点类属可信度的信息来确定的。然后提取粘连笔段并对其进行分析和类型（直线或曲线）判定,从而确定切分点及切分方向。最后利用背景细化算法找到分割曲线。该算法不仅能够很好地适用于两个粘连汉字宽窄不一、含有多个粘连点等粘连情况,而且具有良好的抗噪声效果。