In this paper, we propose a hybrid language model for handwritten Chinese sentence recognition. This hybrid model is integrated from several independent language models, each of which is trained from a distinct type of corpus and models specifically the linguistic behavior for that type of corpus. By inferring the type of the string which the user has already written, we can make this hybrid language model contribute more precisely to the recognition engine. Our experiments show that the hybrid language model performs consistently well among different types of handwritten articles, and the overall performance is significantly better than a single standard language model. We also propose a candidate re-ranking process after recognition by reducing the language scores to improve the recognition accuracy. The experiment result also demonstrates that this re-ranking process effectively improves the performance of the recognition engine in terms of accuracy.
{"title":"A Hybrid Language Model for Handwritten Chinese Sentence Recognition","authors":"Q. He, Shijie Chen, Mingxi Zhao, Wei Lin","doi":"10.1109/ICFHR.2012.157","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.157","url":null,"abstract":"In this paper, we propose a hybrid language model for handwritten Chinese sentence recognition. This hybrid model is integrated from several independent language models, each of which is trained from a distinct type of corpus and models specifically the linguistic behavior for that type of corpus. By inferring the type of the string which the user has already written, we can make this hybrid language model contribute more precisely to the recognition engine. Our experiments show that the hybrid language model performs consistently well among different types of handwritten articles, and the overall performance is significantly better than a single standard language model. We also propose a candidate re-ranking process after recognition by reducing the language scores to improve the recognition accuracy. The experiment result also demonstrates that this re-ranking process effectively improves the performance of the recognition engine in terms of accuracy.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"208 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121884811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Detecting and recognizing texts in real world images such as sign boards and advertisements is an important part of computer vision applications. The complexity of the problem comes out of many factors such as nonuniform background, different languages and fonts, and non consistent text alignment and orientation. In this paper, we present a novel approach to detect characters and words in real-world images. The presented approach decompose the gray level image into sequence of images, each one includes pixels with gray level values from different disjoint ranges. This decomposition enables extracting connected components representing characters or other non textual objects separated from their neighborhood background. An interpolation of two classes of features translated to histograms is used by a support vector machine to classify and collect the textual objects generating the textual zones. The Shape Context Descriptor [1], is used by the Earth Movers Distance(EMD) method to recognize the characters within the image. The recognized characters are fed to heuristic rule based system to determine words and give final results. To optimize the speed of the system, we follow the embedding of the EMD metric presented in [22] to a normed space to enable fast approximation of the k-Nearest Neighbors using Local Sensitivity Hashing functions(LSH). Experiments show that our algorithm can detect and recognize text regions from the ICDAR 2005 datasets [17] with high rates.
{"title":"Text Detection and Recognition in Real World Images","authors":"Raid Saabni, M. Zwilling","doi":"10.1109/ICFHR.2012.279","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.279","url":null,"abstract":"Detecting and recognizing texts in real world images such as sign boards and advertisements is an important part of computer vision applications. The complexity of the problem comes out of many factors such as nonuniform background, different languages and fonts, and non consistent text alignment and orientation. In this paper, we present a novel approach to detect characters and words in real-world images. The presented approach decompose the gray level image into sequence of images, each one includes pixels with gray level values from different disjoint ranges. This decomposition enables extracting connected components representing characters or other non textual objects separated from their neighborhood background. An interpolation of two classes of features translated to histograms is used by a support vector machine to classify and collect the textual objects generating the textual zones. The Shape Context Descriptor [1], is used by the Earth Movers Distance(EMD) method to recognize the characters within the image. The recognized characters are fed to heuristic rule based system to determine words and give final results. To optimize the speed of the system, we follow the embedding of the EMD metric presented in [22] to a normed space to enable fast approximation of the k-Nearest Neighbors using Local Sensitivity Hashing functions(LSH). Experiments show that our algorithm can detect and recognize text regions from the ICDAR 2005 datasets [17] with high rates.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121998486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a study for modeling handwriting styles that derives from handwriting generation studies, according to which handwriting is a temporal sequence of elementary movements. Hence, handwriting style results from the way those movements are actually performed and sequentially executed to reach fluency. We conjecture that handwriting styles depend on two main factors: the shape of the traces corresponding to the elementary movements and the way these traces are connected. To prove this conjecture, and the handwriting style model we have derived from it, we have designed an experiment in which handwriting samples are described by only two parameters and then clustered. The experimental results show that, despite its simplicity, the proposed method is able to capture the distinctive aspects of handwriting styles behind the handwriting samples, even when the writers deliberately attempts to modify it, and therefore corroborate our conjecture.
{"title":"Modeling Handwriting Style: A Preliminary Investigation","authors":"A. Marcelli, Antonio Parziale, Adolfo Santoro","doi":"10.1109/ICFHR.2012.234","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.234","url":null,"abstract":"We present a study for modeling handwriting styles that derives from handwriting generation studies, according to which handwriting is a temporal sequence of elementary movements. Hence, handwriting style results from the way those movements are actually performed and sequentially executed to reach fluency. We conjecture that handwriting styles depend on two main factors: the shape of the traces corresponding to the elementary movements and the way these traces are connected. To prove this conjecture, and the handwriting style model we have derived from it, we have designed an experiment in which handwriting samples are described by only two parameters and then clustered. The experimental results show that, despite its simplicity, the proposed method is able to capture the distinctive aspects of handwriting styles behind the handwriting samples, even when the writers deliberately attempts to modify it, and therefore corroborate our conjecture.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130477529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents a character recognition based approach to search for a keyword in on-line handwritten Japanese text. It employs an on-line character recognizer or an off-line recognizer, produces recognition candidates and search for a keyword in the lattice of the candidates. This paper also presents a feature matching based approach employing on-line features or off-line features. We compare the above two approaches and conclude that the character recognition based approach yields superior performance compared to the feature-matching-based approach.
{"title":"Comparing Character Recognition Based Approach with Feature Matching Based Approach for Digital Ink Search","authors":"Cheng Cheng, Bilan Zhu, M. Nakagawa","doi":"10.1109/ICFHR.2012.193","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.193","url":null,"abstract":"This paper presents a character recognition based approach to search for a keyword in on-line handwritten Japanese text. It employs an on-line character recognizer or an off-line recognizer, produces recognition candidates and search for a keyword in the lattice of the candidates. This paper also presents a feature matching based approach employing on-line features or off-line features. We compare the above two approaches and conclude that the character recognition based approach yields superior performance compared to the feature-matching-based approach.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126446719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this work we propose descriptors for handwritten digit recognition based on multiresolution features by using the CDF 9/7 Wavelet Transform and Principal Component Analysis, in order to improve the classification performance and obtain a strong reduction on the size of the digit representation. This allows for a higher precision in the recognizers and, at the same time, lower training costs, especially for large datasets. Experiments were carried out with the CENPARMI and MNIST databases, widely used in the literature for this kind of problems, combining classifiers of the Support Vector Machine type. The recognition rates are good, comparable to those reported in previous works.
{"title":"A Wavelet-Based Descriptor for Handwritten Numeral Classification","authors":"L. Seijas, E. Segura","doi":"10.1109/ICFHR.2012.174","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.174","url":null,"abstract":"In this work we propose descriptors for handwritten digit recognition based on multiresolution features by using the CDF 9/7 Wavelet Transform and Principal Component Analysis, in order to improve the classification performance and obtain a strong reduction on the size of the digit representation. This allows for a higher precision in the recognizers and, at the same time, lower training costs, especially for large datasets. Experiments were carried out with the CENPARMI and MNIST databases, widely used in the literature for this kind of problems, combining classifiers of the Support Vector Machine type. The recognition rates are good, comparable to those reported in previous works.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117131147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The training of most of the existing recognition systems requires availability of large datasets labeled at the symbol level. However, producing ground-truth datasets is a tedious work. Two repetitive tasks have to be chained. One is to select a subset of strokes that belong to the same symbol, a next step is to assign a label to this stroke group. In this paper, we discuss a framework to reduce the human workload for labeling at the symbol level a large set of documents based on any graphical language. A hierarchical clustering is used to produce a codebook with one or several strokes per symbol, which is used for a mapping on the raw handwritten data. Evaluation is proposed on two different datasets.
{"title":"Reducing Annotation Workload Using a Codebook Mapping and Its Evaluation in On-Line Handwriting","authors":"Jinpeng Li, H. Mouchère, C. Viard-Gaudin","doi":"10.1109/ICFHR.2012.259","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.259","url":null,"abstract":"The training of most of the existing recognition systems requires availability of large datasets labeled at the symbol level. However, producing ground-truth datasets is a tedious work. Two repetitive tasks have to be chained. One is to select a subset of strokes that belong to the same symbol, a next step is to assign a label to this stroke group. In this paper, we discuss a framework to reduce the human workload for labeling at the symbol level a large set of documents based on any graphical language. A hierarchical clustering is used to produce a codebook with one or several strokes per symbol, which is used for a mapping on the raw handwritten data. Evaluation is proposed on two different datasets.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115674571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. Mouchère, C. Viard-Gaudin, Dae Hwan Kim, J. H. Kim, Utpal Garain
This paper presents an overview of the second Competition on Recognition of Online Handwritten Mathematical Expressions, CROHME 2012. The objective of the contest is to identify current advances in mathematical expression recognition using common evaluation performance measures and datasets. This paper describes the contest details including the evaluation measures used as well as the performance of the 7 submitted systems along with a short description of each system. Progress as compared to the 1st version of CROHME is also documented.
{"title":"ICFHR 2012 Competition on Recognition of On-Line Mathematical Expressions (CROHME 2012)","authors":"H. Mouchère, C. Viard-Gaudin, Dae Hwan Kim, J. H. Kim, Utpal Garain","doi":"10.1109/ICFHR.2012.215","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.215","url":null,"abstract":"This paper presents an overview of the second Competition on Recognition of Online Handwritten Mathematical Expressions, CROHME 2012. The objective of the contest is to identify current advances in mathematical expression recognition using common evaluation performance measures and datasets. This paper describes the contest details including the evaluation measures used as well as the performance of the 7 submitted systems along with a short description of each system. Progress as compared to the 1st version of CROHME is also documented.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130910037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper we propose a novel approach for online mode detection, where the task is to classify ink traces into several categories. In contrast to previous approaches working on global features, we introduce a system completely relying on local features. For classification, standard recurrent neural networks (RNNs) and the recently introduced long short-term memory (LSTM) networks are used. Experiments are performed on the publicly available IAMonDo-database which serves as a benchmark data set for several researches. In the experiments we investigate several RNN structures and classification sub-tasks of different complexities. The final recognition rate on the complete test set is 98.47% in average, which is significantly higher than the 97% achieved with an MCS in previous work. Further interesting results on different subsets are also reported in this paper.
{"title":"Local Feature Based Online Mode Detection with Recurrent Neural Networks","authors":"S. Otte, D. Krechel, M. Liwicki, A. Dengel","doi":"10.1109/ICFHR.2012.229","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.229","url":null,"abstract":"In this paper we propose a novel approach for online mode detection, where the task is to classify ink traces into several categories. In contrast to previous approaches working on global features, we introduce a system completely relying on local features. For classification, standard recurrent neural networks (RNNs) and the recently introduced long short-term memory (LSTM) networks are used. Experiments are performed on the publicly available IAMonDo-database which serves as a benchmark data set for several researches. In the experiments we investigate several RNN structures and classification sub-tasks of different complexities. The final recognition rate on the complete test set is 98.47% in average, which is significantly higher than the 97% achieved with an MCS in previous work. Further interesting results on different subsets are also reported in this paper.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131162426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents a prototype system of Chinese payee name recognition (PNR) based on seal information in the back of Chinese bank checks. First, the seal imprints in the back images of Chinese bank checks are detected and extracted based on the color information. Second, the seal characters representing the payee name are segmented, rotated to horizontal position, and then recognized respectively. Third, the recognized seal characters are considered as the dictionary and payee name recognition is carried out as a verification process. Experiments demonstrate the effectiveness of our proposed method.
{"title":"Chinese Payee Name Recognition Based on Seal Information of Chinese Bank Checks","authors":"Chao Ren, Youbin Chen","doi":"10.1109/ICFHR.2012.191","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.191","url":null,"abstract":"This paper presents a prototype system of Chinese payee name recognition (PNR) based on seal information in the back of Chinese bank checks. First, the seal imprints in the back images of Chinese bank checks are detected and extracted based on the color information. Second, the seal characters representing the payee name are segmented, rotated to horizontal position, and then recognized respectively. Third, the recognized seal characters are considered as the dictionary and payee name recognition is carried out as a verification process. Experiments demonstrate the effectiveness of our proposed method.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125310202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we extend the concept of moment-based normalization of images from digit recognition to the recognition of handwritten text. Image moments provide robust estimates for text characteristics such as size and position of words within an image. For handwriting recognition the normalization procedure is applied to image slices independently. Additionally, a novel moment-based algorithm for line-thickness normalization is presented. The proposed normalization methods are evaluated on the RIMES database of French handwriting and the IAM database of English handwriting. For RIMES we achieve an improvement from 16.7% word error rate to 13.4% and for IAM from 46.6% to 37.3%.
{"title":"Moment-Based Image Normalization for Handwritten Text Recognition","authors":"M. Kozielski, Jens Forster, H. Ney","doi":"10.1109/ICFHR.2012.236","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.236","url":null,"abstract":"In this paper, we extend the concept of moment-based normalization of images from digit recognition to the recognition of handwritten text. Image moments provide robust estimates for text characteristics such as size and position of words within an image. For handwriting recognition the normalization procedure is applied to image slices independently. Additionally, a novel moment-based algorithm for line-thickness normalization is presented. The proposed normalization methods are evaluated on the RIMES database of French handwriting and the IAM database of English handwriting. For RIMES we achieve an improvement from 16.7% word error rate to 13.4% and for IAM from 46.6% to 37.3%.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124634719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：