User appreciation of a word-image retrieval system is based on the quality of a hit list for a query. Using support vector machines for ranking in large scale, handwritten document collections, we observed that many hit lists suffered from bad instances in the top ranks. An analysis of this problem revealed that two functions needed to be optimised concerning both separability and prototypicality. By ranking images in two stages, the number of distracting images is reduced, making the method very convenient for massive scale, continuously trainable retrieval engines. Instead of cumbersome SVM training, we present a nearest-centroid method and show that precision improvements of up to 35 percentage points can be achieved, yielding up to 100% precision in data sets with a large amount of instances, while maintaining high recall performances.
{"title":"Separability versus Prototypicality in Handwritten Word Retrieval","authors":"J. V. Oosten, Lambert Schomaker","doi":"10.1109/ICFHR.2012.269","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.269","url":null,"abstract":"User appreciation of a word-image retrieval system is based on the quality of a hit list for a query. Using support vector machines for ranking in large scale, handwritten document collections, we observed that many hit lists suffered from bad instances in the top ranks. An analysis of this problem revealed that two functions needed to be optimised concerning both separability and prototypicality. By ranking images in two stages, the number of distracting images is reduced, making the method very convenient for massive scale, continuously trainable retrieval engines. Instead of cumbersome SVM training, we present a nearest-centroid method and show that precision improvements of up to 35 percentage points can be achieved, yielding up to 100% precision in data sets with a large amount of instances, while maintaining high recall performances.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"88 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":"126307727","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}
Although writer-independent offline signature verification (WI-SV) systems may provide a high level of accuracy, they are not secure due to the need to store user templates for authentication. Moreover, state-of-the-art writer-dependent (WD) and writer-independent (WI) systems provide enhanced accuracy through information fusion at either feature, score or decision levels, but they increase computational complexity. In this paper, a method for adapting WI-SV systems to different users is proposed, leading to secure and compact WD-SV systems. Feature representations embedded within WI classifiers are extracted and tuned to each enrolled user while building a user-specific classifier. Simulation results on the Brazilian signature database indicate that the proposed method yields WD classifiers that provide the same level of accuracy as that of the baseline WI classifiers (AER of about 5.38), while reducing complexity by about 99.5%.
{"title":"Adaptation of Writer-Independent Systems for Offline Signature Verification","authors":"George S. Eskander, R. Sabourin, Eric Granger","doi":"10.1109/ICFHR.2012.175","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.175","url":null,"abstract":"Although writer-independent offline signature verification (WI-SV) systems may provide a high level of accuracy, they are not secure due to the need to store user templates for authentication. Moreover, state-of-the-art writer-dependent (WD) and writer-independent (WI) systems provide enhanced accuracy through information fusion at either feature, score or decision levels, but they increase computational complexity. In this paper, a method for adapting WI-SV systems to different users is proposed, leading to secure and compact WD-SV systems. Feature representations embedded within WI classifiers are extracted and tuned to each enrolled user while building a user-specific classifier. Simulation results on the Brazilian signature database indicate that the proposed method yields WD classifiers that provide the same level of accuracy as that of the baseline WI classifiers (AER of about 5.38), while reducing complexity by about 99.5%.","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":"126338630","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 order to segment and recognize on-line handwritten flowchart symbols precisely, we propose a method that segments the graphic symbols based on the loop structure and recognize the segmented symbols by using SVMs. In our experiments, low error rate of 3.37% for symbol segmentation and high recognition rate of 97.6% were obtained. We also propose a beautification and editing method for recognized symbols, and implement them to construct a prototype system. We compare an input time for drawing flowcharts between our system and a traditional application using icon-based interface. As a result, the input time on our system was faster than that on traditional one for flowcharts without texts.
{"title":"On-Line Handwritten flowchart Recognition, Beautification and Editing System","authors":"H. Miyao, Rei Maruyama","doi":"10.1109/ICFHR.2012.250","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.250","url":null,"abstract":"In order to segment and recognize on-line handwritten flowchart symbols precisely, we propose a method that segments the graphic symbols based on the loop structure and recognize the segmented symbols by using SVMs. In our experiments, low error rate of 3.37% for symbol segmentation and high recognition rate of 97.6% were obtained. We also propose a beautification and editing method for recognized symbols, and implement them to construct a prototype system. We compare an input time for drawing flowcharts between our system and a traditional application using icon-based interface. As a result, the input time on our system was faster than that on traditional one for flowcharts without texts.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"89 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":"124681310","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 aim of this paper is to introduce a novel technique for handwritten digit recognition based on genetic clustering. Cluster design is proposed as a two-step process. The first step is focused on generating cluster solutions, while the second one involves the construction of the best cluster solution starting from a set of suitable candidates. An approach for achieving these goals is presented. Clustering is considered as an optimization problem in which the objective function to be minimized is the cost function associated to the classification. A genetic algorithm is used to determine the best cluster centers to reduce classification time, without greatly affecting the accuracy. The classification task is performed by k-nearest neighbor classifier. It has also been developed a new feature and a distance measure based on the Sokal-Michener dissimilarity measure to describe and compare handwritten numerals. This technique has been evaluated through experimental testing on MNIST dataset and its effectiveness has been proved.
{"title":"A Novel Technique for Handwritten Digit Classification Using Genetic Clustering","authors":"S. Impedovo, Francesco Maurizio Mangini","doi":"10.1109/ICFHR.2012.167","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.167","url":null,"abstract":"The aim of this paper is to introduce a novel technique for handwritten digit recognition based on genetic clustering. Cluster design is proposed as a two-step process. The first step is focused on generating cluster solutions, while the second one involves the construction of the best cluster solution starting from a set of suitable candidates. An approach for achieving these goals is presented. Clustering is considered as an optimization problem in which the objective function to be minimized is the cost function associated to the classification. A genetic algorithm is used to determine the best cluster centers to reduce classification time, without greatly affecting the accuracy. The classification task is performed by k-nearest neighbor classifier. It has also been developed a new feature and a distance measure based on the Sokal-Michener dissimilarity measure to describe and compare handwritten numerals. This technique has been evaluated through experimental testing on MNIST dataset and its effectiveness has been proved.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"28 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":"133091675","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. Boubaker, A. Chaabouni, Najiba Tagougui, M. Kherallah, A. Alimi, H. E. Abed
This paper deals with the improvement of an on-line Arabic handwriting modeling system based on graphemes segmentation. The presented strategy consists in the integration of off-line features to assimilate and take up the handwriting style variation in a multi-writer context. The main contribution of the presented work consists in making off-line fuzzy template for each on-line segmented graphemes trajectory and the extraction of geometric moments invariants by using a method adapted to the irregular spatial sampling of their on-line trajectory. The experimental results prove the added value of the introduced features on the discriminative power of the developed handwriting modeling system.
{"title":"Off-Line Features Integration for On-Line Handwriting Graphemes Modeling Improvement","authors":"H. Boubaker, A. Chaabouni, Najiba Tagougui, M. Kherallah, A. Alimi, H. E. Abed","doi":"10.1109/ICFHR.2012.244","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.244","url":null,"abstract":"This paper deals with the improvement of an on-line Arabic handwriting modeling system based on graphemes segmentation. The presented strategy consists in the integration of off-line features to assimilate and take up the handwriting style variation in a multi-writer context. The main contribution of the presented work consists in making off-line fuzzy template for each on-line segmented graphemes trajectory and the extraction of geometric moments invariants by using a method adapted to the irregular spatial sampling of their on-line trajectory. The experimental results prove the added value of the introduced features on the discriminative power of the developed handwriting modeling system.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"45 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":"114073749","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}
S. Mahmoud, Irfan Ahmad, M. Alshayeb, W. Al-Khatib, M. T. Parvez, G. Fink, V. Märgner, H. E. Abed
In this paper, we report our comprehensive Arabic offline Handwritten Text database (KHATT) after completion of the collection of 1000 handwritten forms written by 1000 writers from different countries. It is composed of an image database containing images of the written text at 200, 300, and 600 dpi resolutions, a manually verified ground truth database that contains meta-data describing the written text at the page, paragraph, and line levels. A formal verification procedure is implemented to align the handwritten text with its ground truth at the form, paragraph and line levels. Tools to extract paragraphs from pages and segment paragraphs into lines are developed. Preliminary experiments on Arabic handwritten text recognition are conducted using sample data from the database and the results are reported. The database will be made freely available to researchers world-wide for research in various handwritten-related problems such as text recognition, writer identification and verification, etc.
{"title":"KHATT: Arabic Offline Handwritten Text Database","authors":"S. Mahmoud, Irfan Ahmad, M. Alshayeb, W. Al-Khatib, M. T. Parvez, G. Fink, V. Märgner, H. E. Abed","doi":"10.1109/ICFHR.2012.224","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.224","url":null,"abstract":"In this paper, we report our comprehensive Arabic offline Handwritten Text database (KHATT) after completion of the collection of 1000 handwritten forms written by 1000 writers from different countries. It is composed of an image database containing images of the written text at 200, 300, and 600 dpi resolutions, a manually verified ground truth database that contains meta-data describing the written text at the page, paragraph, and line levels. A formal verification procedure is implemented to align the handwritten text with its ground truth at the form, paragraph and line levels. Tools to extract paragraphs from pages and segment paragraphs into lines are developed. Preliminary experiments on Arabic handwritten text recognition are conducted using sample data from the database and the results are reported. The database will be made freely available to researchers world-wide for research in various handwritten-related problems such as text recognition, writer identification and verification, etc.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"97 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":"114695097","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 propose in this work a new handwritten digit recognition system based on parallel combination of SVM classifiers for managing conflict provided between their outputs. Firstly, we evaluate different methods of generating features to train the SVM classifiers that operate independently of each other. To improve the performance of the system, the outputs of SVM classifiers are combined through the Dezert-Smarandache theory. The proposed framework allows combining the calibrated SVM outputs issued from a sigmoid transformation and uses an estimation technique based on a supervised model to compute the belief assignments. Decision making is performed by maximizing the new Dezert-Smarandache probability. The performance evaluation of the proposed system is conducted on the well known US Postal Service database. Experimental results show that the proposed combination framework improves the recognition rate even when individual SVM classifiers provide conflicting outputs.
{"title":"Handwritten Digit Recognition Based on a DSmT-SVM Parallel Combination","authors":"Nassim Abbas, Y. Chibani, H. Nemmour","doi":"10.1109/ICFHR.2012.208","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.208","url":null,"abstract":"We propose in this work a new handwritten digit recognition system based on parallel combination of SVM classifiers for managing conflict provided between their outputs. Firstly, we evaluate different methods of generating features to train the SVM classifiers that operate independently of each other. To improve the performance of the system, the outputs of SVM classifiers are combined through the Dezert-Smarandache theory. The proposed framework allows combining the calibrated SVM outputs issued from a sigmoid transformation and uses an estimation technique based on a supervised model to compute the belief assignments. Decision making is performed by maximizing the new Dezert-Smarandache probability. The performance evaluation of the proposed system is conducted on the well known US Postal Service database. Experimental results show that the proposed combination framework improves the recognition rate even when individual SVM classifiers provide conflicting outputs.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"22 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":"133163095","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}
Handwritten text found in historical documents is often difficult to read due to issues such as contrast, noise and degradation. There has been much work on how to process such documents including improvements on binarization of these images. Despite the different advances in this area, improving the quality and readability of these documents is still an open research area. In this paper a novel approach is proposed to improve the text of historical documents through interactive stroke enhancement. This approach utilizes user interaction to indicate parts in the image where stroke enhancement is needed. The algorithm uses a difference of multi-resolution Gaussians to detect text at different scales and to modulate the amount of enhancement needed. This approach could be used for manually restoring text images or for improving readability of the text. Results are given in this paper that show the effectiveness of the proposed method.
{"title":"Interactive Enhancement of Handwritten Text through Multi-resolution Gaussian","authors":"Oliver A. Nina","doi":"10.1109/ICFHR.2012.222","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.222","url":null,"abstract":"Handwritten text found in historical documents is often difficult to read due to issues such as contrast, noise and degradation. There has been much work on how to process such documents including improvements on binarization of these images. Despite the different advances in this area, improving the quality and readability of these documents is still an open research area. In this paper a novel approach is proposed to improve the text of historical documents through interactive stroke enhancement. This approach utilizes user interaction to indicate parts in the image where stroke enhancement is needed. The algorithm uses a difference of multi-resolution Gaussians to detect text at different scales and to modulate the amount of enhancement needed. This approach could be used for manually restoring text images or for improving readability of the text. Results are given in this paper that show the effectiveness of the proposed method.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"39 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":"133268597","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 method for the extraction of signatures from document images. Instead of using a human defined set of features a part-based feature extraction method is used. In particular, we use the Speeded Up Robust Features (SURF) to distinguish the machine printed text from signatures. Using SURF features makes the approach generally more useful and reliable for different resolution documents. We have evaluated our system on the publicly available Tobacco-800 dataset in order to compare it to previous work. Finally, all signatures were found in the images and less than half of the found signatures are false positives. Therefore, our system can be applied for practical use.
{"title":"Signature Segmentation from Document Images","authors":"Sheraz Ahmed, M. I. Malik, M. Liwicki, A. Dengel","doi":"10.1109/ICFHR.2012.271","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.271","url":null,"abstract":"In this paper we propose a novel method for the extraction of signatures from document images. Instead of using a human defined set of features a part-based feature extraction method is used. In particular, we use the Speeded Up Robust Features (SURF) to distinguish the machine printed text from signatures. Using SURF features makes the approach generally more useful and reliable for different resolution documents. We have evaluated our system on the publicly available Tobacco-800 dataset in order to compare it to previous work. Finally, all signatures were found in the images and less than half of the found signatures are false positives. Therefore, our system can be applied for practical use.","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":"116598186","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}
J. Rajkumar, K. Mariraja, Kanakapriya Kanakapriya, S. Nishanthini, V. Chakravarthy
We present two schemas for online recognition of Telugu characters, involving elaborate multi-classifier architectures. Considering the three-tier vertical organization of a typical Telugu character, we divide the stroke set into 4 subclasses primarily based on their vertical position. Stroke level recognition is based on a bank of Support Vector Machines (SVMs), with a separate SVM trained on each of these classes. Character recognition for Schema 1 is based on a Ternary Search Tree (TST), while for Schema 2 it is based on a SVM. The two schemas yielded overall stroke recognition performances of 89.59% and 96.69% respectively surpassing some of the recent online recognition performance results related to Telugu script reported in literature. The schemas yield character-level recognition performances of 90.55% and 96.42% respectively.
{"title":"Two Schemas for Online Character Recognition of Telugu Script Based on Support Vector Machines","authors":"J. Rajkumar, K. Mariraja, Kanakapriya Kanakapriya, S. Nishanthini, V. Chakravarthy","doi":"10.1109/ICFHR.2012.286","DOIUrl":"https://doi.org/10.1109/ICFHR.2012.286","url":null,"abstract":"We present two schemas for online recognition of Telugu characters, involving elaborate multi-classifier architectures. Considering the three-tier vertical organization of a typical Telugu character, we divide the stroke set into 4 subclasses primarily based on their vertical position. Stroke level recognition is based on a bank of Support Vector Machines (SVMs), with a separate SVM trained on each of these classes. Character recognition for Schema 1 is based on a Ternary Search Tree (TST), while for Schema 2 it is based on a SVM. The two schemas yielded overall stroke recognition performances of 89.59% and 96.69% respectively surpassing some of the recent online recognition performance results related to Telugu script reported in literature. The schemas yield character-level recognition performances of 90.55% and 96.42% respectively.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"104 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":"116656760","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：