Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122188
El M'Hadi Hajar, Cherkaoui Abdelghani
More than half world population lives in cities. In Morocco, the urbanization has more than doubled during the last fifty years to reach 59.2 % today. More than ever, this sociodemographic situation conditions the challenges which the country has to raise to assure an optimal quality of life for the Moroccan citizens. The idea of smart-cities is examined with respect to the intent, including current urbanization models, development issues and city planning in Morocco; the case of the proposed smart-city of Casablanca, a flagship of proposals and current realities is looked at. An indigenous alternative following the model proposed of smart-villages instead is examined for appropriateness.
{"title":"Exploring the emergence of a new smart city model: Case analysis of the Moroccan urbanization","authors":"El M'Hadi Hajar, Cherkaoui Abdelghani","doi":"10.1109/ICISIM.2017.8122188","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122188","url":null,"abstract":"More than half world population lives in cities. In Morocco, the urbanization has more than doubled during the last fifty years to reach 59.2 % today. More than ever, this sociodemographic situation conditions the challenges which the country has to raise to assure an optimal quality of life for the Moroccan citizens. The idea of smart-cities is examined with respect to the intent, including current urbanization models, development issues and city planning in Morocco; the case of the proposed smart-city of Casablanca, a flagship of proposals and current realities is looked at. An indigenous alternative following the model proposed of smart-villages instead is examined for appropriateness.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128995052","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}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122137
Srabanti Maji, M. L. Garg
The gene structure is consist of intron, exons, promoter, start codon, stop codon, etc. for the eukaryotic organism. The boundary between intron and exon is splice site. There is the need for accurate algorithms to be used in the splice sites identification and more attention was paid during past few years. This proposed system, Splice Hybrid have three layered architecture — in this layer2nd orderMM is used in the initial stage, i.e. feature extraction; intermediate stage for feature selection principal feature analysis is used; and in the final layer a SVM with RBF kernel is used. In comparison Splice Hybrid tool gives better performance.
{"title":"Hybrid technique for splice site prediction","authors":"Srabanti Maji, M. L. Garg","doi":"10.1109/ICISIM.2017.8122137","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122137","url":null,"abstract":"The gene structure is consist of intron, exons, promoter, start codon, stop codon, etc. for the eukaryotic organism. The boundary between intron and exon is splice site. There is the need for accurate algorithms to be used in the splice sites identification and more attention was paid during past few years. This proposed system, Splice Hybrid have three layered architecture — in this layer2nd orderMM is used in the initial stage, i.e. feature extraction; intermediate stage for feature selection principal feature analysis is used; and in the final layer a SVM with RBF kernel is used. In comparison Splice Hybrid tool gives better performance.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"6 21","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114046289","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}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122147
Suhas B. Dhoke, Anil R. Karwankar, V. Ratnaparkhe
Anemia is a condition in which the hemoglobin (Hb) content becomes less than that of the normal value. In this project, hemoglobin value is estimated using ANN (Artificial Neural Network). Database of blood sample images and their actual Hb values is collected from a local laboratory. Red, green and blue normalized values of images' samples are fed to the ANN as input. Cyanemethemoglobin method based calculated values of Hb obtained from the laboratory are given as output. Comparing the outputs of ANN model results with actual Hb values, accuracy of the network is calculated. This paper covers comparison of performance of different types of Neural Networks for carrying out the stipulated task. It is observed that there is a strong relation between red, green and blue color components of the image with the hemoglobin content of the blood.
{"title":"Estimation of hemoglobin using AI technique","authors":"Suhas B. Dhoke, Anil R. Karwankar, V. Ratnaparkhe","doi":"10.1109/ICISIM.2017.8122147","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122147","url":null,"abstract":"Anemia is a condition in which the hemoglobin (Hb) content becomes less than that of the normal value. In this project, hemoglobin value is estimated using ANN (Artificial Neural Network). Database of blood sample images and their actual Hb values is collected from a local laboratory. Red, green and blue normalized values of images' samples are fed to the ANN as input. Cyanemethemoglobin method based calculated values of Hb obtained from the laboratory are given as output. Comparing the outputs of ANN model results with actual Hb values, accuracy of the network is calculated. This paper covers comparison of performance of different types of Neural Networks for carrying out the stipulated task. It is observed that there is a strong relation between red, green and blue color components of the image with the hemoglobin content of the blood.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129014553","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}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122154
H. Hasan, Falguni Sanyal, Dipankar Chaki, Md. Haider Ali
Keyword extraction is an automated process that collects a set of terms, illustrating an overview of the document. The term is defined how the keyword identifies the core information of a particular document. Analyzing huge number of documents to find out the relevant information, keyword extraction will be the key approach. This approach will help us to understand the depth of it even before we read it. In this paper, we have given an overview of different approaches and algorithms that have been used in keyword extraction technique and compare them to find out the better approach to work in the future. We have studied various algorithms like support vector machine (SVM), conditional random fields (CRF), NP-chunk, n-grams, multiple linear regression, and logistic regression to find out important keywords in a document. We have figured out that SVM and CRF give better results where CRF accuracy is greater than SVM based on F1 score (The balance between precision and recall). According to precision, SVM shows a better result than CRF. But, in case of the recall, logit shows the greater result. Also, we have found out that, there are two more approaches that have been used in keyword extraction technique. One is statistical approach and another is machine learning approach. Statistical approaches show good result with statistical data. Machine learning approaches provide better result than the statistical approaches using training data. Some specimens of statistical approaches are Expectation-Maximization, K-Nearest Neighbor and Bayesian. Extractor and GenEx are the example of machine learning approaches in keyword extraction fields. Apart from these two approaches, semantic relation between words is another key feature in keyword extraction techniques.
关键字提取是一个自动过程，它收集一组术语，说明文档的概述。该术语定义了关键字如何标识特定文档的核心信息。分析海量的文档，找出相关信息，关键字提取将是关键方法。这种方法可以帮助我们在阅读之前就理解它的深度。在本文中，我们概述了在关键字提取技术中使用的不同方法和算法，并对它们进行比较，以找出未来更好的工作方法。我们研究了各种算法，如支持向量机(SVM)、条件随机场(CRF)、NP-chunk、n-grams、多元线性回归、逻辑回归等，以找出文档中的重要关键词。我们已经发现SVM和CRF给出了更好的结果，其中基于F1分数(precision and recall之间的平衡)的CRF准确率大于SVM。从精度上看，SVM优于CRF。但是，在召回的情况下，logit显示了更大的结果。此外，我们还发现，在关键字提取技术中使用了另外两种方法。一种是统计方法，另一种是机器学习方法。统计方法对统计数据显示出良好的效果。机器学习方法比使用训练数据的统计方法提供更好的结果。统计方法的一些例子是期望最大化，k近邻和贝叶斯。Extractor和GenEx是关键字提取领域中机器学习方法的例子。除了这两种方法之外，词间的语义关系是关键词提取技术的另一个关键特征。
{"title":"An empirical study of important keyword extraction techniques from documents","authors":"H. Hasan, Falguni Sanyal, Dipankar Chaki, Md. Haider Ali","doi":"10.1109/ICISIM.2017.8122154","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122154","url":null,"abstract":"Keyword extraction is an automated process that collects a set of terms, illustrating an overview of the document. The term is defined how the keyword identifies the core information of a particular document. Analyzing huge number of documents to find out the relevant information, keyword extraction will be the key approach. This approach will help us to understand the depth of it even before we read it. In this paper, we have given an overview of different approaches and algorithms that have been used in keyword extraction technique and compare them to find out the better approach to work in the future. We have studied various algorithms like support vector machine (SVM), conditional random fields (CRF), NP-chunk, n-grams, multiple linear regression, and logistic regression to find out important keywords in a document. We have figured out that SVM and CRF give better results where CRF accuracy is greater than SVM based on F1 score (The balance between precision and recall). According to precision, SVM shows a better result than CRF. But, in case of the recall, logit shows the greater result. Also, we have found out that, there are two more approaches that have been used in keyword extraction technique. One is statistical approach and another is machine learning approach. Statistical approaches show good result with statistical data. Machine learning approaches provide better result than the statistical approaches using training data. Some specimens of statistical approaches are Expectation-Maximization, K-Nearest Neighbor and Bayesian. Extractor and GenEx are the example of machine learning approaches in keyword extraction fields. Apart from these two approaches, semantic relation between words is another key feature in keyword extraction techniques.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129265647","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}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122142
R. Kabra
Representation of data is very important in case of machine learning. Better the representation, the classifiers will give better results. Contractive autoencoders are used to learn the representation of data which are robust to small changes in the input. This paper uses contractive autoencoder and SVM classifier for handwritten Devanagari numerals recognition. The accuracy obtained using CAE+SVM is 96 %.
{"title":"Contractive autoencoder and SVM for recognition of handwritten Devanagari numerals","authors":"R. Kabra","doi":"10.1109/ICISIM.2017.8122142","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122142","url":null,"abstract":"Representation of data is very important in case of machine learning. Better the representation, the classifiers will give better results. Contractive autoencoders are used to learn the representation of data which are robust to small changes in the input. This paper uses contractive autoencoder and SVM classifier for handwritten Devanagari numerals recognition. The accuracy obtained using CAE+SVM is 96 %.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115549161","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}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122192
R. R. Ragade
Surveillance is one of the most important security system in today's life as it protects home from theft, burglaries and murders, as become routine in big cities. This system is very useful as it is used in many places like offices, industrial, storehouse or bank locker room, ATM etc. This embedded based home security system designed by use of smart sensors like pyroelectric infrared sensor (PIR), ultrasonic sensor to detect an intruder in home. The ultrasonic sensor is used to detect movement of objects and PIR function is to detect changes in temperature of human in infrared radiation. These sensors are built around microcontroller. When the system detects is there any unauthorized person or intruder is present, System triggers a buzzer and sends SMS. After this MCU (microcontroller unit) sends sensor signal to embedded system, to capture an image by web camera.
{"title":"Embedded home surveillance system with pyroelectric infrared sensor using GSM","authors":"R. R. Ragade","doi":"10.1109/ICISIM.2017.8122192","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122192","url":null,"abstract":"Surveillance is one of the most important security system in today's life as it protects home from theft, burglaries and murders, as become routine in big cities. This system is very useful as it is used in many places like offices, industrial, storehouse or bank locker room, ATM etc. This embedded based home security system designed by use of smart sensors like pyroelectric infrared sensor (PIR), ultrasonic sensor to detect an intruder in home. The ultrasonic sensor is used to detect movement of objects and PIR function is to detect changes in temperature of human in infrared radiation. These sensors are built around microcontroller. When the system detects is there any unauthorized person or intruder is present, System triggers a buzzer and sends SMS. After this MCU (microcontroller unit) sends sensor signal to embedded system, to capture an image by web camera.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114775939","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}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122156
R. Telgad, Almas M. N. Siddiqui, Savita A. Lothe, P. Deshmukh, Gajanan Jadhao
In this research paper three biometric characteristics are used i.e. Fingerprint, Face, Iris at score level of Fusion. For finger print images two methods are used i.e. Minutiae Extraction and Gabor filter approach. For Iris recognition system Gabor wavelet is used for feature selection. For Face biometric system P.C.A. is used for feature selection. The match count of every trait is calculated. Then the generated result of match and non match is utilized for the sum score level fusion. Then decision is find out for persons recognition. The system is tested on std. Dataset and KVK data set. On KVK dataset it generates an the results as 99.7 % with FAR of 0.02% and FRR of 0.1% and for FVC 2004 dataset and MMU dataset it gives the result as 99.8 % with FAR of 0.11% and FRR of 0.09%
{"title":"Development of an efficient secure biometric system by using iris, fingerprint, face","authors":"R. Telgad, Almas M. N. Siddiqui, Savita A. Lothe, P. Deshmukh, Gajanan Jadhao","doi":"10.1109/ICISIM.2017.8122156","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122156","url":null,"abstract":"In this research paper three biometric characteristics are used i.e. Fingerprint, Face, Iris at score level of Fusion. For finger print images two methods are used i.e. Minutiae Extraction and Gabor filter approach. For Iris recognition system Gabor wavelet is used for feature selection. For Face biometric system P.C.A. is used for feature selection. The match count of every trait is calculated. Then the generated result of match and non match is utilized for the sum score level fusion. Then decision is find out for persons recognition. The system is tested on std. Dataset and KVK data set. On KVK dataset it generates an the results as 99.7 % with FAR of 0.02% and FRR of 0.1% and for FVC 2004 dataset and MMU dataset it gives the result as 99.8 % with FAR of 0.11% and FRR of 0.09%","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134003548","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}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122138
Shital Anil Phand, Jeevan Anil Phand
Twitter is a micro blogging site where users review or tweet their approach i.e., opinion towards the service providers twitter page in words and it is useful to analyze the sentiments from it. Analyze means finding approach of users or customers where it is positive, negative, neutral, or in between positive-neutral or in between negative-neutral and represent it. In such a system or tool tweets are fetch from twitter regarding shopping websites, or any other twitter pages like some business, mobile brands, cloth brands, live events like sport match, election etc. get the polarity of it. These results will help the service provider to find out about the customers view toward their products.
{"title":"Twitter sentiment classification using stanford NLP","authors":"Shital Anil Phand, Jeevan Anil Phand","doi":"10.1109/ICISIM.2017.8122138","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122138","url":null,"abstract":"Twitter is a micro blogging site where users review or tweet their approach i.e., opinion towards the service providers twitter page in words and it is useful to analyze the sentiments from it. Analyze means finding approach of users or customers where it is positive, negative, neutral, or in between positive-neutral or in between negative-neutral and represent it. In such a system or tool tweets are fetch from twitter regarding shopping websites, or any other twitter pages like some business, mobile brands, cloth brands, live events like sport match, election etc. get the polarity of it. These results will help the service provider to find out about the customers view toward their products.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126490605","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}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122150
Ajay D. Nagne, Rajesh K. Dhumal, Amol D. Vibhute, S. Gaikwad, K. Kale, S. Mehrotra
The objective of this paper is to report the study carried out to assess and evaluate changes in Land-Use Land-Cover(LULC) at the region of Aurangabad Municipal Corporation (AMC) for the year 2009 and 2015 using multispectral images acquired from remotely sensed Linear-Imaging-Self-Scanning-Sensor-HI(LISS-HI). The area was categorized into six types, viz. Residential(R), Vegetation(V), Water_Body(W), Rock(Ro), Barren Land(B) and Fallow_Land(F). Four different types of supervised classifiers have been used and it was found the Maximum Likelihood classifier has provided satisfactory and reliable results. The overall accuracy with the classifier was found to be 83% and 93% with Kappa Coefficient 0.78 and 0.90 for the year 2009 and 2015, respectively. The residential area was found to be increased by 1.35% whereas area related to Water Body, Vegetation and Fallow Land have decreased by 0.83%, 2.59% and 18.43% respectively. The areas for Rock remain same, as it was reserved. The area covered by Barren Land increased by 20.44%. The results are of significant for planning and management of AMC.
本文的目的是报告利用遥感线性成像-自扫描-传感器- hi (lss - hi)获取的多光谱图像对奥兰加巴德市政公司(AMC)地区2009年和2015年土地利用-土地覆盖(LULC)变化进行评估和评价的研究。该地区分为6类，即住宅(R)、植被(V)、水体(W)、岩石(Ro)、荒地(B)和休耕地(F)。使用了四种不同类型的监督分类器，发现最大似然分类器提供了令人满意和可靠的结果。2009年和2015年，该分类器的总体准确率分别为83%和93%，Kappa系数分别为0.78和0.90。住区面积增加了1.35%，而水体、植被和休耕地面积分别减少了0.83%、2.59%和18.43%。岩石的区域保持不变，因为它是保留的。荒地面积增加20.44%。研究结果对AMC的规划和管理具有重要意义。
{"title":"Land use land cover change detection by different supervised classifiers on LISS-III temporal datasets","authors":"Ajay D. Nagne, Rajesh K. Dhumal, Amol D. Vibhute, S. Gaikwad, K. Kale, S. Mehrotra","doi":"10.1109/ICISIM.2017.8122150","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122150","url":null,"abstract":"The objective of this paper is to report the study carried out to assess and evaluate changes in Land-Use Land-Cover(LULC) at the region of Aurangabad Municipal Corporation (AMC) for the year 2009 and 2015 using multispectral images acquired from remotely sensed Linear-Imaging-Self-Scanning-Sensor-HI(LISS-HI). The area was categorized into six types, viz. Residential(R), Vegetation(V), Water_Body(W), Rock(Ro), Barren Land(B) and Fallow_Land(F). Four different types of supervised classifiers have been used and it was found the Maximum Likelihood classifier has provided satisfactory and reliable results. The overall accuracy with the classifier was found to be 83% and 93% with Kappa Coefficient 0.78 and 0.90 for the year 2009 and 2015, respectively. The residential area was found to be increased by 1.35% whereas area related to Water Body, Vegetation and Fallow Land have decreased by 0.83%, 2.59% and 18.43% respectively. The areas for Rock remain same, as it was reserved. The area covered by Barren Land increased by 20.44%. The results are of significant for planning and management of AMC.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115613671","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}
Pub Date : 2017-10-01DOI: 10.1109/ICISIM.2017.8122172
Prashant Devidas Ingle, Parminder Kaur
Owing to the elevated intra/inter variation among the foreground and background text of various document images, the text segmentation from the poorly degraded document images is the difficult job. This paper presents the document image binarization method by adaptive image contrast which is the integration of the local image gradient and the local image contrast which is lenient to background and text variation generated by various document degradations. Initially, an adaptive contrast map is constructed for the input degraded document image by the proposed document image binarization method. Then, the binarization is performed on this adaptive contrast map and the binarized contrast map is integrated with the Canny's edge map for determining the text stroke edge pixels. After that, depends on the local threshold which is defined by the identified text stroke edge pixels' intensities in the local window, the document text is divided. The proposed method is straight forward, vigorous, and it requires least amount of parameter tuning. The experimentation is performed on DIBCO 2011 dataset and the results of the experimentation show that the proposed method achieved high performance than the state-of-the-art methods.
{"title":"Adaptive thresholding to robust image binarization for degraded document images","authors":"Prashant Devidas Ingle, Parminder Kaur","doi":"10.1109/ICISIM.2017.8122172","DOIUrl":"https://doi.org/10.1109/ICISIM.2017.8122172","url":null,"abstract":"Owing to the elevated intra/inter variation among the foreground and background text of various document images, the text segmentation from the poorly degraded document images is the difficult job. This paper presents the document image binarization method by adaptive image contrast which is the integration of the local image gradient and the local image contrast which is lenient to background and text variation generated by various document degradations. Initially, an adaptive contrast map is constructed for the input degraded document image by the proposed document image binarization method. Then, the binarization is performed on this adaptive contrast map and the binarized contrast map is integrated with the Canny's edge map for determining the text stroke edge pixels. After that, depends on the local threshold which is defined by the identified text stroke edge pixels' intensities in the local window, the document text is divided. The proposed method is straight forward, vigorous, and it requires least amount of parameter tuning. The experimentation is performed on DIBCO 2011 dataset and the results of the experimentation show that the proposed method achieved high performance than the state-of-the-art methods.","PeriodicalId":139000,"journal":{"name":"2017 1st International Conference on Intelligent Systems and Information Management (ICISIM)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131312521","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：