Pub Date : 2011-12-01DOI: 10.1109/ICOAC.2011.6165157
R. Vaddi, L. Boggavarapu, H. D. Vankayalapati, K. R. Anne
Contrast enhancement is one of the primary aspects in computer vision. In order to understand the image, the contrast of the image should be clear. In many scenarios, especially in biomedical images, security and surveillance, the visual quality of source images or video is not up to the expected quality. There exist many algorithms such as histogram equalization, genetic algorithms and neural networks to improve the contrast of the images. In this work, we summarized the state of the art and made comparative study among contrast enhancement techniques. Comparisons are done in two cases: one among the histogram based techniques, another between histogram based techniques and method using Cellular Neural Networks (CNN). The method using CNN proved to perform better than the conventional techniques.
{"title":"Comparative analysis of contrast enhancement techniques between histogram equalization and CNN","authors":"R. Vaddi, L. Boggavarapu, H. D. Vankayalapati, K. R. Anne","doi":"10.1109/ICOAC.2011.6165157","DOIUrl":"https://doi.org/10.1109/ICOAC.2011.6165157","url":null,"abstract":"Contrast enhancement is one of the primary aspects in computer vision. In order to understand the image, the contrast of the image should be clear. In many scenarios, especially in biomedical images, security and surveillance, the visual quality of source images or video is not up to the expected quality. There exist many algorithms such as histogram equalization, genetic algorithms and neural networks to improve the contrast of the images. In this work, we summarized the state of the art and made comparative study among contrast enhancement techniques. Comparisons are done in two cases: one among the histogram based techniques, another between histogram based techniques and method using Cellular Neural Networks (CNN). The method using CNN proved to perform better than the conventional techniques.","PeriodicalId":369712,"journal":{"name":"2011 Third International Conference on Advanced Computing","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126298446","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 : 2011-12-01DOI: 10.1109/ICOAC.2011.6165179
V. M. Raj, R. Shriram
Cloud computing and Virtualization has become the focus of tremendous amount of research in recent years. The advances in network bandwidth, the need for services that can be accessed anytime from anywhere and the change in ownership models are some of the factors responsible. As cloud services are intended to be ‘always on’, the energy costs to provision services are already significant with increase in both cloud services user-base and rise in global energy prices. Increase in energy consumption has a direct impact on provider's total cost of ownership and inflates the subscriber's price point. Identifying areas within datacenter hosting cloud infrastructure and services for energy inefficiencies or bottlenecks is one approach to save energy. In this paper, we propose a simulation approach to track service/application request level flow path in a virtualized multi-tier environment from initiation to completion; analyze the energy consumption of the request at every tier, identify bottlenecks that would impact the QOS criteria; and take necessary action to recover. Our simulation results show a 16% improvement in energy consumption using proposed approach when compared with unconstraint/default approach.
{"title":"Improving energy efficiency using request tracing as a tool in a multi-tier virtualized environment","authors":"V. M. Raj, R. Shriram","doi":"10.1109/ICOAC.2011.6165179","DOIUrl":"https://doi.org/10.1109/ICOAC.2011.6165179","url":null,"abstract":"Cloud computing and Virtualization has become the focus of tremendous amount of research in recent years. The advances in network bandwidth, the need for services that can be accessed anytime from anywhere and the change in ownership models are some of the factors responsible. As cloud services are intended to be ‘always on’, the energy costs to provision services are already significant with increase in both cloud services user-base and rise in global energy prices. Increase in energy consumption has a direct impact on provider's total cost of ownership and inflates the subscriber's price point. Identifying areas within datacenter hosting cloud infrastructure and services for energy inefficiencies or bottlenecks is one approach to save energy. In this paper, we propose a simulation approach to track service/application request level flow path in a virtualized multi-tier environment from initiation to completion; analyze the energy consumption of the request at every tier, identify bottlenecks that would impact the QOS criteria; and take necessary action to recover. Our simulation results show a 16% improvement in energy consumption using proposed approach when compared with unconstraint/default approach.","PeriodicalId":369712,"journal":{"name":"2011 Third International Conference on Advanced Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122629001","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 : 2011-12-01DOI: 10.1109/ICOAC.2011.6165162
T. Sumathi, M. Hemalatha
Automatic image annotation is the process by which a computer system automatically assigns metadata in the form of captioning or keywords to a digital image. This application of computer vision technique is used in image retrieval system to organize and locate images of interest from a database. Many techniques have been proposed for image annotation in the last decade that gives reasonable performance on standard datasets. In this work, we introduce an innovative hybrid model for image annotation that treats annotation as a retrieval problem. The proposed technique utilizes low level image features and a simple combination of basic distances using JEC to find the nearest neighbors of a given image; the keywords are then assigned using SVM approach which aims to explore the combination of three different methods. First, the initial annotation of the data using two known methods, and that takes the hierarchy into consideration by classifying consecutively its instances; finally, we make use of pair wise majority voting between methods by simply summing strings in order to produce a final annotation. The proposed technique results show that this method outperforms the current state of art methods on the standard datasets.
{"title":"A combined hierarchical model for automatic image annotation and retrieval","authors":"T. Sumathi, M. Hemalatha","doi":"10.1109/ICOAC.2011.6165162","DOIUrl":"https://doi.org/10.1109/ICOAC.2011.6165162","url":null,"abstract":"Automatic image annotation is the process by which a computer system automatically assigns metadata in the form of captioning or keywords to a digital image. This application of computer vision technique is used in image retrieval system to organize and locate images of interest from a database. Many techniques have been proposed for image annotation in the last decade that gives reasonable performance on standard datasets. In this work, we introduce an innovative hybrid model for image annotation that treats annotation as a retrieval problem. The proposed technique utilizes low level image features and a simple combination of basic distances using JEC to find the nearest neighbors of a given image; the keywords are then assigned using SVM approach which aims to explore the combination of three different methods. First, the initial annotation of the data using two known methods, and that takes the hierarchy into consideration by classifying consecutively its instances; finally, we make use of pair wise majority voting between methods by simply summing strings in order to produce a final annotation. The proposed technique results show that this method outperforms the current state of art methods on the standard datasets.","PeriodicalId":369712,"journal":{"name":"2011 Third International Conference on Advanced Computing","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133640289","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 : 2011-12-01DOI: 10.1109/ICOAC.2011.6165189
Dhananjay Kumar, G. Kalaichelvi, D. Saravanan, T. K. Loheswari
The cognitive radio is an intelligent wireless communication system dynamically adapting itself to the operating environment by changing its parameters, towards reliable communication and efficient spectrum utilization. Radio scene analysis is the first and foremost task based on which the spectrum is sensed towards its efficient utilization. A real-time observation is needed to model the statistical data of spectrum utilization with reference to specific geographic location and time, which can be utilized in resource allocation of cognitive radio system. This paper presents typical spectrum occupancy of the 902–928 MHz ISM band obtained through signal strength measurements and its statistical study. The usage of such channel occupancy statistical data in the spectrum sensing formulation is also elaborated in a typical scenario for a frequency hopping system working in this band. The simulation result of energy based detection of the above system is presented to realize a cognitive environment.
{"title":"Spectrum opportunity in UHF — ISM band of 902–928 MHz for cognitive radio","authors":"Dhananjay Kumar, G. Kalaichelvi, D. Saravanan, T. K. Loheswari","doi":"10.1109/ICOAC.2011.6165189","DOIUrl":"https://doi.org/10.1109/ICOAC.2011.6165189","url":null,"abstract":"The cognitive radio is an intelligent wireless communication system dynamically adapting itself to the operating environment by changing its parameters, towards reliable communication and efficient spectrum utilization. Radio scene analysis is the first and foremost task based on which the spectrum is sensed towards its efficient utilization. A real-time observation is needed to model the statistical data of spectrum utilization with reference to specific geographic location and time, which can be utilized in resource allocation of cognitive radio system. This paper presents typical spectrum occupancy of the 902–928 MHz ISM band obtained through signal strength measurements and its statistical study. The usage of such channel occupancy statistical data in the spectrum sensing formulation is also elaborated in a typical scenario for a frequency hopping system working in this band. The simulation result of energy based detection of the above system is presented to realize a cognitive environment.","PeriodicalId":369712,"journal":{"name":"2011 Third International Conference on Advanced Computing","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133725855","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 : 2011-12-01DOI: 10.1109/ICOAC.2011.6165194
V. Shibu, Philomina Simon
In the proposed method, a combined approach of Adaptive Mean Shift and Normalized Cuts is used for clustering the images. In this method, both color and gray scale images can be segmented effectively and it requires less computational complexity. In the first stage, the image is divided into different segments using Adaptive Mean Shift algorithm and the segments generated are labeled and the labeled segments are represented as nodes in a graph. The result obtained by applying the Adaptive Mean Shift algorithm is given to the normalized cut method for grouping the clustered segments. Experimental result shows that the proposed method gives better performance in terms of segments than other methods when tested with color and gray scale natural images.
该方法采用自适应均值漂移和归一化分割相结合的方法对图像进行聚类。该方法能有效分割彩色图像和灰度图像，且计算复杂度较低。在第一阶段，使用Adaptive Mean Shift算法将图像分割成不同的片段，并对生成的片段进行标记，将标记的片段表示为图中的节点。将自适应Mean Shift算法应用于归一化切割方法对聚类段进行分组。实验结果表明，该方法对彩色和灰度自然图像的分割效果优于其他方法。
{"title":"An efficient method for color image segmentation using adaptive mean shift and normalized cuts","authors":"V. Shibu, Philomina Simon","doi":"10.1109/ICOAC.2011.6165194","DOIUrl":"https://doi.org/10.1109/ICOAC.2011.6165194","url":null,"abstract":"In the proposed method, a combined approach of Adaptive Mean Shift and Normalized Cuts is used for clustering the images. In this method, both color and gray scale images can be segmented effectively and it requires less computational complexity. In the first stage, the image is divided into different segments using Adaptive Mean Shift algorithm and the segments generated are labeled and the labeled segments are represented as nodes in a graph. The result obtained by applying the Adaptive Mean Shift algorithm is given to the normalized cut method for grouping the clustered segments. Experimental result shows that the proposed method gives better performance in terms of segments than other methods when tested with color and gray scale natural images.","PeriodicalId":369712,"journal":{"name":"2011 Third International Conference on Advanced Computing","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133876347","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 : 2011-12-01DOI: 10.1109/ICOAC.2011.6165180
V. Raj, M. Srinivasan, B. Sathiya
Motion Compensated Frame Interpolation addresses the tribulations of defective motion vectors that cause visual artifacts but cannot be detected by high residual energy or bidirectional prediction difference. A correlation-based motion vector processing method is proposed to detect those unreliable motion vectors by explicitly considering motion vectors correlation in the motion vector reliability classification, motion vector correction, and frame interpolation stages. MCFI can effectively discover the areas where no motion is reliable, such as occlusions and deformed scheme for the occlusion areas based on the analysis of their surrounding motion distribution. Interpolated Frame obtained using the proposed schemes have cleared structure edges and ghost artifacts which can be greatly reduced. MCFI shows better visual quality to obtain true motion. MCFI scheme is highly robust for the video sequences that contain fast motion.
{"title":"Detection of small moving objects based on motion vector processing using BDD method","authors":"V. Raj, M. Srinivasan, B. Sathiya","doi":"10.1109/ICOAC.2011.6165180","DOIUrl":"https://doi.org/10.1109/ICOAC.2011.6165180","url":null,"abstract":"Motion Compensated Frame Interpolation addresses the tribulations of defective motion vectors that cause visual artifacts but cannot be detected by high residual energy or bidirectional prediction difference. A correlation-based motion vector processing method is proposed to detect those unreliable motion vectors by explicitly considering motion vectors correlation in the motion vector reliability classification, motion vector correction, and frame interpolation stages. MCFI can effectively discover the areas where no motion is reliable, such as occlusions and deformed scheme for the occlusion areas based on the analysis of their surrounding motion distribution. Interpolated Frame obtained using the proposed schemes have cleared structure edges and ghost artifacts which can be greatly reduced. MCFI shows better visual quality to obtain true motion. MCFI scheme is highly robust for the video sequences that contain fast motion.","PeriodicalId":369712,"journal":{"name":"2011 Third International Conference on Advanced Computing","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130311893","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 : 2011-12-01DOI: 10.1109/ICOAC.2011.6165207
M. Malleswaran, V. Vaidehi, R. A. Joseph
Global positioning System (GPS) and Inertial Navigation System (INS) data can be integrated together to provide a reliable navigation. This paper presents an approach of solving GPS/INS data integration problem, without the need of modeling the characteristics of GPS and INS sensors. This approach uses Genetically optimized Adaptive Neuro-Fuzzy Inference System (GANFIS) as an alternative to the conventional Kalman filter approach in which it is mandatory to model the entire system.
{"title":"Genetically optimized ANFIS based Intelligent Navigation System","authors":"M. Malleswaran, V. Vaidehi, R. A. Joseph","doi":"10.1109/ICOAC.2011.6165207","DOIUrl":"https://doi.org/10.1109/ICOAC.2011.6165207","url":null,"abstract":"Global positioning System (GPS) and Inertial Navigation System (INS) data can be integrated together to provide a reliable navigation. This paper presents an approach of solving GPS/INS data integration problem, without the need of modeling the characteristics of GPS and INS sensors. This approach uses Genetically optimized Adaptive Neuro-Fuzzy Inference System (GANFIS) as an alternative to the conventional Kalman filter approach in which it is mandatory to model the entire system.","PeriodicalId":369712,"journal":{"name":"2011 Third International Conference on Advanced Computing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114162318","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 : 2011-12-01DOI: 10.1109/ICOAC.2011.6165176
R. Mariappan, K. Shriram
Wireless WDM networks are composed of autonomous WDM nodes that are often deployed in unattended environment, thus leaving them vulnerable to capture and compromised by an adversary. One of the major challenges that wireless WDM networks face today is security. In this paper, we consider two types of security attacks namely node replication attack and black hole attack. In node replication attack, the attacker obtains network information from WDM nodes and generates replicas back into the network. Using a distributed approach replica nodes are detected with the help of witness nodes that are randomly selected from the network. Another security attack that occurs in wireless WDM networks is black hole attack, which absorbs all data packets in the network. For secure data delivery in the network, a randomized multipath routing mechanism is proposed, in which multiple paths are computed in a randomized way such that set of routes taken by shares of different packets changes over time which ultimately makes adversary difficult in finding routes traversed by each packet.
{"title":"Randomized multipath routing protocol for secure data transmission in wireless IP-over-WDM networks","authors":"R. Mariappan, K. Shriram","doi":"10.1109/ICOAC.2011.6165176","DOIUrl":"https://doi.org/10.1109/ICOAC.2011.6165176","url":null,"abstract":"Wireless WDM networks are composed of autonomous WDM nodes that are often deployed in unattended environment, thus leaving them vulnerable to capture and compromised by an adversary. One of the major challenges that wireless WDM networks face today is security. In this paper, we consider two types of security attacks namely node replication attack and black hole attack. In node replication attack, the attacker obtains network information from WDM nodes and generates replicas back into the network. Using a distributed approach replica nodes are detected with the help of witness nodes that are randomly selected from the network. Another security attack that occurs in wireless WDM networks is black hole attack, which absorbs all data packets in the network. For secure data delivery in the network, a randomized multipath routing mechanism is proposed, in which multiple paths are computed in a randomized way such that set of routes taken by shares of different packets changes over time which ultimately makes adversary difficult in finding routes traversed by each packet.","PeriodicalId":369712,"journal":{"name":"2011 Third International Conference on Advanced Computing","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124769529","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 : 2011-12-01DOI: 10.1109/ICOAC.2011.6165167
C. Velayutham, K. Thangavel
Feature Selection (FS) has become one of the most active research topics in the area of data mining. It performs to remove redundant and noisy features from high-dimensional data sets. A good feature selection has several advantages for a learning algorithm such as reducing computational cost, increasing its classification accuracy and improving result comprehensibility. In the supervised FS methods various feature subsets are evaluated using an evaluation function or metric to select only those features which are related to the decision classes of the data under consideration. However, for many data mining applications, decision class labels are often unknown or incomplete, thus indicating the significance of unsupervised feature selection. However, in unsupervised learning, decision class labels are not provided. The problem is that not all features are important. Some of the features may be redundant, and others may be irrelevant and noisy. In this paper, a novel unsupervised feature selection in mammogram image, using rough set based measures, is proposed. A typical mammogram image processing system generally consists of mammogram image acquisition, preprocessing of image, segmentation, features extracted from the segmented mammogram image. The proposed method is used to select features from data set, the method is compared with existing rough set based supervised feature selection methods and classification performance of both methods are recorded and demonstrates the efficiency of the method.
{"title":"Unsupervised feature selection based on the measures of degree of dependency using rough set theory in digital mammogram image classification","authors":"C. Velayutham, K. Thangavel","doi":"10.1109/ICOAC.2011.6165167","DOIUrl":"https://doi.org/10.1109/ICOAC.2011.6165167","url":null,"abstract":"Feature Selection (FS) has become one of the most active research topics in the area of data mining. It performs to remove redundant and noisy features from high-dimensional data sets. A good feature selection has several advantages for a learning algorithm such as reducing computational cost, increasing its classification accuracy and improving result comprehensibility. In the supervised FS methods various feature subsets are evaluated using an evaluation function or metric to select only those features which are related to the decision classes of the data under consideration. However, for many data mining applications, decision class labels are often unknown or incomplete, thus indicating the significance of unsupervised feature selection. However, in unsupervised learning, decision class labels are not provided. The problem is that not all features are important. Some of the features may be redundant, and others may be irrelevant and noisy. In this paper, a novel unsupervised feature selection in mammogram image, using rough set based measures, is proposed. A typical mammogram image processing system generally consists of mammogram image acquisition, preprocessing of image, segmentation, features extracted from the segmented mammogram image. The proposed method is used to select features from data set, the method is compared with existing rough set based supervised feature selection methods and classification performance of both methods are recorded and demonstrates the efficiency of the method.","PeriodicalId":369712,"journal":{"name":"2011 Third International Conference on Advanced Computing","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124075995","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 : 2011-12-01DOI: 10.1109/ICOAC.2011.6165182
R. Sudhakar, K. Krishnan, S. Muthukrishnan
In the recent years, with an increase in the awareness of internet usage, there has been an explosion of data on the web. Huge amount of data resides on the web and of late there has been an increased necessity for search engines that retrieve documents and images, at least close to the search criteria if not exactly. The problem of retrieving near approximate images using textual queries has always been an area of research. This paper focuses on bridging the gap between textual search input given by the user and the images retrieved from the database, by making use of visual features instead of the file name, which is generally the case in many search engines.
{"title":"A hybrid approach to content based image retrieval using visual features and textual queries","authors":"R. Sudhakar, K. Krishnan, S. Muthukrishnan","doi":"10.1109/ICOAC.2011.6165182","DOIUrl":"https://doi.org/10.1109/ICOAC.2011.6165182","url":null,"abstract":"In the recent years, with an increase in the awareness of internet usage, there has been an explosion of data on the web. Huge amount of data resides on the web and of late there has been an increased necessity for search engines that retrieve documents and images, at least close to the search criteria if not exactly. The problem of retrieving near approximate images using textual queries has always been an area of research. This paper focuses on bridging the gap between textual search input given by the user and the images retrieved from the database, by making use of visual features instead of the file name, which is generally the case in many search engines.","PeriodicalId":369712,"journal":{"name":"2011 Third International Conference on Advanced Computing","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130749207","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：