Informatics Publishing Limited

R. I. Minu ¹, K. K. Thyagharajan ²

Affiliations
1 Anna University of Technology, Trichy, Tamil Nadu, IN
2 RMK College of Engineering and Technology, Chennai, Tamil Nadu, IN

Abstract

In this world of fast computing, automation plays an important role. In image retrieval technique automation is a great quest. Giving an image as a query and retrieving relevant images is a challenging research area. If we go for automation we are in need of an automatic learning technique to predicate the result. So in this paper we are proposing a design of automatic image classification. For the concept of classification here we are using Support Vector Machine classifier, a semi-unsupervised learning technique to classify the images automatically without any manual work. The attribute used for classification are the low level feature such as color and texture of an image. To extract the feature from an image here we use the standardized MPEG7's color and texture descriptor, with which we create a 34 byte DCE Chuck which is used to classify the Images.

Keywords

Image Retrieval, MPEG 7, DCD, EHD, SVM.

Full Text

     

T. Vignesh ¹, K. K. Thyagharajan ², D. Murugan ³, M. Sakthivel ⁴, S. Pushparaj ⁴

Affiliations
1 Department of Computer Science and Engineering, S. A. Engineering College, Chennai - 600077, Tamil Nadu, IN
2 R. M. D Engineering College, Kavaraipettai - 601206, IN
3 Department of Computer Science and Engineering, M. S. University, Tirunelveli - 627012,Tamil Nadu, IN
4 Department of Geography, University of Madras, Chennai - 600005, Tamil Nadu, IN

Abstract

Objectives: To classify the satellite images into different land use/land cover classes such as water, building, cropland, forest, etc, to monitor the environmental impacts. Method: In this paper, images are grouped into various clusters using a novel SVD trace function clustering algorithm. The clustered samples are used as a training set in a novel unsupervised Ensemble Minimization Learning algorithm (EML) for classification. The main aim of using EML is to classify the forest, vegetative land patterns, build up area in rural and urban areas with the use of best accuracy rate. Finding: Our proposed methods provides 90.56% classification rate with low error rate. This EML applies multinomial probit model and ensembles simulated data set and improves the learning of nonlinear relationships between the classified attributes. Multinomial probit model is used to bring all the related possible segmented values to fall into one single category, thus increasing the classification accuracy. Our proposed methods experimented with three different real data sets. The experimental results indicate that our proposed unsupervised model outperforms than the previous techniques. Application: It could be using for land use/land cover change detection, under water object identification, coastal area monitoring, etc. Improvement: In future it could be apply in video data and could be improve the classification accuracy also.

Keywords

Ensemble Minimization Learning algorithm, Land use/Land Cover Classification, Multinominal Probit Model, SVD Trace Function, Unsupervised Algorithm.

Full Text

   

S. Radhakrishnan ¹, S. Neduncheliyan ², K. K. Thyagharajan ³

Affiliations
1 Dr. Pauls Engineering College, Puducherry - 605109, Tamil Nadu, IN
2 Jaya College of Engineering and Technology, Chennai – 600056, Tamil Nadu, IN
3 R. M. D. Engineering College, Chennai - 600040, Tamil Nadu, IN

Abstract

Objective: In recent times, the demand for high data rates is ever increasing in any wireless network environment. Long Term Evolution-Advanced (LTE-A) is the latest 4G technology which is developed based on 3GPP specifications. Our main objective in this proposed research wok is to analyze the various packet scheduling algorithms for downlink real time data and present their scheduling metrics. Methods: In this review we considered more recent scheduling algorithms which are QoS aware and with specific focus on real time traffic classes such as VoIP, Video Streaming, Interactive Gaming and mobile video conference. Conclusion: Our most significant observation from this review is that any packet scheduling algorithm for downlink real time data should be QoS aware so that it is readily deployable in the present day multimedia networks. The scheduling schemes should also consider the latest technologies such as Carrier Aggregation (CA) and Multi Input and Multi Output (MIMO). Applications: The presented review will help the researchers and academicians to develop more efficient scheduling schemes for real time applications for smart phone users with better quality of experience and efficient radio resource management.

Keywords

LTE-Advanced, Packet Scheduling, QoS, Radio Resource Management, Real Time Traffic

Full Text

   

R. I. Minu ¹, K. K. Thyagharajan ²

Affiliations
1 Department of Computer Science and Engineering, Anna University, Tiruchirappalli, IN
2 RMD Engineering College, IN

Abstract

In this world of fast computing, automation plays an important role. In image retrieval technique automation is a great quest. Giving an image as a query and retrieving relevant images is a challenging research area. In this paper we are proposing a research of using Multi-Modality Ontology integration for image retrieval concept. The core strategy in multimodal information retrieval is the combination or fusion of different data modalities to expand and complement information. Here we use both visual and textual ontology contents to provide search functionalities. Both images and texts are complimentary information units as the human perspective will be different. So, the computational linguistic of images will lead to disambiguate text meaning when it is not quite clear in right sense of several words. That's why the Multi-Modal information retrieval may lead to an improved operation of information retrieval system. If we go for automation we are in need of a fuzzy technique to predicate the result. So in this paper we using Support Vector Machine classifier to classify the image automatically by using the general feature such as color, texture and texton of an image , then by using this result we can create both feature and domain ontology for an particular image. Using this Multi-Modality Ontology we can refine our image searching system.

Keywords

Image Retrieval, Multi-Modality Ontology, SVM Classifier, Domain Ontology, Feature Ontology.

Full Text

     

S. Kavitha ¹, K. K. Thyagharajan ²

Affiliations
1 Department of Computer Science and Engineering, SSN College of Engineering, Chennai – 603110, Tamil Nadu, IN
2 Department of Electronics and Communication Engineering, RMD Engineering College, Chennai – 601206, Tamil Nadu, IN

Abstract

Background: Magnetic Resonance Imaging (MRI) is the most prominently used image acquisition method for brain tumor diagnosis, treatment and research. Objective: In this paper, a fuzzy qualitative reasoning model for diagnosing the grade of Astrocytoma brain tumor using various subtypes of MR images (T1, T1c+, T2, Flair) is explained with its implementation details. Methods: The fuzzy model is implemented in 5 stages namely preprocessing, segmentation, feature extraction, feature selection and building a Fuzzy Inference System (FIS) for diagnosis. In preprocessing, anisotropic filtering is used to remove noise and artifacts whereas the edge information and smoothness are retained. Then the tumor region is segmented by applying active contour method. From the segmented tumor region, textural and shape features are extracted and stored along with the clinical parameters like age, gender and mass effect of the patient for feature selection. The features are analyzed in different dimensions like image, patient, patient with subtype, to determine the sensitive feature subset and its range that discriminates the grade of the tumor. Based on this outcome a Mamdani based fuzzy qualitative reasoning model is built with optimal rule set for tumor grade diagnosis. Findings: The constructed fuzzy model is validated using real data set of MR images and clinical report of patients. The grade of tumor identified is same as that specified in the patient's report and hence the model provides better accuracy. Novelty: The novelty of this research work are: subtypes of MR images with analysis in different dimensions, identification of optimal rule set (minimum number of rules without ambiguity), recognition of irregular shape tumor, suitable model for any knowledge based diagnosis.

Full Text