Journal of

Image Processing &

Pattern Recognition Progress

STM JOURNALSScientific Technical Medical

(JoIPPRP)

Jan - April 2014

www.stmjournals.com

STM Publication, a strong initiative by Consortium E-Learning Network Private ltd.(Estd. 2006) was

launched in the year 2010 under the support and guidance by our esteemed Editorial and Advisory board

members from renowned institutes.

Objectives of STM Publication(s):

† Scientific, Technical and Medical research promotions.

† Publication of genuine Research/Review, Short Articles and Case Studies through proper review

process.

† Publishing Special Issues on Conferences.

† Preparing online platform for other print Journals.

† Empowering the libraries with online and print Journals in Scientific, Technical and Medical

domains.

† Publishing and distribution of books on various subjects which mainly falls in the category of

Nanotechnology, Scientific and technical writing & Environment, Health and Safety.

Salient Features:

† A bouquet of 100+ Journals that fall under Science, Technical & Medical domains.

† Employs Open Journals System (OJS) A Journal Management & Publishing System.

† The first and one of the fastest growing publication website in India as well as in abroad for its quality

and coverage.

† Rapid online submission and publication of papers, soon after their formal acceptance/ finalization.

† Facilitates linking with the other authors or professionals.

† Worldwide circulation and visibility.

Journal of Image Processing & Pattern Recognition Progress

Focus and Scope Covers

† Image digital representation

† Biometrics

† New algorithms and/or technologies for biometrics

† Element of visual perception

† Analysis of specific applications

† Restoration Models: Constrained & Unconstrained

† Processing and analysis

Journal of Image Processing & Pattern Recognition Progress is published (frequency: three times a year) in India by

STM Journals (division of Consortium e-Learning Network Private Ltd. Pvt.) The views expressed in the articles do not

necessarily reflect of the Publisher. The publisher does not endorse the quality or value of the advertised/sponsored

products described therein. Please consult full prescribing information before issuing a prescription for any products

mentioned in this publication.

No part of this publication may be reproduced, stored in retrieval system or transmitted in any from without written

permission of the publisher.

To cite any of the material contained in this Journal, in English or translation, please use the full English reference at the

beginning of each article. To reuse any of the material, please contact STM Journals (info@stmjournals.com)

STM Publication(s)

STM Journals (division of Consortium e-Learning Network Private Ltd. ) having its Marketing office located at Office

No. 4, First Floor, CSC pocket E Market, Mayur Vihar Phase II, New Delhi-110091, India is the Publisher of Journal.

Statements and opinions expressed in the Journal reflect the views of the author(s) and are not the opinion of STM

Journals unless so stated.

Subscription Information and Order:

Cost of Journal:

— National Subscription: Rs. 3750/- per Journal (includes 3 print issues), Single Issue copy purchase Rs.1500/copy

— International Subscription:

— Online Only- $99, Print Only-$149 (includes 3 print issues)

— Online + Print-$199 (includes 3 print issues + online access of published back volumes )

To purchase print compilation of back issues please send your query at info@stmjournals.com

Subscription must be prepaid. Rates outside the India includes speed delivery charges. Prices subject to change

without notice.

Mode of Payment: At par cheque, Demand draft, and RTGS (payment to be made in favor of

Consortium E-Learning Network. Pvt. ltd., payable at Delhi/New Delhi.

Online Access Policy

A). For Authors:

In order to provide maximum citation and wide publicity to the authors work, STM Journals also have Open Access

Policy, authors who would like to get their work open access can opt for Optional Open Access publication at

nominal cost as follows

India, SARC and African Countries: INR 2500 or 100 USD including single hard copy of Author's Journal.

Other Countries: USD 200 including single hard copy of Author's Journal.

B.) For Subscribers:

— Online access will be activated within 72 hours of receipt of the payment (working days), subject to receipt of

correct information on user details/Static IP address of the subscriber.

— The access will be blocked:

— If the user requests for the same and furnishes valid reasons for blocking.

— Due to technical issue.

— Misuse of the access rights as per the access policy.

Advertising and Commercial Reprint Inquiries: STM Journals with wide circulation and visibility offer an excellent

media for showcasing/promotion of your products/services and the events-namely, Conferences, Symposia/Seminars

etc. These journals have very high potential to deliver the message across the targeted audience regularly with each

published issue. The advertisements on bulk subscriptions, gift subscriptions or reprint purchases for distribution etc. are

also very welcome.

Lost Issue Claims: Please note the following when applying for lost or missing issues:

— Claims for print copies lost will be honored only after 45 days of the dispatch date and before publication of the

next issue as per the frequency.

— Tracking id for the speed post will be provided to all our subscribers and the claims for the missing Journals will

be entertained only with the proofs which will be verified at both the ends.

— Claims filed due to insufficient (or no notice) of change of address will not be honored.

— Change of Address of Dispatch should be intimated to STM Journals at least 2 months prior to the dispatch

schedule as per the frequency by mentioning subscriber id and the subscription id.

— Refund requests will not be entertained.

Legal Disputes

All the legal disputes are subjected to Delhi Jurisdiction only.

If you have any questions, please contact the Publication Management Team:

info@stmjournals.com; Tel : +91 0120-4781211.

Chairman

Mr. Puneet Mehrotra

Managing Director STM Journals, Consortium eLearning Network Pvt. Ltd.(CELNET)

Noida ,India

Group Managing Editor Dr. Archana Mehrotra

DirectorCELNET, Delhi, India

Puneet Pandeya

ManagerMonika Malhotra

Assistant Manager

Assistant Editors

Aditya Sanyal

Himani Garg

Himani Pandey

Publication Management Team

Internal Members

External Members

Dr. Bimlesh Lochab

Industrial Tribology Machine Dynamics & Maintenance

Engineering Centre (ITMMEC)

Indian Institute of Technology Delhi, India.

Prof. S. Ramaprabhu

Alternative Energy Technology Laboratory,

Department of Physics,

Indian Institute of Technology, Chennai, India.

Dr. Rajiv Prakash

School of Materials Science and Technology,

Institute of Technology, Banaras Hindu University,

Varanasi, India.

Dr. Rakesh Kumar

Assistant Professor, Department of

Applied Chemistry, BIT Mesra,

Patna, India.

Associate Editors

Gargi Asha Jha

Nupur Anand

Priyanka Aswal

Sona Chahal

STM Journal (s) Advisory Board

Dr. Ashish RunthalaLecturer, Biological Sciences Group,

Birla Institute of Technology & Science, Pilani Rajasthan, India.

Dr. Baldev RajDistinguished Scientist & Director,

Indira Gandhi Centre for Atomic Research

(ICGAR)Kalpakkam, India.

Dr. Baskar KaliyamoorthyAssociate Professor, Department

of Civil Engineering National Institute of Technology Trichy, India.

Prof. Bankim Chandra RayProfessor and Head, Department of

Metallurgical and Materials Engineering National Institute of Technology,

Rourkela, India.

Prof.D. N. Rao Professor, Department of Biochemistry,

AIIMS, New Delhi, India.

Prof. Jugal KishoreProfessor, Department of Community

Medicine, Maulana Azad Medical College, New Delhi, India.

Dr. Pankaj PoddarScientist, Physical & Materials ChemistryDivision, National Chemical Laboratory,

Pune, India.

Dr. Hardev Singh VirkProfessor Emeritus, Eternal

University, Baru Sahib, India.

Dr. Nandini Chatterjee SinghAssociate Professor,

National Brain Research Centre, Manesar, India.

Dr. Shankargouda PatilAsst. Prof., Department of Oral

Pathology, KLE Society's Institute of Dental Sciences, Bangalore, India.

Prof. Subash Chandra MishraProfessor, Metallurgical & Materials

Engineering Department, NIT, Rourkela, India.

Prof. Yuwaraj Marotrao GhugalProfessor and Head Department, Govt.College of Engineering Station Road,

Osmanpura, Aurangabad, India.

Prof. Sundara RamaprabhuProfessor, Department of Physics

Indian Institute of Technology Madras, India.

Dr. Shrikant Balkisan DhootHead Research & Development,

Nurture Earth R&D Pvt LtdMIT Campus, Beed bypass road,

Aurangabad, India.

Dr. Rakesh KumarAssistant Professor,

Department of Applied Chemistry, BIT Mesra, Patna, India.

Dr. Priyavrat TharejaHead, Materials and Metallurgical

Engineering department, PEC University of Technology,

Chandigarh, India.

STM Journal (s) Advisory Board Editorial Board

Dr. Aniruddha BhattacharjyaAssistant Professor (Senior Grade)CSE DepartmentAmrita School of

Engineering Amrita Vishwa VidyaPeetham (University), Kasavanahalli.

Rajiv KapoorProfessor and Head of Department

Department Ellectronics and CommunicationEngineering Delhi Technological University, India.

Dr. Narendra KohliAssociate Professor and Ex. Head

Computer Science and Engineering DepartmentHarcourt Butler Technological

Institute Nawab Gang, Kanpur.

Prof. Pavel ZemcikVice-dean for external relations,

Graph@FIT DCGM memberBozetechova Czech Republic.

Editorial Board

Chun Ming ChangAssistant Professor

Department of Applied Informatics and Multimedia Asia University

Wufeng, Taichung 41354, Taiwan.

Dr. Abhishek DasAssistant Professor Dept. of Information

Technology, Tripura University (A Central University)

Suryamaninagar, Agratala.

Dr. V. K. GovindanProfessor Computer science and

engineering, and Dean AcademicNational Institute of Technology Calicut,

Kerala, India.

Dr. Bijan KarimiProfessor Electrical & Computer Engineering

and Computer ScienceTagliatela College of Engineering, India.

Dr. Rameswar DebnathHead Computer Science and

Engineering Discipline.Khulna University, Khulna 9208,

Bangladesh.

Prof. Hsu-Yung ChengAssociate Professor Department of Computer Science and Information

Engineering National Central University, Taiwan.

Dr. Hari OmAssistant Professor Department of Computer Science & EngineeringIndian School of Mines Dhanbad-

826 004 Jharkhand India.

Arup Kumar PalAssistant Professor Department of Computer Science and EngineeringIndian School of Mines, Dhanbad

Jharkhand-826004, India.

Dr. U. S. ReddyAssistant Professor Department of

Computer ApplicationsNational Institute of Technology Tiruchirappalli – 620 015 India.

Prof. Dilip Singh SisodiaAssistant Professor Department of Computer Science & Engineering

National Institute of Technology RaipurIndia.

Prof. Mu-Chun SuProfessor Dept. of Computer Science and

Information EngineeringNational Central University, Taiwan.

Gonzalo VegasAssociate Teacher

University of Valladolid (Spain).

I take the privilege to present the print version for the [Volume 1 Issue (1)] of Journal of Image

Processing & Pattern Recognition Progress. The intension of JoIPPRP is to create an atmosphere that

stimulates creativeness, research and growth in the area of image processing.

The development and growth of the mankind is the consequence of brilliant Research done by

eminent Scientists and Engineers in every field. JoIPPRP provides an outlet for Research findings

and reviews in areas of image processing found to be relevant for National and International recent

developments & research initiative.

The aim and scope of the Journal is to provide an academic medium and an important reference for

the advancement and dissemination of Research results that support high level learning, teaching and

research in the domain of image processing.

Finally, I express my sincere gratitude and thanks to our Editorial/ Reviewer board and Authors for

their continued support and invaluable contributions and suggestions in the form of authoring write

ups/ reviewing and providing constructive comments for the advancement of the journals. With

regards to their due continuous support and co-operation, we have been able to publish quality

Research/Reviews findings for our customers base.

I hope you will enjoy reading this issue and we welcome your feedback on any aspect of the Journal.

Dr. Archana Mehrotra

Director

STM Journals

Director's Desk

STM JOURNALS

1. Estimation of Convolution Masks for MRI Image Restoration using Genetic Algorithm Ashwani Kumar, Yogesh Kumar 1

2. Performance Comparison between Back-Propagation Learning and Kohonen Self-Organizing Neural Networks Algorithm in Terms of Pattern Recognition Md. Rabiul Islam 7

3. Region Segmentation and Annotation with Vehicle Detection Validation Application in Airborne ImagesHsu-Yung Cheng, Ding-Wen Wu 15

4. Image Segmentation based on Region Merging using Breadth-First SearchAmandeep Kaur, Neeru Jindal 26

5. Q-Metrics for Early Detection of Cervical Cancer Das A., Kar A., Bhattacharyya D. 32

ContentsJournal of Image Processing & Pattern Recognition Progress

JoIPPRP (2014)© STM Journals 2014. All Rights Reserved

Journal of Image Processing & Pattern Recognition Progress

Volume 1, Issue 1

www.stmjournals.com

Estimation of Convolution Masks for MRI Image

Restoration using Genetic Algorithm

Ashwani Kumar1*, Yogesh Kumar

2

1Neelkanth Institute of Technology Meerut, UP, India 2Translam Institute of Technology Meerut, UP, India

Abstract The present paper proposes the technique for the restoration of images using convolution masks generated using GA. Image restoration is carried out to recover a

corrected image from a degraded image and is specific to the type of degradation. In

image restoration there is need to build the specific mathematical model for degradation or degradation function hence there is need to know about the cause of degradation

without which some time it becomes impossible to correct the image. In most practical

cases there is not enough information available about the degradation, and is needed to be estimated either analytically or empirically. The level of problem of image

restoration is further increased by the presence of noise, and more than one cause of degradation, as in these circumstances it becomes difficult to formulate the

mathematical model or degradation function. To alleviate this difficulty we have

proposed method to generate convolution mask using GA for application in image restoration technique. The proposed algorithm has been tested on images simulated

with the motion blurring and for the presence of noise. Finally the algorithm is applied to correct the motion artefact in Computed tomography images; the results

obtained are promising and can be applied to other area of imaging also.

Keywords: convolution masks, image restoration, genetic algorithm.

JoIPPRP (2014)© STM Journals 2014. All Rights Reserved

Journal of Image Processing & Pattern Recognition Progress

Volume 1, Issue 1

www.stmjournals.com

Performance Comparison between Back-Propagation

Learning and Kohonen Self-Organizing Neural Networks

Algorithm in Terms of Pattern Recognition

Md. Rabiul Islam* Department of Computer Science & Engineering, Rajshahi University of Engineering & Technology

Rajshahi, Bangladesh

Abstract Pattern recognition using back-propagation learning and Kohonen self-organizing

neural network algorithms has been developed and measured various performance based

on different criteria and environment of the pattern. These pattern recognition systems have taken the object image as input. In image pre-processing stage, scaling and clipping

process has been applied from the background image to avoid unnecessary portion of the object image. Feature extraction has been performed after applying filtering and edge-

detection method. The extracted feature has been used as the input of the back-

propagation learning neural networks (BPN) algorithm and Kohonen self-organizing mapping (SOM) algorithm. Networks have been trained to create the knowledgebase

from the input features. Finally, these learned templates have been used for testing

purpose. The difference between two training procedure is that the learned weights and thresholds have been updated to calculate the output for BPN and feature mapping

technique in output grid has been used for Kohonen network. Finally, the performances of both algorithms have been measured and compared the learning and recognition

performance on the various selected criteria.

Keywords: Back-propagation learning neural networks, kohonen self-organizing

mapping neural network, feture extraction, pattern recognition

JoIPPRP (2014)© STM Journals 2014. All Rights Reserved

Journal of Image Processing & Pattern Recognition Progress

Volume 1, Issue 1

www.stmjournals.com

Region Segmentation and Annotation with Vehicle

Detection Validation Application in Airborne Images

Hsu-Yung Cheng*, Ding-Wen Wu Department of Computer Science and Information Engineering, National Central University, Taiwan

Abstract In this work, the authors propose an automatic image segmentation and annotation system

for airborne images. Initial region segmentation using existing region segmentation

methods is applied to airborne images first. To deal with over-segmentation on the initial

region segmentation results, the authors performed graph-based region merging by

constructing an undirected-graph based on 8-connected local neighborhood. For each

region, the authors extracted low-level features and used the Support Vector Machine

(SVM) classifier to annotate the region with labels. Based on the output of the SVM

classifier, adjacent regions with the same label were further merged to obtain the final

segmentation and labeling result. The segmentation and annotation results are useful for

vehicle detection validation. The experiments show that the proposed system can

effectively segment and label various aerial images on a highly challenging dataset. Also,

vehicle detection can be substantially enhanced with the help of the proposed annotation

results and validation scheme.

Keywords: Airborne images, vehicle detection, region segmentation, annotation

JoIPPRP (2014) © STM Journals 2014. All Rights Reserved

Journal of Image Processing & Pattern Recognition Progress

Volume 1, Issue 1

www.stmjournals.com

Image Segmentation based on Region Merging using

Breadth-First Search

Amandeep Kaur*, Neeru Jindal

Electronics & Communication, R.I.E.I.T Railmajra, SBS Nagar, India

Abstract This paper proposed a new method for image segmentation based on region merging using breadth-first search (BFS). The image can be partitioned into multiple segments so

that meaningful information is extracted out and then image is analyzed easily. In the

proposed method, first the oversegmented image is obtained by applying a standard

watershed transformation on original image. Then BFS is executed on the oversegmented

image to obtain a segmented image. The quality parameter F-measure has been calculated for the segmented images. The proposed algorithm is also compared with

existing method and better results are obtained.

Keywords: Image segmentation, watershed transformation, BFS.

JoIPPRP (2014)© STM Journals 2014. All Rights Reserved

Journal of Image Processing & Pattern Recognition Progress

Volume 1, Issue 1

www.stmjournals.com

Q-Metrics for Early Detection of Cervical Cancer

Das A.1*, Kar A.

2, Bhattacharyya D.

3

1Department of Information Technology, Tripura University (A Central University),

Agartala, Tripura, India 2Department of Computer Science & Engineering, Jadavpur University, Kolkata, West Bengal, India

3Department of Gynecology & Obstetrics, College of Medicine & SD Hospital, Kolkata,

West Bengal, India

Abstract The most prevalent form of cancer in women worldwide is uterine cervical cancer. Through screening programs aimed at detecting precancerous lesions most cases of

cervical cancer can be prevented. In this article, Q-metrics has been proposed for

carrying out automated image segmentation of uterine cervical cancer. The validation of detection of cervical lesions is an important issue in medical image processing because it

has a specific impact on surgical planning. We evaluated the segmentation accuracy on the basis of a four-sample validation metric against the estimated gold standard, which

was derived from several domain experts’ manual segmentations by a novel algorithm.

The distribution functions of the lesion and control pixel data were parametrically assumed to be a mixture of two beta distributions with different shape parameters. We

estimated the corresponding receiver operating characteristic (R.O.C.) curve and Dice

similarity coefficient (D.S.C.) in all possible decision thresholds. The automated segmentation yielded satisfactory accuracy with varied optimal thresholds.

Keywords: cervical cancer, automated segmentation, E.M. algorithm, sensitivity,

specificity, clustering, R.O.C., D.S.C.