Conference Alerts 2013

The 2013 IEEE International Conference on Signal Processing, Computing and Control (2013 IEEE ISPCC) will take place at Jaypee University of Information Technology, Shimla, India from 26-28 September 2013.

2013 IEEE ISPCC is financially co-sponsored by IEEE India Council. It is technically co-sponsored by IEEE Communications Society and IEEE Delhi Section. The conference is endorsed by the Radio Communications Committee (RCC) of the IEEE Communications Society.

The proceedings of 2013 IEEE ISPCC will be published by IEEE and included in IEEE Xplore

Media	IEEE Catalog No.	ISBN
Compliant PDF Files/packing list	CFP1356S-ART	978-1-4673-6190-3
CD-ROM version	CFP1356S-CDR	978-1-4673-6188-0

The conference will provide a platform for researchers from across the world to present their scholarly work among experts and peers and explore new dimensions to further their research. The conference will also have several Keynote Speakers from academia and industry whose talks would put everyone through the paces of the trends, developments and future vision in areas of research related to the conference topics.

The first edition of ISPCC successfully concluded in March 2012. 2012 ISPCC was supported by IEEE, technically co-sponsored by IEEE Delhi Section and the proceedings of which are available on IEEEXplore.

2013 IEEE ISPCC will focus and feature world-class speakers, tutorials and poster sessions on the following topics and their applications:

Signal Processing

VLSI And Embedded computing

Networks and Communication

Control and Automation

Artificial Intelligence and Neural Netowrks

for more details, click here

Submission of Manuscripts

---

Prospective authors are invited to submit full-length manuscripts not exceeding 6 pages (including figures, tables and references) through EDAS.

Important deadlines

---

Submission of Manuscript	15th April, 2013
Notification of Acceptance	15th June 2013
Registration Deadline	5th July 2013
Final Manuscript (Camera Ready)	6th July 2013

Conference Alerts

Fuzz IEEE 2013 

The 2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2013) will be held in the historical city of Hyderabad, India. Hyderabad, the Pearl City of India, is located in the southern part of the Country. It is a vibrant city having many tourist attractions and fine cuisines that blend Mughal, Persian and Telugu cuisines. The city has a very modern International Airport (Rajiv Gandhi International Airport) which is directly connected to many places including Abu Dhabi, Bangkok, Singapore, Doha, Dubai, Jeddah, Kuala Lampur, Kuwait, Muskat, Riyadh, and Sharjah.

It is very well connected to all major cities in India. People from Asia can fly either directly or via Bangkok or Singapore. People from Europe / America can fly to Hyderabad either via Doha, Dubai, London or can fly to Mumbai or Delhi and take a domestic flight to Hyderabad.

The conference will provide a platform for researchers and practitioners to deliberate / exchange ideas on a wide range topics in fuzzy systems and related areas, including but not limited to:

• Fuzzy control and robotics, fuzzy hardware/architectures
• Fuzzy systems design, modeling, identification
• Fuzzy pattern recognition - clustering, classification, feature analysis 
• Fuzzy data/text/web mining, information/text/image retrieval.
• Fuzzy knowledge discovery, learning, reasoning, agents, knowledge representation
• Type-2 fuzzy sets, computing with words, granular computing, rough sets, fuzzy human computer interaction
• Fuzzy set theory, fuzzy measures, fuzzy integrals
• Fuzzy systems in brain science and brain computer interface.
• Fuzzy image, speech and signal processing, vision and multimedia
• Fuzzy decision support systems, decision analysis, multi- criteria decision making
• Applications of fuzzy theories in all areas including bioinformatics, medicine, biomedical signal analysis, software engineering, and industries  
• Evolvable fuzzy systems, adaptive, hierarchical, evolutionary, neural and nature- inspired systems
• Hybrid computational intelligence systems.

Researchers, practitioners, and students are invited to submit full papers (not exceeding 8 pages in IEEE 2-column format) through our submission system at www.isical.ac.in/~fuzzieee2013. 

1st International Conference on Advances in Computing and Information Technology (ICACITY 2013)Conference

  28th February 2013
Kanyakumari, Tamilnadu, India

Website: http://www.irdindia.in/ICACITY_Kanyakumari_Feb/Home.html
Contact person: Prof. Pradeep Kumar Malick

All registered papers of the conference will be published in the conference proceeding having the ISBN number.Selected papers out of this conference will be published in any one or two of the IRD India journals.

Organized by: IRD India
Deadline for abstracts/proposals: 10th February 2013

 

Emerging Trends in IT - eit13Conference

28th   to  28th February 2013
Bangalore, Karnataka, India

Website: http://cs.christuniversity.in/eit
Contact person: Dr. Meenakumari

The fourth national conference would focus on innovative ideas of the current and future challenges and deliberate on emerging trends in IT.

Organized by: Department of Computer Science , Christ University & CSI ( Computer Society of INDIA )
Deadline for abstracts/proposals: 17th January 2013  

 

 

Image Processing in MATLAB

SEGMENTATION

Edge detection

Edge detection is the operation of finding the boundaries of objects present in an image. This is where the image intensity/color changes sharply. Classical methods use the image gradient or approximations of the image gradient to detect edge location. In MATLAB, the function edge detect edges in grayscale and binary images:

BW = edge(I);

If you have a noisy image it is a good practice to smooth it out before detecting the edges. The reason is that noise may produce unreliable oscillating derivative values across short distances.

 Let's investigate the profile of rows of our sample image (its red channel):

 I = imread('sample.TIF');
R = I(:,:,1);
figure, imshow(R);
figure, plot( R(128,:));

Smooth using a Gaussian filter and plot the same line after smoothing:

h = fspecial('gaussian',5,4);
G = imfilter(R, h);
figure, imshow(G);
figure, plot( G(128,:));

Experiment the edge detection methods provided by the edge function in the smoothed image G. Which one(s) works best?

So = edge(G, 'sobel');
Pr = edge(G, 'prewitt');
Ro = edge(G, 'roberts');
Lo = edge(G, 'log');
Ca = edge(G, 'canny');
Use the returned value for the gradient threshold to help you calibrate your edge detection:

[S t] = edge(G, 'sobel');
Snew = edge(G, 'sobel', t + 0.1 );

K-Means

Kmeans is an iterative clustering technique that separates a data set into K mutually exclusive clusters, such that members within a cluster are closer to each other and to the cluster centroid (its mean) than to members and centroid of any other cluster. When applied to perform image segmentation, Kmeans partitions the image into regions of similar intensities. It works very well for images with similarly defined regions.

In MATLAB, use the function kmeans (note that kmeans is not part of the image processing toolbox as it can be used for general data sets; it is a function of the statistics toolbox):

doc kmeans

Let's use Kmeans to segment the red channel of the HELA image. We will need to reshape the image matrix to a format acceptable by kmeans (a flat array):

I = imread('HELA');
I = I(:,:,1);
num_rows = size(I, 1);
num_cols = size(I, 2);
R = reshape( I, num_rows*num_cols, 1 ); (or simply I(:) )
k = 2;
[IDX, C] = kmeans( double(R), k, 'Replicates', 4, 'start', 'sample' );
B = zeros(size(IDX));
B(IDX == 2) = 255;
S = reshape(B, num_rows, num_cols);
figure, imshow(S);

As it is, the kmeans segmentation seems to be a bit inferior when compared to the threshold segmentation we achieved in the previous lecture for the HELA nuclei image.

But we can easily adjust the kmeans result using morphological operations (try also with imfill to fill holes):

sel = strel('disk', 1);
C = bwareaopen( imclose(S, sel), 30 );
figure, imshow(C);

Watershed

The watershed algorithm is a powerful mathematical morphology based segmentation tool. Think of an image as a topographic map where bright regions represent mountain top ridges and dark regions represent valley plateaus. By flood filling this topographic map the watershed algorithm determines the catchment basins that are separated by the ridge lines.



A classical usage of the watershed approach is to separate overlapping, touching regions, a common scenario when imaging cell nuclei, moving bacteria, etc. The watershed method works very well when applied to the Euclidean distance transform of a binary image.

MATLAB provides the watershed function as part of the image processing toolbox:

doc watershed

Consider our HELA nuclei image to be a small piece of a much larger image where you had much success doing some morphological operations to segment the other nuclei but a few touching regions remained. We can try to use watershed to separate these touching regions.


I = imread('overlap-2.png');
D = bwdist(~I);
B = -D;
B(~I) = -Inf;
W = watershed(B, 8);
C = label2rgb( W, 'jet' );
figure, imshow(C);