Education & Training

  • Ph.D.2015-Present

    Graduate Student at the College of IST

    Pennsylvania State University

  • M.Sc.2013-2015

    Master of Science in Communication Systems

    Sharif University of Technology

  • B.Sc.2008-2013

    Bachelor of Science in Electrical Engineering

    Sharif University of Technology

I always like to look on the optimistic side of life, but I am realistic enough to know that life is a complex matter.

Honors, Awards and Grants

  • 2017
    Academic Computing Fellowship
    image
    PennState Academic Computing Fellowship for 3 years. I am the first awardee of this fellowship in the history of the College of Information Sciences and Technology.
  • 2016
    NSF Travel Award
    image
    NSF Travel Award to attend to International IEEE Big Data Conference in Washington D.C. (Dec 2016)
  • 2013
    University Entrance Exam for Postgraduate Studies Achievement
    image
    Ranked 19th in the Nationwide Electrical Engineering University Entrance Exam for postgraduate studies among 40000 participants (Feb 2013)
  • 2008
    University Entrance Exam Achievement
    image
    Ranked 7th in the Nationwide Mathematics and Physics University Entrance Exam among 300,000 participants (Jul 2008)
  • 2008
    Exceptional Talents of Iran
    image
    Member of the National Organization of Exceptional Talents in Iran
  • 2008
    Exceptional Talents of Sharif University of Technology
    image
    Member of the organization of Exceptional Talents at Sharif University of Technology
  • 2006
    National Chemistry Olympiad
    image
    Accepted in the first stage of National Chemistry Olympiad Ranked 4th among 10,000 participants

Research Summary

My research interests are in the realm of Data Analysis and extracting information out of pure data. Up to now, I have worked on different kind of data in this field such as speech, image and market data. Becoming a master in this field needs to have knowledge of Machine Learning, Pattern Recognition, and Computer Vision.

My past and recent projects revolve around Data Analysis in different applications. The most important projects of mine are: Severe Weather Forcasting, Image Processing in Cultural Heritage, Fuzzy Speech Recognition and Business Intelligence.

Interests

  • Computer Vision
  • Machine Learning
  • Data Mining & Data Analysis
  • Big Data
  • Signal & Image Processing
  • Business Intelligence

My Advisers

Dr. Ali Fotowat Ahmadi

Associate Professor

Website

Dr. Saeed Bagheri Shouraki

Professor

Website

Dr. James Z. Wang

Professor

Website

Dr. Farrokh Marvasti

Professor

Website

Dr. Arash Amini

Assistant Professor

Website

Great Advisers!

Working under supervision of variety of professors have had quite number of advantages for me. I have benefited greatly from experience of my supervisors. Using different approach toward solving a problem is one of the greatest offspring of having these supervisors.

Filter by type:

Sort by year:

Shape Matching using Skeleton Context for automated Bow Echo Detection

Mohammad Mahdi Kamani, Farshid Farhat, Stephen Wistar, James Z. Wang
Conference Papers IEEE International Conference on Big Data. December 2016.

Abstract

Severe weather conditions cause enormous amount of damages around the globe. Bow echo patterns in radar images are associated with a number of these destructive conditions such as damaging winds, hail, thunderstorms, and tornadoes. They are detected manually by meteorologists. In this paper, we propose an automatic framework to detect these atterns with high accuracy by introducing novel skeletonization and shape matching approaches. In this framework, first we extract regions with high probability of occurring bow echo from radar images, and apply our skeletonization method to extract the skeleton of those regions. Next, we prune these skeletons using our innovative pruning scheme with fuzzy logic. Then, using our proposed shape descriptor, Skeleton Context, we can extract bow echo features from these skeletons in order to use them in shape matching algorithm and classification step. The output of classification indicates whether these regions are bow echo with over 97% accuracy.

Image Processing in Paintings using Multispectral Imaging

Mohammad Mahdi Kamani
Master Thesis Sharif University of Technology, Tehran, Iran, June 2015
Master Thesis; Mohammad Mahdi Kamani

Considering the tremendous development in imaging systems’ industry, today we canafford to have imaging equipment, capable of taking multispectral images in very highresolution. One of the remarkable benefits of this technology is in the realm of artsand particularly in museums. Taking advantage of the potentials of multispectral, high-quality imaging, curators will be able to probe their priceless works of art ( e.g. paintings) without putting them in danger through invasive research. Besides, one can investigateand control the transformation of these works through time by using this new imagingmethod.

Recently, Multispectral Imaging of paintings, in different frequency bands from approx-imately 300 nm to 1000 nm, has been proposed and used in some museums. Since theseimages are taken with different filters from visible light to infra-red, one might expectthat they contain some data beyond what is seen in visible light images. So these imagescontain data from beneath layers of the paintings, which can be compared with the RGBimage and result in extracting early sketches of the painter which are the basis of thosepaintings. In this project the ultimate goal is to find and extract those regions from mul-tispectral bands that cannot be seen in the RGB image. We use statistical methods andimage processing tools in order to extract those hidden objects automatically by computer.

The process will start with using a statistical tool known as canonical correlation analysisto find a projection which uncorrelates the frequency bands from 3 RGB bands. Thenwe can use canny edge detector to find edges in the resulting image bands from previoussection and in the RGB file. After that we can implement some morphological opera-tions to reduce redundant edges that represent data which can also be found in the RGBfile, or some noisy edges. At the end we implement an algorithm to find edges that canbe linked together to represent a larger object and connect them using active contours.Results show that this approach can be helpful in finding hidden layers of the paintingswhich is a stepping stone to find the method of painters in their paintings.

Skeleton matching with applications in Severe Weather Detection (Under Review)

Mohammad Mahdi Kamani, Farshid Farhat, Stephen Wistar, James Z. Wang
Journal Paper Journal of Applied Soft Computing, Elsevier, 2016.

Abstract

Severe weather conditions cause enormous amount of damages around the globe. Bow echo patterns in radar images are associated with a number of these destructive conditions such as damaging winds, hail, thunderstorms, and tornadoes. They are detected manually by meteorologists. In this paper, we propose an automatic framework to detect these atterns with high accuracy by introducing novel skeletonization and shape matching approaches. In this framework, first we extract regions with high probability of occurring bow echo from radar images, and apply our skeletonization method to extract the skeleton of those regions. Next, we prune these skeletons using our innovative pruning scheme with fuzzy logic. Then, using our proposed shape descriptor, Skeleton Context, we can extract bow echo features from these skeletons in order to use them in shape matching algorithm and classification step. The output of classification indicates whether these regions are bow echo with over 97% accuracy.

  • ShapeMatching, Kamani

    Severe Weather Forecasting

    NSF Research Project on weather forecasting using radar images

    In this project we use radar images and apply a novel shape matching technique, along with machine learning algorithms, in order to detect bow echo patterns, which are associated with severe weather conditions.

    The ultimate goal is to forecast these bow echo patterns beforehand, so we can alert people about upcoming severe weather incident.

  • CulturalHeritage Mohammad Mahdi Kamani

    Image Processing in Cultural Heritage

    using Image Processing techniques for investigating Cultural Heritage

    This project was my M.Sc. thesis under supervision of prof. Marvasti and prof. Amini at Sharif University of Technology. The exact name of thesis is: “Image Processing in paintings using Multispectral imaging.”

    Developing of imaging instruments and technology, today capturing very high spatial resolution and multiband images is feasible. One of the greatest application of these high resolution, multiband images is in Cultural Heritage. Curators with using these images can investigate their antiquities without invasion of these priceless heritage. In this project, we have multiband images from works of some of greatest painters in Europe such as Monet. The goal of this project is that we design a system which can compare differences in frequency layers automatically.

  • Fuzzy Speech Recognition Mohammad Mahdi Kamani

    Fuzzy Speech Recognition

    Using new approach in Speech Recognition by means of Fuzzy logic.

    p>This project was my B.Sc. thesis in partnership with Karen Khatami under supervision of Prof. Saeed Bagheri Shouraki a professor at the Electrical Engineering Department of Sharif University.

    The exact name of thesis was: Comparison between FEMM and HMM algorithms on Speech Recognition in noisy environments.

    Nowadays Speech Recognition is one of the most important applications in technology. One of algorithms which is widely used in this area is HMM (Hidden Markov Model). HMM is highly sensitive to noise. The Computer Engineering Department at Sharif University invented a new approach to speech recognition based on Fuzzy Logic named FEMM (Fuzzy Elastic Matching Machine). In this project we compared these two methods in noisy environments; the results revealed that FEMM is more immune to noise than HMM.

  • BI Mohammad Mahdi Kamani

    Business Intelligence

    Turning raw data into knowledge

    Living in the internet era, nowadays companies make huge amounts of data without extracting comparable information out of them. Business Intelligence is a new approach to deal with the big amount of data. Making Decisions easier, faster and more efficiently are the ultimate goals of BI.

    Tadbir Pardaz computer group is supporting lots of Brokerages, Securities and Mutual Funds in Iran’s capital market. We decided to implement BI on mutual funds for the first time in Iran and our goal is to implement BI in the whole capital market of Iran.

NearuKamani

Nearu Kamani

Sport

  • Present 2012

    NEARU Martial Arts

    I have been training in a kind of martial arts called NEARU, since 2012.

    Goals of NEARU:
    • Increases physical fitness & self confidence
    • Achieves harmony of body & mind
    • Teaches defence of body & mind
    • Enables one to reach Inner peace & unleash the inner power of the individual's soul
    • Teaches the art of breathing which has long been forgotten due to the modern way of life
    My current level: Purple Beltimage
    See it live
image

Music

  • Present 2009

    Violin

    I love classical music and I have been playing the violin since 2009. Music, in particular classical music, makes me relaxed and calm.

    My violin class is in Pars School of Music with a talented musician named Hamed Kermani who is a member of Tehran Symphony Orchestra.

    I am also passionate about the Piano and Oboe.

Contact

You can contact me whenever you want through these ways.

At My Lab

You can find me at Intelligent Information Systems Laboratory located at PennState University in IST Building

I am at IST 310 every day from 7:00 until 2:00 pm