MATLAB DIP IEEE Based Project Guidance in Pune for ME & BE.

CONTACT: 9764259156

Some latest IEEE 2013 , 2014 DIP MATLAB  projects for this month are listed below:

More projects will be added to this list

1. Audio Forensic marking technology using DWT-SVD

2. Non-blind Watermarking scheme for color images

in RGB space using DWT-SVD

3. Efficient Compression of Encrypted Grayscale Images using Slepian-Wolf coding.

4. Removal of High Density Salt and Pepper Noise

Through Modified Decision Based Unsymmetric

Trimmed Median Filter

5. Adaptive MMSE Rake Receiver for WCDMA

6. DWDM Effects of Single Model Optical Fiber in Radio over Fiber System

7. Convolutional Codes in Two-Way Relay Networks with Physical-Layer Network Coding

8. Cooperative and Constrained MIMO Communications in Wireless Ad Hoc/Sensor Networks

9. Efficiency of the LDPC Codes in the Reduction

of PAPR in Comparison to Turbo Codes and

Concatenated Turbo-Reed Solomon Codes in a

MIMO-OFDM System

10. New low complexity DCT based video compression method

11. Enhancement of Color Images by Scaling the Coefficients DCT 

12. Performance Assessment of OFDM-based and

OWDM-based Radio-over-Fiber Systems in the

Presence of Phase Noise

13. BER of Adaptive Arrays in AWGN Channel

14. Bi-2DPCA: A Fast Face Coding Method for

Recognition

15. Neural Network-Based Face Detection

16. Novel Speech Signal Processing Algorithms for

High-Accuracy Classification of Parkinson’s Disease

17. On Convolution Model for Ultrasound Echo Signal Processing (*provided samples are available)

18. Automatic Segmentation of Digital Images Applied in Cardiac Medical Images

19. A Novel Haar Wavelet-Based BPSK OFDM System

Robust to Spectral Null Channels and with Reduced

PAPR

20. Diversity Gain for MIMO Neyman–Pearson

Signal Detection

Detail Synopsis for MATLAB Projects are as below:

Novel Speech Signal Processing Algorithms for

High-Accuracy Classification of Parkinson’s Disease

There has been considerable recent research into theconnection between Parkinson’s disease (PD) and speech impairment.Recently, awide range of speech signal processing algorithms(dysphonia measures) aiming to predict PD symptom severity usingspeech signals have been introduced. In this paper, we test howaccurately these novel algorithms can be used to discriminate PDsubjects fromhealthy controls. In total, we compute 132 dysphoniameasures fromsustained vowels. Then,we select four parsimonioussubsets of these dysphonia measures using four feature selectionalgorithms, and map these feature subsets to a binary classification

response using two statistical classifiers: random forests andsupport vector machines.We use an existing database consisting of263 samples from 43 subjects, and demonstrate that these new dysphoniameasures can outperform state-of-the-art results, reachingalmost 99% overall classification accuracy using only ten dysphoniafeatures.We find that some of the recently proposed dysphoniameasures complement existing algorithms in maximizing the abilityof the classifiers to discriminate healthy controls from PD subjects.We see these results as an important step toward noninvasivediagnostic decision support in PD.

NEUROLOGICAL disorders affect people’s lives at an epidemicrate worldwide. Parkinson’s disease (PD) is oneof the most common neurodegenerative disorders with an incidencerate of approximately 20/100 000 and a prevalence rate exceeding 100/100 000. Moreover, these statisticsmight underestimate the problem because PD diagnosis is complicated. Given that age is the single most importantfactor for PD and the fact that the population is growingolder, these figures could further increase in the not too distant future.

Software: MATLAB 2010a