Biomedical Image Processing / Medical Image Processing
Saeid Shakeri; Farnaz Ghassemi; Farshad Almasganj
Volume 13, Issue 1 , April 2019, , Pages 17-30
Abstract
Noise removal is one of the most important steps in digital image processing. Cone beam computed tomography (CBCT) is increasingly utilized in maxillofacial and dental imaging. Compared to conventional CT, CBCT images have diffrent noise and artifacts due to much less applied dose and their reconstruction ...
Read More
Noise removal is one of the most important steps in digital image processing. Cone beam computed tomography (CBCT) is increasingly utilized in maxillofacial and dental imaging. Compared to conventional CT, CBCT images have diffrent noise and artifacts due to much less applied dose and their reconstruction algorithm. Therefore, the use of noise reduction techniques in these images is necessary to increase the signal-to-noise ratio. In this paper, the independent component analysis (ICA) method has been used to seperate noise from CBCT images and three different ICA algorithms, NG-FICA, ERICA and FastICA were investigated. In addition, two powerful noise reduction method, 2D discrete wavelet thresholding and optimized anisotropic diffusion filter is used to evaluate the results. Our proposed method has been validated on 12 different images in the presence of Gaussian and Spectral noise and the results are evaluated using processing time criteria, PSNR, MSE and SSIM. The results show that the ICA methods have advantage in noise reduction from CBCT images compared to the other noise reduction methods and among the three studied ICA algorithms, the NG-FICA algorithm has better performance in terms of processing time, preserving image quality and noise reduction.
Speech processing
Shahla Azizi; Farzad Towhidkhah; Farshad Almasganj
Volume 6, Issue 4 , June 2012, , Pages 257-265
Abstract
In present work, recognition of isolated word has been studied. The purpose of this research is to increase the performance of children’s speech recognizer using Vocal Tract Length Normalization. This recognition system has been created to design a speech therapy software. Recognition of correct ...
Read More
In present work, recognition of isolated word has been studied. The purpose of this research is to increase the performance of children’s speech recognizer using Vocal Tract Length Normalization. This recognition system has been created to design a speech therapy software. Recognition of correct and wrong pronunciation and help children to improve it using some feedbacks are the goals of this software. In test phase, some speech data that are related to correct and incorrect pronunciation of 47 words have been utilized. Four Baseline models have been Trained, one for children, one combined model (females and children) and two for Adults (by exploiting one Persian database). Children’s model was trained and tested with data that have been collected from 38 children (5 to 8 years old). These experiments were implemented in HTK toolkit. Poor performance was improved using VTLN. Improvement of adult’s model was more than children’s model.
Speech processing
Yaser Shekofteh; Farshad Almasganj
Volume 6, Issue 1 , June 2012, , Pages 17-33
Abstract
Recent researches show that nonlinear and chaotic behavior of the speech signal can be studied in the reconstructed phase space (RPS). Delay embedding theorem is a useful tool to study embedded speech trajectories in the RPS. Characteristics of the speech trajectories have rarely used in the practical ...
Read More
Recent researches show that nonlinear and chaotic behavior of the speech signal can be studied in the reconstructed phase space (RPS). Delay embedding theorem is a useful tool to study embedded speech trajectories in the RPS. Characteristics of the speech trajectories have rarely used in the practical speech recognition systems. Therefore, in this paper, a new feature extraction (FE) method is proposed based on parameters of vector AR (VAR) analysis over the speech trajectories. In this method, using filter and reflection matrices obtained from applying VAR analysis on static and dynamic information of the speech trajectory in the RPS, a high-dimensional feature vector can be achieved. Then, different transformation methods are utilized to attain final feature vectors with appropriate dimension. Results of discrete and continuous phoneme recognition over FARSDAT speech corpus show that the efficiency of the proposed FE method is better than other time-domain-based FE methods such as LPC and LPREF.