@article{ author = {GhaneiYakhdan, Hossei}, title = {A New Error Concealment Technique for Video Frames Using a RBF Neural Network}, abstract ={Transmission of compressed video over error prone channels may result in packet losses, which can degrade the image quality. Error concealment (EC) is an effective approach to reduce the degradation caused by the missed information. The conventional temporal EC techniques are always inefficient when the motions of the video object are irregular. In this paper, in order to overcome this problem, an efficient temporal EC approach to conceal the macroblock error for video coding systems is proposed. The proposed EC method employs a RBF neural network to estimate the motion vectors of the damaged macroblocks. RBF estimator is used only for areas of the fast motions, which reduces computation complexity. Because the neural networks have a great capacity for visualizing and interpreting high-dimensional data sets, the estimation model proposed herein can exploit the nonlinearity property of the neural networks to estimate lost motion vectors more accurately. Simulation results show that the proposed technique enhances both subjective and objective quality of reconstructed frames, such as the average PSNR increases about 1.6469 dB compared to the BMA method for the test video sequences in some frames}, Keywords = {temporal error concealment, RBF neural network, motion vector estimation, motion compensation }, volume = {10}, Number = {1}, pages = {12-3}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-95-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-95-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2013} } @article{ author = {}, title = {New fast pre training method for deep neural network learning}, abstract ={In this paper, we propose efficient method for pre-training of deep bottleneck neural network (DBNN). Pre-training is used for initial value of network weights convergence of DBNN is difficult because of different local minimums. While with efficient initial value for network weights can avoided some local minimums. This method divides DBNN to multi single hidden layer and adjusts them, then weighs of these networks is used for initial value of DBNN weights and then train network. Proposed network is used for extraction of face component. This Method is implemented on Bosphorus database. Comparing results shows that new method has more convergence speed and generalization than random initial value. By means of this new training method and with same training error rate pixel reconstruction error is decreased 13.69% and recognition rate is increased 10%}, Keywords = {Deep Architecture, Learning Convergence,Neural Network, Pre-training, Components }, volume = {10}, Number = {1}, pages = {26-13}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-112-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-112-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2013} } @article{ author = {Shekofteh, Yasser and Almasganj, Farsh}, title = {Performance Improvement of Continuous Speech Recognition System Using Extracted Features of Speech Manifolds in the Reconstructed Phase Space}, abstract ={The design for new feature extraction methods out of the speech signal and combination of their obtained information is one of the most effective approaches to improve the performance of automatic speech recognition (ASR) system. Recent researches have been shown that the speech signal contains nonlinear and chaotic properties, but the effects of these properties are not used in the continuous ASR systems. Reconstructed phase space (RPS) is an appropriate domain to exhibit nonlinear properties of a chaotic signal. Therefore, in this paper a new method is proposed to utilize the RPS-based features (LLRPS). These features will be computed using similarity scores between the embedded speech signal in the RPS and a set of predefined phoneme manifolds. Then, TMLP-based neural network estimates phoneme posterior probability over the LLRPS features. The used neural network includes proper properties such as extracting dynamic information and output combination methods. Experimental results using Farsdat speech database show that nonlinear combination of the speech recognition outputs including traditional MFCC features and the LLRPS features, leading to improvement of 3.94% and 4.02% in the accuracy of frame and phoneme recognition, respectively.}, Keywords = {Continuous speech recognition, Feature extraction, Reconstructed phase space, Phoneme manifolds, Likelihood Score, Neural network}, volume = {10}, Number = {1}, pages = {42-27}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-76-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-76-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2013} } @article{ author = {}, title = {A novel method for suitable selection of watermark strength in digital image watermarking based on imperialist competitive algorithm}, abstract ={Watermarking systems have specific feathers in accordance with their applications. In many applications transparency and robustness are needed which are the most important features. These two features are in contrast to each other and are controlled by a parameter named watermark strength. With decreasing the watermark strength, transparency of the watermarking system increases while the robustness of the watermarking system decreases and vice versa. Having these two features is not possible at the same time in a watermarking system and there should be tradeoff between transparency and robustness choosing correct watermark strength. In this paper, the imperialist competitive algorithm is used for determining the watermark strength for having transparency and robustness at the same time. The simulation results show that the imperialist competitive algorithm can propose proper watermark strength for a watermarking system with less computational complexity}, Keywords = {image watermarking, discrete cosine transform, imperialist competitive algorithm }, volume = {10}, Number = {1}, pages = {56-43}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-53-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-53-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2013} } @article{ author = {Kittler, Josef}, title = {Speech Signals Processing Using New Compressive Sampling Based Feature Extraction Method}, abstract ={In this paper, we present a Compressive Sampling (CS)-based feature extraction method for audio signals. In the proposed approach, the audio signal is firstly segmented by hamming windows and the Discrete Fourier Transform (DFT) of the samples is calculated within each frame. Then, the normalized values of the DFT coefficients of each frame are accumulated. At the next step, the second DFT is applied on the vector formed from the accumulated sum in consecutive frames. Finally, considering the sparseness of the resulted vector, our proposed CS-2FFT feature vector is achieved by a random sampling. In this research, the performance of CS-2FFT feature vector has been examined in the applications of audio classification and audio source localization. The simulation show that the proposed feature vector results in a classifier which is more accurate and less computationally complex compared to the classical classifiers. Also, it is shown that the employing CS-2FFT feature vector, the localization error will be less than 2%.}, Keywords = {Feature Extraction, Compressive Sampling, Genre Classification, Sound Source Localization.}, volume = {10}, Number = {1}, pages = {68-57}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-63-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-63-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2013} } @article{ author = {Ghassemian, Hass}, title = {Multispectral and Panchromatic image fusion using Spatial PCA}, abstract ={Obtaining of an image with high spectral and spatial resolution is the goal of image fusion. The PCA is a well-known pan-sharpening approach widely used for its efficiency and high spatial resolution. However, it can distort the spectral characteristics of the multispectral images. To avoid the weak points of the standard PCA technique, Spatial PCA transform has been proposed and the reasons of superiority of this method in maintaining of the spectral information are discussed in this paper. At the end of the paper, a new assessment is proposed and the advantage of this method relative to the conventional mutual information is argued. The proposed assessment and the other popular metrics such as: ERGAS, SAM, correlation coefficient UIQI, and mutual information are used to analyze the fusion result. These assessments show that the proposed method has the least color distortions and contains more spatial information.}, Keywords = {Image Fusion, Panchromatic Image, Multispectral Images, Spatial Information, Spectral Information, Standard PCA, Spatial PCA, Wavelet, Contourlet. }, volume = {10}, Number = {1}, pages = {78-69}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-100-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-100-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2013} } @article{ author = {Kabiri, Peyman and Mohebol-Hojeh, Alirez}, title = {}, abstract ={}, Keywords = {}, volume = {10}, Number = {2}, pages = {3-20}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-80-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-80-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2014} } @article{ author = {yazdchi, mohamadreza and mahnam, ami}, title = {Designing an Experiment to Improve Automatic Emotion Detection Using EEG}, abstract ={Emotions play an important role in daily life of human, so the need and importance of automatic emotion recognition have grown with increasing role of Human Computer Interaction (HCI) applications. Since emotion recognition using EEG can show inner emotions, this method is more attention from other ways. In consideration to lack of emotion induction collection for doing such researches at Iranian culture, in this research some emotion induction experiments are designed to create four emotion states in subjects. Once subjects are experimented by International Affective Picture System (IAPS) that collected at Florida University and then they are experimented by corresponding movies with Iranian culture. Results show that corresponding movies get higher accuracy in comparison with IAPS. Fast computing, using only two electrodes and obtaining high accuracy from EEG signals are other advantages of this research}, Keywords = {Emotion recognition, EEG signal, International Affective Picture System, Fractal dimension }, volume = {10}, Number = {2}, pages = {21-34}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-83-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-83-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2014} } @article{ author = {}, title = {Development and Enhancement of an interactive Computer-Assisted Translation System for English to Persian}, abstract ={In recent years, significant improvements have been achieved in statistical machine translation (SMT), but still even the best machine translation technology is far from replacing or even competing with human translators. Another way to increase the productivity of the translation process is computer-assisted translation (CAT) system. In a CAT system, the human translator begins to type the translation of a given source text by typing each character the MT system interactively offers the choices to enhance and complete the translation. Human translator may continue typing or accept the whole completion or part of it. In this paper, we propose new approaches for increasing the performance of the interactive CAT. Our approaches are included a new search way and a hybrid back-off model. We could achieve 1.3% improvement by using our offered search approach}, Keywords = {Statistical Machine Translation (SMT), Computer-Assisted Translation (CAT), Interactive CAT, Prefix Search.}, volume = {10}, Number = {2}, pages = {35-46}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-55-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-55-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2014} } @article{ author = {}, title = {An Improvement on Robust Pattern Recognition Using Chaotic Dynamics in Attractor Recurrent Neural Network}, abstract ={In this paper, two kinds of chaotic neural networks are proposed to evaluate the efficiency of chaotic dynamics in robust pattern recognition. The First model is designed based on natural selection theory. In this model, attractor recurrent neural network, intelligently, guides the evaluation of chaotic nodes in order to obtain the best solution. In the second model, a different structure of chaotic neural network is presented which includes chaotic neurons in the hidden layer. The behavior of these neurons can be controlled by changing the parameters of chaotic neurons. Furthermore, both models are supposed to recognize the noisy patterns even those with high levels of additional noise (up to 60%). Using the first proposed model, the accuracy of recognition was improved by 37.16%, 29.15% and 8.5% comparing to feedforward neural network, chaotic neural network based on chaotic nodes - NDRAM, and ARNN respectively. The second model increased the accuracy of recognition by an average of 13.91%, and 5.41% in comparison to ARNN and first model. In addition, it has been observed that the second model had a better performance, even in point attractor mode, than ARNN which acts in non chaotic mode.}, Keywords = {Attractor Recurrent Neural Network, Chaotic Dynamics, Chaotic Neuron, Point Attractor, Robust Pattern Recognition}, volume = {10}, Number = {2}, pages = {47-67}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-145-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-145-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2014} } @article{ author = {salimibadr, armin and Homayounpour, Mohammad Mehdi}, title = {Phrase chunking in Persian texts}, abstract ={Text tokenization is the process of tokenizing text to meaningful tokens such as words, phrases, sentences, etc. Tokenization of syntactical phrases named as chunking is an important preprocessing needed in many applications such as machine translation information retrieval, text to speech, etc. In this paper chunking of Farsi texts is done using statistical and learning methods and the grammatical characteristics of Farsi texts. Many features and labeling methods are examined one by one and the best features and labeling techniques are used for the detection of syntactic phrases and their boundaries. Several machine learning techniques including Support Vector Machine and Conditional Random Fields are used as classifier in our experiments. The impact of the size of training texts on chunking performance was studied as well. Using the proposed methods in this paper, a performance of 84.02% was obtained for detection of phrase boundaries and 78.04% for detection of both phrase boundaries and phrase type}, Keywords = {Natural language processing, Phrase chunking, POS tagging, Support vector machine, Conditional random fields, Text to speech, Machine translation}, volume = {10}, Number = {2}, pages = {69-86}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-73-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-73-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2014} } @article{ author = {}, title = {FARSIARABIC TEXT DETECTION AND LOCALIZATION IN VIDEO FRAMES}, abstract ={Video text detection plays an important role in applications such as semantic-based video analysis, text information retrieval, archiving and so on. In this paper, we propose a Farsi/Arabic text detection approach. First, with an appropriate edge detector, edges are extracted and then by using edges cross ponts, artificial corners are extracted. Artificial corner histogram analysis is done for rejecting some non text corners. The discrete cosine transform (DCT) coefficients of input picture are extracted and texture intensity picture is created by combining appropriate coefficients. With combining artificial corners image and texture intensity image, a features vector is extracted and fed into support vector machine (SVM) classifier for detecting text regions. Finally with drawing normalized texture intensity profiles, final verification is done and text lines are sepersted from each others}, Keywords = {Farsi/Arabic, video sequence, text detection, artificial corner, DCT }, volume = {10}, Number = {2}, pages = {87-104}, publisher = {Research Center on Developing Advanced Technologies}, url = {http://jsdp.rcisp.ac.ir/article-1-132-en.html}, eprint = {http://jsdp.rcisp.ac.ir/article-1-132-en.pdf}, journal = {Signal and Data Processing}, issn = {2538-4201}, eissn = {2538-421X}, year = {2014} }