In the last few years analog adaptive filters have been a subject of active research because they have the ability to handle in real time much higher frequencies, with a smaller size and lower power consumption that their digital counterparts. During this time several analog adaptive filter algorithms have been reported in the literature, almost all of them use the continuous time version of the least mean square (LMS) algorithm. However the continuous time LMS algorithm presents the same limitations than its digital counterpart, when operates in noisy environments, although their convergence rate may be faster than the digital versions. This fact suggests the necessity of develop analog versions of recursive least square (RLS) algorithm, which in known to have a very low sensitivity to additive noise. However a direct implementation of the RLS in analog way would require a considerable effort. To overcome this problem, we propose an analog RLS algorithm in which the adaptive filter coefficients vector is estimated by using a fully connected network that resembles a Hopfield network. Theoretical and simulations results are given which show that the proposed and conventional RLS algorithms have quite similar convergence properties when they operate with the same sampling rate and signal-to-noise ratio.

Several recent proposals would enable us, at least theoretically, to overcome some of the limitations of transversal echo cancelers with gradient-search-based adaptation algorithms in acoustic environments. Of these, the subband echo canceler (SBEC) structure appears to be a desirable alternative because it both, reduces the computational load and speeds up convergence rates. Conventional SBECs introduce undesirable spectral gaps or aliased components, however, which degrade the echo canceler's performance. The SBEC structure we propose uses oversampling, i.e., a decimation factor smaller than the number of subbands, and complex adaptive filters. It also enables the use of large decimation factors with a relatively short delay in the sending side, keeping the local room signal undistorted. Computer simulations using actual speech signals show that by using relatively large decimation factors, in addition to reducing the computational load, convergence rates become almost independent of the statistics of the input signals.

An alaryngeal speech enhancement system is proposed to improve the intelligibility and quality of speech signals generated by an artificial larynx transducer (ALT). Proposed system identifies the voiced segments of alaryngeal speech signal, by using pattern recognition methods, and replaces these by their equivalent voiced segments of normal speech. Evaluation results show that proposed system provides a fairly good improvement of the quality and intelligibility of ALT generated speech.

This paper presents a facial expression recognition algorithm based on segmentation of a face image into four facial regions (eyes-eyebrows, forehead, mouth and nose). In order to unify the different results obtained from facial region combinations, a modal value approach that employs the most frequent decision of the classifiers is proposed. The robustness of the algorithm is also evaluated under partial occlusion, using four different types of occlusion (half left/right, eyes and mouth occlusion). The proposed method employs sub-block eigenphases algorithm that uses the phase spectrum and principal component analysis (PCA) for feature vector estimation which is fed to a support vector machine (SVM) for classification. Experimental results show that using modal value approach improves the average recognition rate achieving more than 90% and the performance can be kept high even in the case of partial occlusion by excluding occluded parts in the feature extraction process.

We present the Fuzzy Directional (FD) filter to remove impulse noise from corrupted colour images. Simulation results have shown that the restoration performance is better in comparison with other known filters.

In this letter we present an imperceptible and robust watermarking algorithm that uses a cryptographic hash function in the authentication application of digital medical imaging. In the proposed scheme we combine discrete Fourier transform (DFT) and local image masking to detect the watermark after a geometrical distortion and improve its imperceptibility. The image quality is measured by metrics currently used in digital image processing, such as VSNR, SSIM and PSNR.

A visible watermarking technique to provide copyright protection for portrait images is proposed in this paper. The proposal is focused on real-world applications where a portrait image is printed and illegitimately used for commercial purposes. It is well known that this is one of the most difficult challenges to prove ownership through current watermark techniques. We propose an original approach which avoids the deficiencies of typical watermarking methods in practical scenarios by introducing a smart process to automatically detect the most suitable region of the portrait image, where the visible watermark goes unnoticed to the naked eye of a viewer and is robust enough to remain visible when printed. The position of the watermark is determined by performing an analysis of the portrait image characteristics taking into account several conditions of their spatial information together with human visual system properties. Once the location is set, the watermark embedding process is performed adaptively by creating a contrast effect between the watermark and its background. Several experiments are performed to illustrate the proper functioning of the proposed watermark algorithm on portrait images with different characteristics, including dimensions, backgrounds, illumination and texture, with the conclusion that it can be applied in many practical situations.

A new variable step size Least Mean Square (LMS) FIR adaptive filter algorithm (VSS-CC) is proposed. In the VSS-CC algorithm the step size adjustment (α) is controlled by using the correlation between the output error (e(n)) and the adaptive filter output ((n)). At small times, e(n) and (n) are correlated which will cause a large α providing faster tracking. When the algorithm converges, the correlation will result in a small size α to yield smaller misadjustments. Computer simulations show that the proposed VSS-CC algori thm achieves a better Echo Return Loss Enhancemen (ERLE) than a conventional NLMS Algorithm. The VSS-CC algorithm was also compared with another variable step algorithm, achieving the VSS-CC a better ERLE when the additive noise is incremented.

This letter proposes a time varying step size normalized LMS (TVS-NLMS) algorithm for adaptive echo canceler structures. Proposed algorithm reduces distortion during double talk, without increasing the computational cost nor decreasing the convergence rate of the normalized LMS algorithm significantly. Simulation results using white noise and actual speech signals confirm the desirable features of the proposed scheme.

In a recent paper, we proposed a subband echo canceler (SBEC) structure that has a shorter transmission delay than conventional SBEC structures and is free of distortion due to frequency gaps or aliased components. The double-talk detector we propose in this paper, takes advantages of the subband realization form and is based on adaptive echo canceler operation even during periods of double-talk. The computationally simple structure quickly and accurately detects periods of double-talk and track variations in echo path characteristics. The extended complex LMS algorithm we also propose avoids distortion during periods of double-talk. Computer simulations using white noise and actual speech signals confirm fast tracking speed, accurate double-talk detection, and other desirable features of the proposed scheme. We evaluated the proposed hardware structure using a WE DSP32C development system. Assuming a 16 kHz sampling rate, a decimation factor of 32, and a 4000-tap echo path, we found 4 DSP chips to be sufficient to implement the proposed scheme. Results of our experiments show almost the same convergence performance as that obtained in computer simulation.

This letter propose a fast frequency domain adaptive filter algorithm (FADF) for applications in which large order adaptive filters are required. Proposed FADF algorithm reduces the block delay of conventional FADF algorithms allowing a more efficient selection of the fast Fourier Transform (FFT) size. Proposed FADF algorithm also provides faster convergence rates than conventional FBAF algorithms by using a near-optimum convergence factor derived by using the FFT. Computer simulations using white and colored signals are given to show the desirable features of proposed scheme.