Although contrast is a major issue in overall quality assessment of an image, existing contrast evaluators with a reasonable performance are currently scarce. Here, we propose a learning-based blind/no-reference (NR) image quality assessment (IQA) model, a dubbed histogram eigen-feature-based contrast score (HEFCS) for evaluating image contrast. This research seeks for the inter-relationship between contrast degradation and relevant image histogram features. We introduce “eigen-histograms,” which are the eigenvectors of the set of image patches' histograms. We found that the randomness of image eigen-histograms and the amplitude of corresponding eigenvalues can reliably reflect the changes in image contrast. Employing these characteristics leads to contrast-aware HEF vectors, which are used to compute the contrast score through a prediction model trained using support vector regression. Extensive analysis and cross validation are performed with five contrast relevant image databases, and the HEFCS performance results are compared with a collection of full-reference (FR), reduced-reference (RR), and NR measures. Despite its simplicity and low computational complexity, the HEFCS performs better than all competing NR-IQA models and also stands among the three best performers of FR and RR models.

This paper presents a novel image zooming method using a neural network. The main issue in any image zooming algorithms is to preserve the main structure of the image. The proposed method uses a multi-layer perceptron for image zooming. For zooming an image, the neural network is initially trained using the same image down-sampled by a factor of 2. In training the network, individual pixels along with their neighborhoods from the down-sampled image and the corresponding pixels in a 2 × 2 block from the original image are used as the input and output data, respectively. The trained neural network is then used to enlarge the original image by a factor of 2. The obtained image can be re-applied to the neural network for further enlarging. The blurring and staircase effects are faint in the zoomed image, and the edges are preserved. Besides, the proposed method is simple and easy to implement. The evaluation results on different images show that the proposed method is more efficient than other recently developed image zooming methods, particularly for high magnification factors.

Vehicle make and model recognition (VMMR) has become an important part of intelligent transportation systems. VMMR can be useful when license plate recognition is not feasible or fake number plates are used. VMMR is a hard, fine-grained classification problem, due to the large number of classes, substantial inner-class, and small inter-class distance. A novel cascaded part-based system has been proposed in this paper for VMMR. This system uses latent support vector machine formulation for automatically finding the discriminative parts of each vehicle category. At the same time, it learns a part-based model for each category. Our approach employs a new training procedure, a novel greedy parts localization, and a practical multi-class data mining algorithm. In order to speed up the system processing time, a novel cascading scheme has been proposed. This cascading scheme applies classifiers to the input image in a sequential manner, based on the two proposed criteria: confidence and frequency. The cascaded system can run up to 80% faster with analogous accuracy in comparison with the non-cascaded system. The extensive experiments on our data set and the CompCars data set indicate the outstanding performance of our approach. The proposed approach achieves an average accuracy of 97.01% on our challenging data set and an average accuracy of 95.55% on CompCars data set.

Fine‐grained recognition is a challenge that the computer vision community faces nowadays. The main category of the object is known in this problem and the goal is to determine the subcategory or fine‐grained category. Vehicle make and model recognition (VMMR) is a hard fine‐grained classification problem, due to the large number of classes, substantial inner‐class and small inter‐class distance. In this study, a novel approach has been proposed for VMMR based on latent SVM formulation. This approach automatically finds a set of discriminative parts in each class of vehicles by employing a novel greedy parts localisation algorithm, while learning a model per class using both features extracted from these parts and the spatial relationship between them. An effective and practical multi‐class data mining method is proposed to filter out hard negative samples in the training procedure. Employing these trained individual models together, the authors’ system can classify vehicles make and model with a high accuracy. For evaluation purposes, a new dataset including more than 5000 vehicles of 28 different makes and models has been collected and fully annotated. The experimental results on this dataset and the CompCars dataset indicate the outstanding performance of the authors’ approach.

Gender classification is one of the most challenging problems in computer vision. Facial gender detection of neonates and children is also known as a highly demanding issue for human observers. This study proposes a novel gender classification method using frontal facial images of people. The proposed approach employs principal component analysis (PCA) and fuzzy clustering technique, respectively, for feature extraction and classification steps. In other words, PCA is applied to extract the most appropriate features from images as well as reducing the dimensionality of data. The extracted features are then used to assign the new images to appropriate classes – male or female – based on fuzzy clustering. The computational time and accuracy of the proposed method are examined together and the prominence of the proposed approach compared to most of the other well‐known competing methods is proved, especially for younger faces. Experimental results indicate the considerable classification accuracies which have been acquired for FG‐Net, Stanford and FERET databases. Meanwhile, since the proposed algorithm is relatively straightforward, its computational time is reasonable and often less than the other state‐of‐the‐art gender classification methods.

Several approaches have been introduced in literature for active noise control (ANC) systems. Since FxLMS algorithm appears to be the best choice as a controller filter, researchers tend to improve performance of ANC systems by enhancing and modifying this algorithm. This paper proposes a new version of FxLMS algorithm. In many ANC applications an online secondary path modelling method using a white noise as a training signal is required to ensure convergence of the system. This paper also proposes a new approach for online secondary path modelling in feedfoward ANC systems. The proposed algorithm stops injection of the white noise at the optimum point and reactivate the injection during the operation, if needed, to maintain performance of the system. Benefiting new version of FxLMS algorithm and not continually injection of white noise makes the system more desirable and improves the noise attenuation performance. Comparative simulation results indicate effectiveness of the proposed approach.

This paper presents an approach for improving the performance of the SVD-based technique enhancing the time-frequency representation of signals previously introduced by the author. The improvement is achieved by two adjustments on the original method. First, the time-frequency representation of the signal is divided into signal subspace and noise subspace using singular values of the matrix as a criterion for space division. Since singular vectors are the span bases of the matrix, reducing the effect of the noise on the singular vectors and using them in reproducing the matrix enhances the information embedded in the time-frequency representation of the signal. The proposed approach utilizes the Savitzkey-Golay low-pass filter for noise attenuation from the singular vectors. This smoothing filter keeps the structure of the existing patterns in the time-frequency representation of the signal as the second improvement.

The paper presents a new method for detecting EEG spikes. The method is based on the time-frequency distribution of the signal. As spikes are short time broadband events, they are represented as ridges in the time-frequency domain. In this domain, the high instantaneous energy of spikes allows them to be distinguishable from the background. To detect spikes, the time-frequency distribution of the signal of interest is first enhanced to attenuate the noise. Two frequency slices of the enhanced time-frequency distribution are then extracted and subjected to the smoothed nonlinear energy operator (SNEO). Finally, the output of the SNEO is thresholded to localise the position of the spikes in the signal. The SNEO is employed to accentuate the spike signature in the extracted frequency slices. A spike is considered to exist in the time domain signal if a signature of the spike is detected at the same position in both frequency slices.

This paper investigates the performance of four nonparametric newborn EEG seizure detection methods. The authors recently proposed a time-frequency (TF) based technique suitable for nonstationarity of EEG signal. This method attempts to detect seizure activities through analysing the interspike intervals of the EEG in the TF domain. The performance of this method is compared to those of three nonparametric techniques for seizure detection. These methods are: autocorrelation, spectrum and singular spectrum analysis (SSA). The autocorrelation method performs analysis in the time domain and is based on the autocorrelation function of short epochs of EEG data. The spectrum technique is based on spectral analysis and is used to detect periodic discharges. The SSA technique employs singular spectrum analysis and information theoretic-based selection of the signal subspace. These three methods are based on the assumption that newborn EEG signal is quasi-stationary. The obtained results show the superior performance of the TF-based technique for detecting newborn EEG seizures.