The texture is the surface property that contains the repetition of patterns. One iteration of a pattern is called the texel. The regularity in the texels and texel's placement defines the texture ...

Face recognition (FR) is getting a lot of attention for a good reason in the field of research and making a big impact in areas such as computer vision and human-computer interaction. This paper proposes a FR model based on the windowing technique using discrete cosine transform (DCT), average covariance and artificial neural network (ANN). The windowing technique is used to divide the whole image into 4 × 4, 8 × 8 and 16 × 16 size of windows. The DCT is applied to each window to acquire DCT coefficients. The average covariance is calculated for the obtained DCT coefficient matrix. The calculation of an average covariance decreases the original size of the image by around 97%. The network is created, trained and tested to assess the performance of the network using nine standard face databases. Experimental results indicate that the proposed model achieves a higher recognition rate with a reduced number of features and computational intricacy compared with conventional methods.

Bank check processing is an important application of document analysis and recognition. Recognising the literal amounts from the check images is challenging and an open research problem. In this paper, we present our work on Arabic bank check literal amounts' sub-word recognition using four sets of features and three classifiers namely: support vector machine (SVM), neural network (NN), and decision tree forest (DTF) classifiers. In addition, we investigated two different approaches for classifier fusion. We tested our system on the CENPARMI database of Arabic bank check images. Our recognition results outperform previous published results on the same database.

In the past few years, face recognition based on sparse representation is providing satisfactory classification accuracy. Face images involved in real life applications usually exhibit considerable pose, lighting, and expression variations, resulting in significant performance degradation of traditional sparse-based algorithms. In this paper, a novel face recognition method is developed as multi-level sparse (MLS) classifier with multi-modal feature extraction, which integrates benefits of sparse representation manifolds. In MLS classifier, sparse representation-based classification is performed at multiple levels to extract the hierarchical relationship information between training and testing images, which not only improves classification accuracy but also makes the system scalable. Also, the use of multi-modal feature in MLS classifier makes it discriminative to face changes while robust to intra-personal variations. To highlight the competency of proposed method, results are compared with sparse representation and other existing state-of-art methods in terms of mean classification error. An investigation on classification accuracy is performed to showcase the reliability of proposed method.

In this paper we propose two algorithms for assessing skill of soccer players. We introduce an adaptation of the Elo rating algorithm, which is widely used in chess, to handle teams. A different approach is proposed to assess player skill as a function of the proportion of matches won. Since it is hard to measure skill directly, to estimate the performance of our approach we propose as a proxy the number of correctly predicted match outcomes of a classifier that takes as input our algorithms' output. Numerical experiments suggest that our approach is competitive with book-keeper's estimates, even though we rely only on historical game outcome data.

In the past few years, face recognition based on sparse representation is providing satisfactory classification accuracy. Face images involved in real life applications usually exhibit considerable pose, lighting, and expression variations, resulting in significant performance degradation of traditional sparse-based algorithms. In this paper, a novel face recognition method is developed as multi-level sparse (MLS) classifier with multi-modal feature extraction, which integrates benefits of sparse representation manifolds. In MLS classifier, sparse representation-based classification is performed at multiple levels to extract the hierarchical relationship information between training and testing images, which not only improves classification accuracy but also makes the system scalable. Also, the use of multi-modal feature in MLS classifier makes it discriminative to face changes while robust to intra-personal variations. To highlight the competency of proposed method, results are compared with sparse representation and other existing state-of-art methods in terms of mean classification error. An investigation on classification accuracy is performed to showcase the reliability of proposed method.

This paper implements a colour and shape-based Zebra crossings detection model. As Zebra crossings are white coloured, a robust binarisation based on the V channel of the input image is used to find the large rectangle sized white stripes of Zebra crossing. After the morphological open operation, boundary tracing is done using Moore-neighbourhood tracing algorithm along with Jacob's stopping criterion. For every region, the bounding quadrilateral with the minimum area is computed and the candidate regions are then filtered out using some criteria, e.g., aspect ratio. The y-coordinates of the lower vertices of the white stripes are considered as 'cluster' and the optimal number of clusters is determined using the Calinski-Harabasz criterion. These clusters are now checked to determine whether they represent crosswalks and then validate using projective invariant. Various Zebra crossing images are used to test the proposed framework and the results are presented to prove its effectiveness.

A new illumination normalisation scheme based on reflectance ratio (RR) and contrast stretching (CS), feature extraction by integer wavelet transform (IWT) in fisher subspace for face recognition is proposed in this paper. RR is ratio of pixel intensity to average pixel intensity of its neighbourhood that discards illumination effects which is followed by CS to obtain further illuminated normalised images. Robust feature extraction is acquired by selecting low frequency coefficients and ignoring high frequency coefficients using IWT which makes proposed scheme computationally efficient. Illumination normalised feature extraction by combination of RR-CS and IWT model is followed by fisher linear discriminant analysis (FLDA) to achieve robust feature vector that provides best projection direction of training and test data sets. The recognition accuracy of 100% on CMU-PIE, Yale B and 99.05% (average) on extended Yale B face databases along with comparison with state of art methods proved strength of proposed model.

Intensity-hue-saturation (IHS) method is an exceptional mixing moving towards with computational capability and spatial classification holding. An isolated identifying picture blend count in light of HIS change and neighbourhood grouping and its interaction with little computational flightiness are projected. Visual impact and total examination happens as expected demonstrate that the proposed crucial estimation out plays out the standard picture mix procedures in the spectre space with the spatial excellence like that of un-obliterated wavelet change related course of action. The proposed changed procedure can secure the relative spatial assurance of the solidified picture with the IHS-related blend computation and the improved spooky excellence. In this paper, we develop our past results for picture mix estimations by including the strategies to satellite images against night vision and single-metric biomedical picture blend examination. Multispectral outlines consolidate satellite descriptions for arrive cover examination. In this manuscript, we explored grouping of estimations which are used to assess the execution of the entwined picture things. In this manuscript we assemble the distinctive estimations into multiple categories and show a utilisation of the estimations to satellite descriptions with an entropy-dependant picture mix technique.

Cardiovascular abnormalities have become one of the most dangerous diseases. They affect people around the entire world and some countries are more concerned by this illness. In this paper, a new methodological approach dedicated to analyse and delineate the short-axis cardiac MRI of the left ventricle (LV) is presented. In this case, thresholding and morphological operation, active contours model and region growing are combined to extract endocardial exactly. The systole volume (VTS), diastole volume (VTD) and ejection volume (EV) are then successively calculated to predict the cardiovascular diseases. The results are validated by a database (Cousty et al., 2010) where the expert manual contouring was available and the similarity index (Jaccard index) between the proposed method and expert segmentations are calculated. After discussion, we conclude that the presented method leads to satisfying results end-diastolic endocardium (0.92) and end-systolic endocardium (0.88), achieving both fast calculation and accuracy objectives.