Multi-scale local pattern co-occurrence matrix for textural image classification

Textural image classification technologies have been extensively explored and widely applied in many areas. It is advantageous to combine both the occurrence and spatial distribution of local patterns to describe a texture. However, most existing state-of-the-art approaches for textural image classification only employ the occurrence histogram of local patterns to describe textures, without considering their co-occurrence information. And they are usually very time-consuming because of the vector quantization involved. Moreover, those feature extraction paradigms are implemented at a single scale. In this paper we propose a novel multi-scale local pattern co-occurrence matrix (MS_LPCM) descriptor to characterize textural images through four major steps. Firstly, Gaussian filtering pyramid preprocessing is employed to obtain multi-scale images; secondly, a local binary pattern (LBP) operator is applied on each textural image to create a LBP image; thirdly, the gray-level co-occurrence matrix (GLCM) is utilized to extract local pattern co-occurrence matrix (LPCM) from LBP images as the features; finally, all LPCM features from the same textural image at different scales are concatenated as the final feature vectors for classification. The experimental results on three benchmark databases in this study have shown a higher classification accuracy and lower computing cost as compared with other state-of-the-art algorithms.

Experimental comparison of approaches for feature extraction of facial attributes

In this paper, we compare the effectiveness of widely used approaches for representation of facial features in face images. Feature extraction is performed on face images for representation of four facial attributes, namely gender, age, race, and expression, by using discrete wavelet transform (DWT), Gabor wavelet, scale-invariant feature transform, local binary pattern (LBP), and Eigenfaces. After feature extraction and dimension reduction, demographic and expression classification is performed to identify the most discriminating techniques for representation of facial features. Extensive experiments are performed using publicly available face databases, namely Yale, Face95 Essex, and Cohn-Kanade (CK+) databases. Experimental results show that DWT, LBP, and Gabor wavelet methods are robust to variations of illumination, facial expression, and geometric transformations. Experimental results also show that race and expression are more difficult to predict than gender and age.

Intelligent facial emotion recognition using a layered encoding cascade optimization model

In this research, we propose a facial expression recognition system with a layered encoding cascade optimization model. Since generating an effective facial representation is a vital step to the success of facial emotion recognition, a modified Local Gabor Binary Pattern operator is first employed to derive a refined initial face representation and we then propose two evolutionary algorithms for feature optimization including (i) direct similarity and (ii) Pareto-based feature selection, under the layered cascade model. The direct similarity feature selection considers characteristics within the same emotion category that give the minimum within-class variation while the Pareto-based feature optimization focuses on features that best represent each expression category and at the same time provide the most distinctions to other expressions. Both a neural network and an ensemble classifier with weighted majority vote are implemented for the recognition of seven expressions based on the selected optimized features. The ensemble model also automatically updates itself with the most recent concepts in the data. Evaluated with the Cohn-Kanade database, our system achieves the best accuracies when the ensemble classifier is applied, and outperforms other research reported in the literature with 96.8% for direct similarity based optimization and 97.4% for the Pareto-based feature selection. Cross-database evaluation with frontal images from the MMI database has also been conducted to further prove system efficiency where it achieves 97.5% for Pareto-based approach and 90.7% for direct similarity-based feature selection and outperforms related research for MMI. When evaluated with 90° side-view images extracted from the videos of the MMI database, the system achieves superior performances with >80% accuracies for both optimization algorithms. Experiments with other weighting and meta-learning combination methods for the construction of ensembles are also explored with our proposed ensemble showing great adpativity to new test data stream for cross-database evaluation. In future work, we aim to incorporate other filtering techniques and evolutionary algorithms into the optimization models to further enhance the recognition performance.

Sparse representation with multi-manifold analysis for texture classification from few training images

Texture classification is one of the most important tasks in computer vision field and it has been extensively investigated in the last several decades. Previous texture classification methods mainly used the template matching based methods such as Support Vector Machine and k-Nearest-Neighbour for classification. Given enough training images the state-of-the-art texture classification methods could achieve very high classification accuracies on some benchmark databases. However, when the number of training images is limited, which usually happens in real-world applications because of the high cost of obtaining labelled data, the classification accuracies of those state-of-the-art methods would deteriorate due to the overfitting effect. In this paper we aim to develop a novel framework that could correctly classify textural images with only a small number of training images. By taking into account the repetition and sparsity property of textures we propose a sparse representation based multi-manifold analysis framework for texture classification from few training images. A set of new training samples are generated from each training image by a scale and spatial pyramid, and then the training samples belonging to each class are modelled by a manifold based on sparse representation. We learn a dictionary of sparse representation and a projection matrix for each class and classify the test images based on the projected reconstruction errors. The framework provides a more compact model than the template matching based texture classification methods, and mitigates the overfitting effect. Experimental results show that the proposed method could achieve reasonably high generalization capability even with as few as 3 training images, and significantly outperforms the state-of-the-art texture classification approaches on three benchmark datasets. © 2014 Elsevier B.V. All rights reserved.

Capitanian (late Guadalupian, permian) global brachiopod palaeobigeography and latitudinal diversity pattern

A global database containing 3365 occurrences, 821 species and 251 genera of the Capitanian (Late Guadalupian, Permian) brachiopod faunas from 24 stations has been analyzed by cluster analysis using the Jaccard and Otsuka coefficients and the probabilistic index of similarity, nonmetric multidimensional scaling and minimum spanning tree. Two supergroups, three groups and six subgroups are revealed and interpreted as representing, respectively, two biotic realms (the Palaeoequatorial and Gondwanan Realms), two regions and six provinces. An additional realm (the Boreal Realm), based on the fauna from Spitsbergen, also appears recognizable although it also shows considerable similarities with southwestern North America and the northern margin of Gondwana as revealed by the statistical analysis. The Palaeoequatorial Realm can be further subdivided into the North America Region and the Asian Tethyan Region. The six biotic provinces are the Cathaysian Province in the Palaeotethys and Mesotethys, the Greenland-Svalbard Province in the Arctic region, the Austrazean Province in eastern Australia and New Zealand, the Grandian Province in western North America and the two transitional zones (the Himalayan Province in the southern temperate zone and the Sino–Mongolian–Japanese Province in the northern temperate zone). Polynomial regression analysis and rarefaction analysis indicate that the generic diversities of brachiopod faunas during the Capitanian peaked in the Palaeoequatorial Cathaysian Province and the two transitional zones (Himalayan Province and Sino–Mongolian–Japanese Province), but fell dramatically in the polar regions. The generic diversity of the Palaeoequatorial Grandian Province is apparently lower than in the two transitional zones of temperate palaeolatitudes, suggesting that the generic diversity of Capitanian brachiopod faunas does not exhibit a strict negative correlation with palaeolatitudes. This in turn would suggest that biogeographical determinants (such as geographical barriers, inhabitable area and ocean currents) other than latitude-related temperature control may also have played an important role in the dispersal of some brachiopods and the characterization of some local provinces and high diversities. The Capitanian global brachiopod palaeobiogeography is generally comparable with those in the Wuchiapingian and Changhsingian, but with some notable differences. These include: (1) that the Grandian Province of the Capitanian in western North America vanished after the end-Guadalupian regression, (2) that the western Tethyan Province of the Lopingian could not be distinguished in the Capitanian, and (3) that the Austrazean Province was larger in area than either in the Wuchiapingian or in the Changhsingian.

The spatial pattern of natural selection when selection depends upon experience

Apostatic (frequency‐ or density‐dependent) selection, aposematic signals, and mate choice behavior generally require that the mean prey or potential mate density m value be high enough (above a threshold T) to result in sufficient encounter rates for the searcher to learn or retain the association between conspicuous signals and prey unprofitability, to forage apostatically, or to choose among mates. This assumes that all searchers experience , which implicitly assumes an even dispersion of targets among searcher territories. Uneven dispersion generates new phenomena. If , then only territories with local density x values that are greater than T favor experience‐based behavior, leading to spatially variable frequency‐ or density‐dependent selection intensity. As aggregation increases, the increase in percentage of targets in favorable territories ( ) is greater than the increase in the percentage of territories that are favorable. The relationship is reversed when . In both cases, because as few as 10% of the territories can contain 80% of the targets, only a few territory holders may account for most of the selection on most of the target population; accidents of experience in only a few searchers can have unexpectedly large effects on the target population. This also provides an explanation for high searcher behavior variation (personalities) : individuals from favorable territories will behave differently in behavioral experiments than those from unfavorable territories, at least with respect to similar kinds of targets. These effects will generate spatial heterogeneity in natural and sexual selection in what are otherwise uniform environments.

Knowledge discovery in multi-databases by analyzing local instances

Multi-databases mining is an urgent task. This thesis solves 4 key problems in multi-databases mining: Application-independent database classification - Local instance analysis model - Useful pattern discovery - Pattern synthesis.

Attacking anonymous web browsing at local area networks through browsing dynamics

The majority of current anonymous systems focus on improving anonymity at the network and website level in order to defend against traffic analysis attacks. However, the vulnerability of the connections between end users and the anonymous network do not attract any attention yet. For the first time, we reveal an end user browsing dynamics based attack on anonymous browsing systems at the LAN where the victim locates. This new attack method is fundamentally different from existing attack methodologies. In general, web surfers browse the web following certain patterns, such as requesting a web page, viewing it and requesting another page. The browsing pattern of a victim can be clearly observed by a local adversary when the victim is viewing the web without protection. Unfortunately, browsing dynamics releases rich information for attacking even though the web page content is encrypted. In order to show how a local eavesdropper can decipher which pages have been viewed with the knowledge of user browsing dynamics and the public information of a given website, we established a specific hidden Markov model to represent browsing dynamics for the website. By using this model, we can then identify the optimal of the accessed pages using the Viterbi algorithm. In order to confirm the effectiveness of the revealed attack method, we have conducted extensive experiments on a real data set. The results demonstrated that the attack accuracy can be more than 80%. A few possible counter-attack strategies are discussed at the end of the paper.

Local energy and pre-envelope

We observe that the local energy is the pre-envelope for analytic function. The maxima and phase of this function can be used to compute and classify visual features such as motion and stereo disparity, texture, etc. We examine the construction of new filters for computing Local Energy, and compare these filters with the Gabor filters and the three-point-filter of Venkatesh and Owens.

Association between fast food purchasing and the local food environment

Objective: In this study, an instrument was created to measure the healthy and unhealthy characteristics of food environments and investigate associations between the whole of the food environment and fast food consumption.

Design and subjects: In consultation with other academic researchers in this field, food stores were categorised to either healthy or unhealthy and weighted (between +10 and −10) by their likely contribution to healthy/unhealthy eating practices. A healthy and unhealthy food environment score (FES) was created using these weightings. Using a cross-sectional study design, multilevel multinomial regression was used to estimate the effects of the whole food environment on the fast food purchasing habits of 2547 individuals.

Results: Respondents in areas with the highest tertile of the healthy FES had a lower likelihood of purchasing fast food both infrequently and frequently compared with respondents who never purchased, however only infrequent purchasing remained significant when simultaneously modelled with the unhealthy FES (odds ratio (OR) 0.52; 95% confidence interval (CI) 0.32–0.83). Although a lower likelihood of frequent fast food purchasing was also associated with living in the highest tertile of the unhealthy FES, no association remained once the healthy FES was included in the models. In our binary models, respondents living in areas with a higher unhealthy FES than healthy FES were more likely to purchase fast food infrequently (OR 1.35; 95% CI 1.00–1.82) however no association was found for frequent purchasing.

Conclusion: Our study provides some evidence to suggest that healthier food environments may discourage fast food purchasing.

Landscapes in transition : local perceptions of indigenous and European settlement changes along the Victorian coast

Around the world coastal areas are witnessing dramatic changes due to the consequences of the growth of human settlements. Rapid urban expansion in coastal settlements due to ‘life style migration’ impacts negatively on environmental coastal amenities that are the driving factor behind the attraction of these areas. The Victorian Coast in Australia is under stress, with the growth pattern of coastal settlements in a sprawling linear fashion resulting in devastating effects on the natural coastal environment, biodiversity and the loss of cultural heritage. The Victorian coast is rich in history, and the coastal towns are often described in literature as places with ‘sense of place’, or referred to as place character. This place character has been formed over many years with the interaction between social histories and natural environments woven together across time. This paper reviews the transition of the landscapes along the Great Ocean Road coastal region, and ask the question how can a potential Generative Plan be developed to establish a process to keep the place character of coastal towns. The proposed plan considers the interrelationships of nature and people as fundamental to forming place character, from the time of Indigenous habitation before European settlement, to the current day of rapid increased developments scattered along this coast.

Political competition and environmental reporting: evidence from New Zealand local governments

Purpose - The purpose of this paper is to investigate the relationship between "political competition" and "environmental reporting" by New Zealand local governments. Design/methodology/approach - The research method includes a longitudinal analysis of environmental reporting by New Zealand local governments in their annual reports for the financial years 2005-2006 to 2009-2010. "Content analysis" was used to attach scores to the extent of environmental reporting. The "number of candidates divided by the number of available positions at the previous election" was used as the proxy for "political competition". Findings - The study reports a positive relationship between "political competition" and "environmental reporting" in 2007-2008. The number of local governments reporting voluntary environmental information increased in 2006-2007 and 2007-2008 compared to 2005-2006, followed by a reduction in such numbers following the 2007-2008 financial year. This trend in disclosure can be attributed to the local government elections in October 2007. This finding is consistent with the expectation of "agency theory" and provides insight into the pattern of perceived agency costs. The study also finds a dearth in reporting "monetary" and "bad" news. Originality/value - The study contributes towards the previous literature on environmental reporting by concentrating on the public sector and New Zealand, together with investigating the relationship of such reporting with "political competition" through a longitudinal analysis. The theoretical contribution of this study is the adoption of "agency theory" in the context of public sector voluntary reporting and investigating the significance attached by agents to environmental reporting to minimise agency cost. The practical contribution of the study is in the area of future development of reporting standards in regards to environmental reporting.

Local deformation in roll forming

In a previous paper, a simple model was developed to extend the application of the traditional flower pattern diagram as a design tool for roll forming. The position of a point on the strip as it passes through each set of rolls can be identified as a series of points in the two-dimensional flower pattern diagram. In three dimensions, these points will lie on a non-circular cylindrical surface having its axis parallel to the machine axis. Assuming that these points are joined by a smooth curve, the forming path of a point on the strip as it passes through the roll forming process can be obtained as a plane curve on the plane development of this surface. It was shown in previous work that the longitudinal membrane strain and, in certain cases, local curvature of the sheet are functions of the slope of this plane curve. In this work, the strains on both surfaces at the edge of a strip in the forming of a simple V-channel are measured using strain gauges. It is shown that near the point of contact with the rolls, the strains differ by nearly an order of magnitude from those determined from the simple model which assumes that the trajectory is a smooth curve. A modification of the forming path is obtained from the measured bending strains. Although the changes in displacement are small, the peak values of strain near the point of roll contact are large and a consequence of highly localised changes in the forming path as the strip passes over each roll. Measurement of this perturbation in the forming path is difficult as the region is obscured by the forming rolls. The technique described here permits the reconstruction of this path and identifies a new area of investigation of longitudinal strains in roll forming. These are often associated with shape defects such as bow, warping and end flare.