International Journal of Pattern Recognition and Artificial Intelligence

In the past three decades nature-inspired and meta-heuristic algorithms have dominated the literature in the broad areas of search and optimization. Harmony search algorithm (HSA) is a music-inspired population-based meta-heuristic search and optimization algorithm. The concept behind the algorithm is to find a perfect state of harmony determined by aesthetic estimation. This paper starts with an overview of the harmonic phenomenon in music and music improvisation used by musicians and how it is applied to the optimization problem. The concept of harmony memory and its mathematical implementation are introduced. A review of HSA and its variants is presented. Guidelines from the literature on the choice of parameters used in HSA for effective solution of optimization problems are summarized.

The paper proposes a fault diagnosis model based on the HIWO–SVM algorithm given the fact that the basic support vector machines (SVM) cannot solve effectively the problem of fault diagnosis in analog circuit. First of all, the wavelet package technique is adopted for extracting the information of the faults from the test points in the analog circuit. The differential evolution (DE) algorithm is then integrated with the purpose of improving the performance of the basic IWO algorithm, i.e. a hybrid IWO (HIWO) algorithm. The HIWO algorithm is further used to optimize the parameters of SVM in order to avoid the randomness of the parameter selection, thereby improving the diagnosis precision and robustness. The experimental results on a filter circuit show that the method is more effective and reliable than the other methods for fault diagnosis.

As one of the most popular data reduction category for large scale data mining, simple random sampling (SRS) often leads to the loss of small clusters when dealing with unevenly distributed datasets. A density biased sampling algorithm based on grid can avoid the problem. However, the grid division granularity has an influence on the efficiency and effectiveness of the algorithm. To overcome the drawback, a variable grid density biased sampling is proposed to deal with large scale unevenly distributed datasets. However, the efficiency is restricted by dimensionality. Aiming at this, an efficient density biased sampling algorithm is proposed for large high-dimensional datasets. Firstly, an efficient feature selection method is designed to obtain the feature subsets. Secondly, the variable grid division is executed in the selected feature subsets. Finally, the sample is obtained from the grid space. Synthetic datasets and UCI datasets, tested in our experiments, reveal that the proposed algorithm can achieve higher quality than SRS. Meanwhile, the proposed algorithm consumes less sampling time comparing with density biased sampling algorithm based on grid and density biased sampling algorithm based on variable grid division.

A new classifier for image data classification named as linear twin bounded support tensor machine (linear TBSTM) is proposed by adding regularization terms in objective functions, which results in the realization of structural risk minimization avoids of the singularity of matrices. We know that up to now nonlinear classifiers based on STM for image data classification are not seen more. In order to remedy this limitation, a new matrix kernel function is introduced and based on which the nonlinear version of TBSTM is studied with a detailed theoretical derivation, and then a nonlinear classifier called as nonlinear TBSTM is suggested. In order to examine the effectiveness of the proposed classifiers, a series of comparative experiments with three linear classifiers STM, TSTM and PSTM are performed on 15 binary image classification problems taken from ORL, YALE and AR datasets. Experiment results show that the proposed classifiers are effective and efficient.

Classification is an important field in machine learning and pattern recognition. Amongst various types of classifiers such as nearest neighbor, neural network and Bayesian classifiers, support vector machine (SVM) is known as a very powerful classifier.

One of the advantages of SVM in comparison with the other methods, is its efficient and adjustable generalization capability. The performance of SVM classifier depends on its parameters, specially regularization parameter C, that is usually selected by cross-validation. Despite its generalization, SVM suffers from some limitations such as its considerable low speed training phase. Cross-validation is a very time consuming part of training phase, because for any candidate value of the parameter C, the entire process of training and validating must be repeated completely.

In this paper, we propose a novel approach for early stopping of the SVM learning algorithm. The proposed early stopping occurs by integrating the validation part into the optimization part of the SVM training without losing any generality or degrading performance of the classifier. Moreover, this method can be considered in conjunction with the other available accelerator methods since there is not any dependency between our proposed method and the other accelerator ones, thus no redundancy will happen. Our method was tested and verified on various UCI repository datasets and the results indicate that this method speeds up the learning phase of SVM without losing any generality or affecting the final model of classifier.

Techniques to identify printed and handwritten text in scanned documents differ significantly. In this paper, we address the question of how to discriminate between each type of writing on registration forms. Registration-form documents consist of various type zones, such as printed text, handwriting, table, image, noise, etc., so segmenting the various zones is a challenge. We adopt herein an approach called “multiscale-region projection” to identify printed text and handwriting. An important aspect of our approach is the use of multiscale techniques to segment document images. A new set of projection features extracted from each zone is also proposed. The classification rules are mining and are used to discern printed text and table lines from handwritten text. The proposed system was tested on 11118 samples in two registration-form-image databases. Some possible measures of efficiency are computed, and in each case the proposed approach performs better than traditional methods.

The decrease in camera and smartphone sizes, the increase in picture resolutions, and the convenient access to cameras have created tremendous increases in a large volume of images being captured daily. As computer technology continues to improve, smartphones keep getting smaller, mobile processing power continues to significantly increase, and dual- or quad-core processors are becoming more popular. This has created an increase in the availability of software on small portable devices that cannot only take photos, but also edit them directly on the device, including the use of the copy-paste feature. In this paper, we present the copy-cover image forgery detection that can be used to identify a photo, whether it was altered by copying a portion of the image over another portion of itself. We also extend the detection in parallel processing by utilizing a computer with multiple CPU cores and parallel enhancements to the algorithm. Experimental results show there are significant improvements in performance by taking advantage of parallelism. Changing the detection routines in parallel can scale and take advantage of computing hardware equipped with multiple processors and large amounts of memory.

Head pose and facial feature detection are important for face analysis. However, many studies reported good results in constrained environment, the performance could be decreased due to the high variations in facial appearance, poses, illumination, occlusion, expression and make-up. In this paper, we propose a hierarchical regression approach, Dirichlet-tree enhanced random forests (D-RF) for face analysis in unconstrained environment. D-RF introduces Dirichlet-tree probabilistic model into regression RF framework in the hierarchical way to achieve the efficiency and robustness. To eliminate noise influence of unconstrained environment, facial patches extracted from face area are classified as positive or negative facial patches, only positive facial patches are used for face analysis. The proposed hierarchical D-RF works in two iterative procedures. First, coarse head pose is estimated to constrain the facial features detection, then the head pose is updated based on the estimated facial features. Second, the facial feature localization is refined based on the updated head pose. In order to further improve the efficiency and robustness, multiple probabilitic models are learned in leaves of the D-RF, i.e. the patch’s classification, the head pose probabilities, the locations of facial points and face deformation models (FDM). Moreover, our algorithm takes a composite weight voting method, where each patch extracted from the image can directly cast a vote for the head pose or each of the facial features. Extensive experiments have been done with different publicly available databases. The experimental results demonstrate that the proposed approach is robust and efficient for head pose and facial feature detection.

This paper shows a comparative study among different local matching-based methods for thermal infrared face recognition. The principal assumption of this work is that the thermal face corresponds to the diffuse energy emission captured by an infrared camera, where the thermal signature is unique for each subject and it can be addressed as a texture descriptor with thermal images. Local matching-based methods find inter-class differences that improve the face recognition rate in thermal spectrum. Specifically, this work considers four methods: Local Binary Pattern (LBP), Local Derivative Pattern (LDP), Weber Linear Descriptor (WLD) and Histograms of Oriented Gradients Descriptors (HOG). The methods are evaluated and compared using the UCHThermalFace database, that considers real-world conditions and unconstrained environments, such as indoor and outdoor setups, natural variations in illumination, facial expression, pose, accessories, occlusions, and background. Results indicate that HOG variants followed by LBP method achieved the best recognition rates for face recognition systems.

In todays world, identity of human beings has expanded beyond the real world to the cyber world. Virtual identity of millions of users is present at various web-based Social Networking Sites (SNSs) such as Myspace, Facebook, and Twitter. Interactions through SNSs have become a part of our daily practices, which eventually leaves a big trail of behavioral pattern in virtual domain. In this paper, the authors examined the feasibility of person identification using such social network activities as behavioral biometrics. Experimentation includes extraction of a number of idiosyncratic features from SNSs and analysis of their performance as novel social behavioral biometric features.

Biometric information is widely used in user identification system. Because of the unique and invariant properties of the iris through a lifetime, iris recognition is one of the most stable and reliable means in biometric identification. Extracting distinguishable iris features for iris recognition is very important. In this paper, for capturing effective texture features that represent the complex directional structures of an iris image, a new iris recognition method using the nonsubsampled contourlet transform (NSCT) features is proposed. With the shift-invariance, multiscale, and multidirection properties, significant NSCT coefficient features along the radial and angular directions in an iris image can be represented efficiently. Iris segmentation and normalization are considered at first as pre-processing. The modified normalized iris image is obtained from the normalized iris regions for extracting the robust iris features, and then is filtered with the NSCT to obtain the distinct coefficient features in each directional subband. Next, using the NSCT coefficients in each subband, an iris code vector is constructed for iris matching. Comparison of experimental results of the proposed and existing methods with three databases show the effectiveness of the proposed NSCT feature-based iris recognition algorithm, in terms of the three performance measures.

At present, frontal or even near frontal face recognition problem is no longer considered as a challenge. Recently, the shift has been to improve the recognition rate for the nonfrontal face. In this work, a neural network paradigm based on the radial basis function approach is proposed to tackle the challenge of recognizing faces in different poses. Exploiting the symmetrical properties of human face, our work takes the advantage of the existence of even half of the face. The strategy is to maximize the linearity relationship based on the local information of the face rather than on the global information. To establish the relationship, our proposed method employs discrete wavelet transform and multi-color uniform local binary pattern (ULBP) in order to obtain features for the local information. The local information will then be represented by a single vector known as the face feature vector. This face feature vector will be used to estimate the frontal face feature vector which will be used for matching with the actual vector. With such an approach, our proposed method relies on a database that contains only single frontal face images. The results shown in this paper demonstrate the robustness of our proposed method even at low-resolution conditions.

One of the crucial and inherent issues in a practical iris recognition system is the occlusion that happens due to eyelids and eyelashes. This occlusion increases the complexity and degrades the performance of matching and feature extraction processes. Generally, two types of approaches have been proposed to solve this issue. The first approach requires generating an iris mask that indicates which part of the iris is useful and which others are occluded. However, in the second approach, a fixed region of interest (ROI) within the iris area is selected to avoid the regions of occlusion. In this paper, we experimentally study both approaches but due to the latter characteristic, which is its ability to simplify the matching and feature extraction processes, it has been adopted in our techniques used, specifically for iris segmentation, iris normalization, and feature extraction. Accordingly, for matching and feature extraction, the lower side of the pupillary region (i.e. the innermost 25% of the lower half of the iris ring) is found to be the best ROI. This small area of iris is almost free of eyelids and eyelashes and it contains abundant texture information. Interestingly, this selection of small area helps us in proposing a simple yet efficient technique for feature extraction, called mean-based feature extraction technique (MB-FET). This technique is based on analyzing the local intensity variations. The proposed technique achieves a lower processing burden than other traditional methods such as Fourier or wavelet decompositions (e.g. Gabor wavelet). In most traditional techniques, many parameters (e.g. five parameters for 2D-Gabor filter) must be optimally determined in advance to achieve an accurate feature extraction process. Unfortunately, these parameters may not match various variations in image capturing conditions (e.g. variations in illumination due to change in image capturing distance). Moreover, the basic functions of the traditional methods are fixed in advance (off-line) and do not necessarily match the texture of all irises in the database. However, for our proposed technique MB-FET, there is no need to determine in advance any parameter or basic function. MB-FET dynamically adapts its parameter (only one parameter) with intensity variations. The proposed technique generates a binary iris code, hence a simple and fast matching process is done using the Hamming distance. The experimental results using the CASIA iris database show that the proposed technique achieves promising results for a robust and reliable iris recognition.

This paper proposed an efficient omnidirectional surveillance system for i-habitat (intelligent habitat or smart home in another name) security. In this surveillance system, the omnidirectional scenes in a room, kitchen, balcony, dining hall, corridor, garage or backyard within an i-habitat are first captured using wireless webcam attached to a specially designed hyperbolic optical mirror. The captured scenes are then fed into a wireless router connected to laptop computer for image processing and alarm purposes. A mapping algorithm is developed to match the captured omnidirectional image into panoramic image, hence providing the observer or image processing tools a complete wide angle of view. An efficient trespasser detection algorithm is designed for trespasser detection purpose, and an efficient faint detection algorithm is designed to identify/monitor if there is any member who stay in i-habitat (old-folks or ill-patients) who fall down or faint and thus, immediate attention can be carried out. Based on the experimental findings, both the proposed trespasser and faint detection algorithm achieves high accuracy.