International Journal of Pattern Recognition and Artificial Intelligence

In this paper, we examine the main advances registered in the last ten years in Pattern Recognition methodologies based on graph matching and related techniques, analyzing more than 180 papers; the aim is to provide a systematic framework presenting the recent history and the current developments. This is made by introducing a categorization of graph-based techniques and reporting, for each class, the main contributions and the most outstanding research results.

In this paper, a novel multi-instance learning (MIL) algorithm based on pyramid match kernel (PMK) and classifier ensemble is proposed for recognizing pornographic scene from image database. First, an improved JSEG image segmentation technique is deployed for dividing every image into several regions, and regards the whole image as a "bag", the low-level visual features (i.e. color and texture) of each segmented region as "instance". As a result, the pornographic images filtering problem can be transferred into a typical MIL problem. Second, similarity between the multi-instance bags is measured by PMK method, which allows MIL problem to be solved directly by the support vector machine (SVM). Finally, many base classifiers based on PMK with different levels are constructed, and the performance weighting rule is used to dynamically determine the weights of them, so the strategy of classifier ensemble is used to improve the filtering accuracy. In a real condition image set that the ratio of normal image to pornographic image is 9:1, experimental results show that the proposed algorithm, named PMKCE-MIL, is robust, and its performance is superior to other algorithms.

Most of the actual research in writing recognition focuses on specific applications where the vocabulary is relatively small. Many applications can be opened up when handling with large vocabulary. In this paper, we studied the classifier collaboration interest for the recognition of a large vocabulary of arabic words. The proposed approach is based on three classifiers, named Transparent Neuronal Networks (TNN), which exploit the morphological aspect of the Arabic word and collaborate for a better word recognition. We focused on decomposable words which are derived from healthy tri-consonantal roots and easy to proof the decomposition. To perform word recognition, the system extracts a set of global structural features. Then it learns and recognizes roots, schemes and conjugation elements that compose the word. To help the recognition, some local perceptual information is used in case of ambiguities. This interaction between global recognition and local checking makes easier the recognition of complex scripts as Arabic. Several experiments have been performed using a vocabulary of 5757 words, organized in a corpus of more than 17 200 samples. In order to validate our approach and to compare the proposed system with systems reported in ICDAR 2011 competition, extensive experiments were conducted using the Arabic Printed Text Image (APTI) database. The best recognition performances achieved by our system have shown very promising results.

Indoor environment is a common scene in our everyday life, and detecting and tracking multiple targets in this environment is a key component for many applications. However, this task still remains challenging due to limited space, intrinsic target appearance variation, e.g. full or partial occlusion, large pose deformation, and scale change. In the proposed approach, we give a novel framework for detection and tracking in indoor environments, and extend it to robot navigation. One of the key components of our approach is a virtual top view created from an RGB-D camera, which is named ground plane projection (GPP). The key advantage of using GPP is the fact that the intrinsic target appearance variation and extrinsic noise is far less likely to appear in GPP than in a regular side-view image. Moreover, it is a very simple task to determine free space in GPP without any appearance learning even from a moving camera. Hence GPP is very different from the top-view image obtained from a ceiling mounted camera. We perform both object detection and tracking in GPP. Two kinds of GPP images are utilized: gray GPP, which represents the maximal height of 3D points projecting to each pixel, and binary GPP, which is obtained by thresholding the gray GPP. For detection, a simple connected component labeling is used to detect footprints of targets in binary GPP. For tracking, a novel Pixel Level Association (PLA) strategy is proposed to link the same target in consecutive frames in gray GPP. It utilizes optical flow in gray GPP, which to our best knowledge has never been done before. Then we "back project" the detected and tracked objects in GPP to original, side-view (RGB) images. Hence we are able to detect and track objects in the side-view (RGB) images. Our system is able to robustly detect and track multiple moving targets in real time. The detection process does not rely on any target model, which means we do not need any training process. Moreover, tracking does not require any manual initialization, since all entering objects are robustly detected. We also extend the novel framework to robot navigation by tracking. As our experimental results demonstrate, our approach can achieve near prefect detection and tracking results. The performance gain in comparison to state-of-the-art trackers is most significant in the presence of occlusion and background clutter.

Face recognition is a challenging problem in computer vision and artificial intelligence. One of the main challenges consists in establishing a low-dimensional feature representation of the images having enough discriminatory power to perform high accuracy classification. Different methods of supervised and unsupervised classification can be found in the literature, but few numerical comparisons among them have been performed on the same computing platform. In this paper, we perform this kind of comparison, revisiting the main spectral decomposition methods for face recognition. We also introduce for the first time, the use of the noncentered PCA and the 2D discrete Chebyshev transform for biometric applications. Faces are represented by their spectral features, that is, their projections onto the different spectral basis. Classification is performed using different norms and/or the cosine defined by the Euclidean scalar product in the space of spectral attributes. Although this constitutes a simple algorithm of unsupervised classification, several important conclusions arise from this analysis: (1) All the spectral methods provide approximately the same accuracy when they are used with the same energy cutoff. This is an important conclusion since many publications try to promote one specific spectral method with respect to other methods. Nevertheless, there exist small variations on the highest median accuracy rates: PCA, 2DPCA and DWT perform better in this case. Also all the covariance-free spectral decomposition techniques based on single images (DCT, DST, DCHT, DWT, DWHT, DHT) are very interesting since they provide high accuracies and are not computationally expensive compared to covariance-based techniques. (2) The use of local spectral features generally provide higher accuracies than global features for the spectral methods which use the whole training database (PCA, NPCA, 2DPCA, Fisher's LDA, ICA). For the methods based on orthogonal transformations of single images, global features calculated using the whole size of the images appear to perform better. (3) The distance criterion generally provides a higher accuracy than the cosine criterion. The use of other p-norms (p > 2) provides similar results to the Euclidean norm, nevertheless some methods perform better. (4) No spectral method can provide 100% accuracy by itself. Therefore, other kind of attributes and supervised learning algorithms are needed. These results are coherent for the ORL and FERET databases. Finally, although this comparison has been performed for the face recognition problem, it could be generalized to other biometric authentication problems.

In this paper, we propose a hybrid computational geometry-gray scale algorithm that enhances fingerprint images greatly. The algorithm extracts the local minima points that are positioned on the ridges of a fingerprint, then, it generates a Delaunay triangulation using these points of interest. This triangulation along with the local orientations give an accurate distance and orientation-based ridge frequency. Finally, a tuned anisotropic filter is locally applied and the enhanced output fingerprint image is obtained. When the algorithm is applied to rejected fingerprint images from FVC2004 DB2 database by the veryfinger application, these images pass and experimental results show that we obtain a low false and missed minutiae rate with an almost uniform distribution over the database. Moreover, the application of the proposed algorithm enables the extraction of features from all low-quality fingerprint images where the equal error rate of verification is decreased from 6.50% to 5% using nondamaged low-quality images in the database.

Many gel electrophoresis image segmentation methods have been proposed. However, most of the proposed methods cannot provide a satisfying performance since a gel electrophoresis image is a manually captured image often with various noise and poor quality. This paper presents a one-dimensional-gel image segmentation method (1DGISM) to cut the bands off from a one-dimensional gel electrophoresis image (1D-gel image). The experimental results showed that 1DGISM can give an impressive segmentation performance even if the band boundaries are very indistinct. Moreover, the authors suggest that a low exposure for imaging be helpful in segmenting bright bands. Alternatively, taking the image at a high exposure is useful if the bands are dark.

Pornographic images are disturbing and malicious contents that are easily available through Internet technology. It has a negative and lasting effect on children who use the Internet; thus, pornography has become a serious threat not only to Internet users but also to society at large. Therefore, developing efficient and reliable tools to automatically filter pornographic contents is imperative. However, the effective interception of pornography remains a challenging issue. In this paper, a four-phase anti-pornography system based on the neural and Bayesian methods of artificial intelligence is proposed. Primitive information on pornography is examined and then used to determine if a given image falls under the pornography category. First, we present a detailed description of preliminary study phase followed by the modeling phase for the proposed skin detector. An anti-pornography system is created in the development phase, which also includes the proposed pornography classifier based on skin detection. Finally, the performance assessment method for the proposed anti-pornography system is discussed in the evaluation phase.

Autonomous helicopter stabilization in the presence of a wind disturbance is presented. A controller is designed based on the nonlinear adaptive output regulation and robust stabilization of a chain of integrators by a saturated feedback to stabilize the position and velocity of a helicopter. The controller is able to adaptively estimate the wind disturbance whose measurements are not made available. In addition to robustness against the external disturbance input the control design is carried out to handle helicopter parameter uncertainties. The cost of the robustly stabilizing control strategy is the challenge to tune 13 controller parameters for a desired output response. Particle swarm optimization (PSO), a metaheuristic optimization algorithm is applied to automate the tuning process. Simulation results demonstrate the effectiveness of the proposed control and tuning methods in the robust stabilization of the helicopter motion.

In order to accelerate the convergence and improve the calculation accuracy for parameter optimization of the Muskingum model, we propose a novel, adaptive hybrid particle swarm optimization (AHPSO) algorithm. With the decreasing of inertial weight factor proposed, this method can gradually converge to a global optimal with elite individuals obtained by hybrid PSO. In the paper, we analyzed the feasibility and the advantages of the AHPSO algorithm. Then, we verified its efficiency and superiority by application of the Muskingum model. We intensively evaluated the error fitting degree based on the comparison with four known formulas: the test method (TM), the least residual square method (LRSM), the nonlinear programming method (NPM), and the Broyden–Fletcher–Goldfarb–Shanno (BFGS) method. The results show that the AHPSO has a higher precision. In addition, we compared the AHPSO algorithm with the binary-encoded genetic algorithm (BGA), the Gray genetic algorithm (GGA), the Gray-encoded accelerating genetic algorithm (GAGA) and the particle swarm optimization (PSO), and results show that AHPSO has faster convergent speed. Moreover, AHPSO has a competitive advantage compared with the above eight methods in terms of robustness. With the efficiency of this approach it can be extended to estimate parameters of other dynamic models.