International Journal of Pattern Recognition and Artificial Intelligence

A robust traffic surveillance system is crucial in improving the control and management of traffic systems. Vehicle flow processing primarily involves counting and tracking vehicles; however, due to complex situations such as brightness changes and vehicle partial occlusions, traditional image segmentation methods are unable to segment and count vehicles correctly. This paper presents a novel framework for vision-based vehicle counting and tracking, which consists of four main procedures: foreground detection, feature extraction, feature analysis, and vehicles counting/tracking. Foreground detection intends to generate regions of interest in an image, which are used to produce significant feature points. Vehicles counting and tracking are achieved by analyzing clusters of feature points. As for testing on recorded traffic videos, the proposed framework is verified to be able to separate occluded vehicles and count the number of vehicles accurately and efficiently. By comparing with other methods, we observe that the proposed framework achieves the highest occlusion segment rate and the counting accuracy.

Multi-string matching (MSM) is a core technique searching a text string for all occurrences of some string patterns. It is widely used in many applications. However, as the number of string patterns increases, most of the existing algorithms suffer from two issues: the long matching time, and the high memory consumption. To address these issues, in this paper, a fast matching engine is proposed for large-scale string matching problems. Our engine includes a filter module and a verification module. The filter module is based on several bitmaps which are responsible for quickly filtering out the invalid positions in the text, while for each potential matched position, the verification module confirms true pattern occurrence. In particular, we design a compact data structure called Adaptive Matching Tree (AMT) for the verification module, in which each tree node only saves some pattern fragments of the whole pattern set and the inner structure of each tree node is chosen adaptively according to the features of the corresponding pattern fragments. This makes the engine time and space efficient. The experiments indicate that, our matching engine performs better than the compared algorithms, especially for large pattern sets.

Imbalanced dataset affects the learning of classifiers. This imbalance problem is almost ubiquitous in biological datasets. Resampling is one of the common methods to deal with the imbalanced dataset problem. In this study, we explore the learning performance by varying the balancing ratios of training datasets, consisting of the observed peptides and absent peptides in the Mass Spectrometry experiment on the different machine learning algorithms. It has been observed that the ideal balancing ratio has yielded better performance than the imbalanced dataset, but it was not the best as compared to some intermediate ratio. By experimenting using Synthetic Minority Oversampling Technique (SMOTE) at different balancing ratios, we obtained the best results by achieving sensitivity of 92.1%, specificity value of 94.7%, overall accuracy of 93.4%, MCC of 0.869, and AUC of 0.982 with boosted random forest algorithm. This study also identifies the most discriminating features by applying the feature ranking algorithm. From the results of current experiments, it can be inferred that the performance of machine learning algorithms for the classification tasks can be enhanced by selecting optimally balanced training dataset, which can be obtained by suitably modifying the class distribution.

This paper presents main paradigms of research for feature extraction methods to further augment the state of art in speaker recognition (SR) which has been recognized extensively in person identification for security and protection applications. Speaker recognition system (SRS) has become a widely researched topic for the last many decades. The basic concept of feature extraction methods is derived from the biological model of human auditory/vocal tract system. This work provides a classification-oriented review of feature extraction methods for SR over the last 55 years that are proven to be successful and have become the new stone to further research. Broadly, the review work is dichotomized into feature extraction methods with and without noise compensation techniques. Feature extraction methods without noise compensation techniques are divided into following categories: On the basis of high/low level of feature extraction; type of transform; speech production/auditory system; type of feature extraction technique; time variability; speech processing techniques. Further, feature extraction methods with noise compensation techniques are classified into noise-screened features, feature normalization methods, feature compensation methods. This classification-oriented review would endow the clear vision of readers to choose among different techniques and will be helpful in future research in this field.

Image denoising as a part of pre-processing in image analysis is a challenging area of research since noise removal and image detail preservation need a tradeoff. For classical denoising models, the convex total variation (TV) or some nonconvex regularizers are used to achieve the tradeoff. However, the denoising performance of classical models is still inadequate. To overcome this problem, this paper proposes a new variational model for image restoration, where a weighted regularizer is designed to protect more geometric structural details of images from over-smoothing and to remove much noise simultaneously. To solve the model efficiently, a novel algorithm based on Chambolle’s dual projection method and the iteratively reweighting method is presented. Numerical results prove that the proposed denoising method can show better performance than the classical TV-based and the nonconvex regularizer-based denoising methods.

Graph cuts (GC) have become one of the most important methodologies in image segmentation. Recently, some researches tend to study GC and kernel mapping of the image pixels. However, most of the methods of existing kernel GC (KGC) image segmentation not only suffers from different types of noise, but also suffers from the settings of the regularizing parameter, which is used to balance the edge and region terms in the existing KGC. This paper is to investigate the image segmentation via principal component analysis and KGC ensemble. The principal components are selected by the estimated strength of introduced noise, which is calculated by the maximum statistics of variation coefficient. Besides, the regularization term of KGC is difficult to choose the appropriate scaling factor value for the regularization term, and it is always obtained by experience. Here, we aim to present KGC ensemble strategy to combine the segmenting results under different settings of scaling parameter. Furthermore, to achieve higher segmenting accuracy, the KGC is implemented in the projected lower dimensional subspace by selected principal components. Experiments on synthetic image, nature image, medical image and real SAR images demonstrate the advantages of the proposed algorithm over the existing KGC, two variants of fuzzy c-means not only in region consistence but also in the boundary localization.

In multi-camera video tracking, the tracking scene and tracking-target appearance can become complex, and current tracking methods use entirely different databases and evaluation criteria. Herein, for the first time to our knowledge, we present a universally applicable template library updating approach for multi-camera human tracking called multi-state self-learning template library updating (RS-TLU), which can be applied in different multi-camera tracking algorithms. In RS-TLU, self-learning divides tracking results into three states, namely steady state, gradually changing state, and suddenly changing state, by using the similarity of objects with historical templates and instantaneous templates because every state requires a different decision strategy. Subsequently, the tracking results for each state are judged and learned with motion and occlusion information. Finally, the correct template is chosen in the robust template library. We investigate the effectiveness of the proposed method using three databases and 42 test videos, and calculate the number of false positives, false matches, and missing tracking targets. Experimental results demonstrate that, in comparison with the state-of-the-art algorithms for 15 complex scenes, our RS-TLU approach effectively improves the number of correct target templates and reduces the number of similar templates and error templates in the template library.

Sentiment analysis is becoming increasingly important mainly because of the growth of web comments. Sentiment polarity classification is a popular process in this field. Writing style features, such as lexical and word-based features, are often used in the authorship identification and gender classification of online messages. However, writing style features were only used in feature selection for sentiment classification. This research presents an exploratory study of the group characteristics of writing style features on the Internet Movie Database (IMDb) movie sentiment data set. Furthermore, this study utilizes the specific group characteristics of writing style in improving the performance of sentiment classification. We determine the optimum clustering number of user reviews based on writing style features distribution. According to the classification model trained on a training subset with specific writing style clustering tags, we determine that the model trained on the data set of a specific writing style group has an optimal effect on the classification accuracy, which is better than the model trained on the entire data set in a particular positive or negative polarity. Through the polarity characteristics of specific writing style groups, we propose a general model in improving the performance of the existing classification approach. Results of the experiments on sentiment classification using the IMDb data set demonstrate that the proposed model improves the performance in terms of classification accuracy.

This paper presents a new approach called the empirical mode decomposition — window fractal (EMDWF) algorithm in classification of fingerprint of medicinal herbs. In this way, we consider a glycyrrhiza fingerprint of medicinal herb as a signal sequence, and apply empirical mode decomposition (EMD) and Hiaguchis fractal dimension to construct a feature vector. By using EMD, the glycyrrhiza fingerprint of medicinal herb can be decomposed into some intrinsic mode functions (IMFs). As window fractal dimension (WFD) is applied to each IMF and original signal, the features of the glycyrrhiza fingerprint of medicinal herb can be obtained. Thereafter, SVM is applied as a classifier. The results of the experiments state clearly that the feature extracted by EMDWF is better than that of the existing methods including the pure EMD. With the increase of the number of training samples and the increase of the number of layers in EMD, the classification result achieves more stability.

An illumination and expression invariant face recognition method based on uniform local binary patterns (uLBP) and Legendre moments is proposed in this work. The proposed method exploits uLBP texture features and Legendre moments to make a feature representation with enhanced discriminating power. The input images are preprocessed to extract the face region and normalized. From normalized image, uLBP codes are extracted to obtain texture image which overcomes the effect of monotonic temperature changes. Legendre moments are computed from this texture image to get the required feature vector. Legendre moments conserve the spatial structure information of the texture image. The resultant feature vector is classified using k-nearest neighbor classifier with $L_1$ norm. To evaluate the proposed method, experiments are performed on IRIS and NVIE databases. The proposed method is tested on both visible and infrared images under different illumination and expression variations and performance is compared with recently published methods in terms of recognition rate, recall, length of feature vector, and computational time. The proposed method gives better recognition rates and outperforms other recent face recognition methods.

In this paper, we propose a novel approach of Gabor feature based on bi-directional two-dimensional principal component analysis ((2D)²PCA) for somatic cells recognition. Firstly, Gabor features of different orientations and scales are extracted by the convolution of Gabor filter bank. Secondly, dimensionality reduction of the feature space applies (2D)²PCA in both row and column. Finally, the classifier uses Support Vector Machine (SVM) to achieve our goal. The experimental results are obtained using a large set of images from different sources. The results of our proposed method are not only efficient in accuracy and speed, but also robust to illumination in bovine mastitis via optical microscopy.

Different kinds of illustrations and artistic imagery can be generated or simulated through the nonphotorealistic rendering (NPR) technique. However, designing and simulating new NPR artistic styles remains extremely challenging. Chalk art style is a very famous artistic work all over the world, and few algorithms have been put forward to illustrate this style. This paper presents a novel NPR technique which generates a chalk art drawing from a 2D photograph automatically. We aim at obtaining a set of lines surface with coarse appearance and generating stroke textures of the real chalk painting. Firstly, the edge of the source image is extracted by difference-of-Gaussian filter method. To simulate chalk painting’s lines, image diffusion and enhancement techniques are proposed to produce coarse and rough lines. Secondly, we developed an improved line integral convolution and dilation operation methods to produce the chalk stroke texture. Finally, the edge image, stroke texture image and color image will be mapped to another background image to generate the chalk art drawing. Experimental results are presented to show the effectiveness of our method in producing the color chalk stylistic illustrations, and the methods can simulate the characters of the real chalk art painting. The proposed method of this paper will enlarge the research and application fields of NPR. Meanwhile, it provides a tool for the user to create chalk art paintings via computers even without painting skill.