Jesse S. Jin

A novel statistical cerebrovascular segmentation algorithm with particle swarm optimization

Abstract We present an automatic statistical intensity-based approach to extract the 3D cerebrovascular structure from time-of flight (TOF) magnetic resonance angiography (MRA) data. We use the finite mixture model (FMM) to fit the intensity histogram of the brain image sequence, where the cerebral vascular structure is modeled by a Gaussian distribution function and the other low intensity tissues are modeled by Gaussian and Rayleigh distribution functions. To estimate the parameters of the FMM, we propose an improved particle swarm optimization (PSO) algorithm, which has a disturbing term in speeding updating the formula of PSO to ensure its convergence. We also use the ring shape topology of the particles neighborhood to improve the performance of the algorithm. Computational results on 34 test data show that the proposed method provides accurate segmentation, especially for those blood vessels of small sizes.

A review of algorithms for filtering the 3D point cloud

Abstract In recent years, 3D point cloud has gained increasing attention as a new representation for objects. However, the raw point cloud is often noisy and contains outliers. Therefore, it is crucial to remove the noise and outliers from the point cloud while preserving the features, in particular, its fine details. This paper makes an attempt to present a comprehensive analysis of the state-of-the-art methods for filtering point cloud. The existing methods are categorized into seven classes, which concentrate on their common and obvious traits. An experimental evaluation is also performed to demonstrate robustness, effectiveness and computational efficiency of several methods used widely in practice.

Monte Carlo Convex Hull Model for classification of traditional Chinese paintings

While artists demonstrate their individual styles through paintings and drawings, how to describe such artistic styles well selected visual features towards computerized analysis of the arts remains to be a challenging research problem. In this paper, we propose an integrated feature-based artistic descriptor with Monte Carlo Convex Hull (MCCH) feature selection model and support vector machine (SVM) for characterizing the traditional Chinese paintings and validate its effectiveness via automated classification of Chinese paintings authored by well-known Chinese artists. The integrated artistic style descriptor essentially contains a number of visual features including a novel feature of painting composition and object feature, each of which describes one element of the artistic style. In order to ensure an integrated discriminating power and certain level of adaptability to the variety of artistic styles among different artists, we introduce a novel feature selection method to process the correlations and the synergy across all elements inside the integrated feature and hence complete the proposed style-based descriptor design. Experiments on classification of Chinese paintings via a parallel MCCH model illustrate that the proposed descriptor outperforms the existing representative technique in terms of precision and recall rates.

Video fire detection based on Gaussian Mixture Model and multi-color features

This paper proposes a new approach to detect fire from a video stream. It takes full advantage of the motion feature and color information of fire. Firstly, motion detection using Gaussian Mixture Model-based background subtraction is applied to extract moving objects from a video stream. Then, multi-color-based detection combining the RGB, HSI and YUV color space is employed to obtain possible fire regions. Finally, the results of the above two steps are combined to identify the accurate fire areas. The experimental results obtained by applying this method on different fire videos show that the proposed method can achieve better effectiveness, adaptability and robustness.

The Improved Canny Edge Detection Algorithm Based on an Anisotropic and Genetic Algorithm

Edge detection plays a crucial role in image processing. This paper proposes an improved Canny edge detection algorithm to deal with existing problems in traditional algorithms. Firstly, we use the anisotropic filter to denoise original grayscale images. This method can effectively suppress noise and preserve the edge feature. Secondly, the paper searches optimizing high and low thresholds used in Canny operator utilizing genetic algorithm based on the Otsu evaluative function to avoid human factors. In our experiment, we got the optimizing value (227, 84), and the interclass variance (3833) for image Lena. Compared with the traditional operator, this improved algorithm can reduce the false positive rate and improve the accuracy of detection. Meanwhile, the experiment shows that the algorithm is also robust in pedestrian detection.

Brushstroke based sparse hybrid convolutional neural networks for author classification of Chinese ink-wash paintings

A novel stroke based sparse hybrid convolutional neural networks (CNNs) method is proposed for author classification of Chinese ink-wash paintings (IWPs). As Chinese IWPs usually have many authors in several art styles, this differs from real images or western paintings and has led to a big challenge. In our work, we classify Chinese IWPs of different artists by analyzing a set of automatically extracted brushstrokes. A sparse hybrid CNNs in a deep-learning framework is then proposed to extract brushstroke features to replace the commonly used handcrafted ones such as edge, color, intensity and texture. Using 120 IWPs from six famous artists, promising results have been shown in successfully classifying authors in comparison to two other state-of-the-art approaches.

Iterative guidance normal filter for point cloud

Abstract3D point clouds have become increasingly popular in recent year due to the rapid development of low-cost 3D sensors. One of the most interesting challenges is to filter point cloud, which undoubtedly becomes a crucial part of the point cloud processing pipeline. Based on normal information, this paper proposes a simple but effective point cloud filter framework. In this framework, a kd-tree structure is constructed for representing point cloud to search neighborhood and estimate normal for each point at first. Then, iteratively performing the processing that a bilateral filter is applied to the normal field obtained from the previous iteration, using the same normal field as the guidance; afterward, adjusting point positions is performed depending on the filtered normals. Experimental results indicate the effectiveness of our algorithms.

Guided 3D point cloud filtering

Abstract3D point cloud has gained significant attention in recent years. However, raw point clouds captured by 3D sensors are unavoidably contaminated with noise resulting in detrimental efforts on the practical applications. Although many widely used point cloud filters such as normal-based bilateral filter, can produce results as expected, they require a higher running time. Therefore, inspired by guided image filter, this paper takes the position information of the point into account to derive the linear model with respect to guidance point cloud and filtered point cloud. Experimental results show that the proposed algorithm, which can successfully remove the undesirable noise while offering better performance in feature-preserving, is significantly superior to several state-of-the-art methods, particularly in terms of efficiency.

Pedestrian intrusion detection based on improved GMM and SVM

In recent years, the computer vision and intelligent video surveillance technology have been significantly developed, thanks to the development of computer science. The automated scenario pedestrian intrusion detection has been widely used in more and more fields, such as security. In this paper, we focus on the research work of dynamic pedestrian intrusion detection, improving some shortcomings in traditional methods. First, we take advantage of the GMM, based on gradient images, to finish the video motion foreground detection. In this stage, we promoted the traditional methods which could not deal with the light mutations, shadows and other interference. On the basis of this, SVM classifier based on HOG feature is used to detect the pedestrian in the moving area. On the other side, in order to significantly increase the performance of detection, we take advantage of the least squares fitting to optimize the motion area, making the detection rate has been greatly improved. In this experiment, the rate of highest accuracy of intrusion detection has reached 97.5% successfully, that is to say, our method in this paper has good accuracy and robustness in practical application.

A perspective correction method based on the bounding rectangle and least square fitting

Although Automatic License Plate Recognition (ALPR) systems have achieved high recognition speed and efficiency, perspective distortion may still affect the accuracy and reliability of ALPR due to the uncertainty of camera shooting angle. Some existing license plate correction methods are computational expensive and low robust. We proposed a perspective correction method based on the bounding rectangle and least square fitting. We extracted the bounding rectangle and the minimum bounding rectangle of each character. We use the least square method to fit a line for key points. Finally, the approach uses four vertices of license plate to get perspective transformation matrix and correct the distorted images. The results of our experiments show that our method is fast, accurate and robust.