A new hybrid tracking strategy based on Pulse Coupled Neural Network

Visual tracking is one of fundamental tasks in the field of computer vision. In recent years, detection algorithms have been more and more interested in the use of discriminative classifiers for tracking system. Template drift is the major shortcoming of the detection algorithms because of the online self-learning mechanism of the visual tracker. Multiple Instance Learning (MIL) method has been applied to target tracking, which can alleviate the drift to some extent. However, the MIL tracker cannot discriminatively consider the importance of sample and instance in its learning procedure. Particle filter is employed to make the use of the learned classifier and to help generating a better representative set of training samples for the online learning. In this paper, we present a tracking method built by particle filter and weighted MIL tracker, which integrates the sample and instance importance into an efficient online learning procedure when the classifier is being trained. At the end, the experimental results on various videos verify that the proposed method has a satisfaction performance in real-time object tracking.

Image segmentation is a very important aspect in the field of image processing. According to certain principles, it will be divided into a number of small regional disjoint. Small region is a sense sets of common attributes of the connectivity pixels. The so-called connectivity which refers to the fact that any two points in the pool existing a connectivity path between all belong to the set. Pulse coupled neural networks was proposed based on the brain simultaneously pulsed release phenomenon of the visual cortex of the cats, monkeys, and other animals, the similar input data can be outbreak synchronized through interrelated neurons. The digital image can be processed by pulse coupled neural networks, the pixels of space based approach and brightness can be made up to a group. Pulse coupled neural networks has a good nature in image processing applications, which can effectively for the various aspects of image processing, and it can be used in the image processing system. Experimental results show that the method can achieve better image segmentation and have a common applicability.

In this paper, a novel algorithm for microscopic color cell image edge detection based on Pulse Coupled Neural Networks (PCNN) is presented. Microscopic color image edge detection has proven to be a difficult task due to uneven brightness, cross-color existing between cell boundary and background caused by dyeing and noise. To solve these problems, this paper originally employs an improved PCNN model called multi-dimensional PCNN to implement edge detection of microscopic color cell image. PCNN is an advanced approach which aims at processing color images parellelly rather than separately dispose signal to every channel because it is characterized by synchronous neuronal burst and multi-dimensional convolution. To test the feasibility and effectiveness of multi-dimensional PCNN on edge detection of microscopic color cell images, experiments of several microscopic cell images are carried out. Empirical results show that multi-dimensional PCNN outperforms classical methods in terms of anti-noise and the accuracy of weak edge detection.

A new approach to object detection using image icons based on Unit-linking PCNN (Pulse Coupled Neural Network) is introduced in this paper. Unit-linking PCNN, which has been developed from PCNN exhibiting synchronous pulse bursts in cat and monkey visual cortexes, is a kind of time-space-coding SNN (Spiking Neural Network). We have used Unit-linking PCNN to produce the global image icons with translation and rotation invariance. Unit-linking PCNN image icon (namely global image icons) is the 1-dimentional time series, and is a kind of image feature extracted from the time information that Unit-linking PCNN code the 2-dimentional image into. Its translation and rotation invariance is a good property in object detection. In addition to translation, rotation invariance, the object detection approach in this paper is also independent of scale variation.

In this paper, a novel method is proposed for face recognition based on combined Gabor features and unit-linking pulse coupled neural network (PCNN) time signature. In this approach, a probe face is first divided into a 2times2 block then the mean and standard deviation of the Gabor sub-face image are extracted which includes 40-dimension features in each block. The PCNN time signature of a face image is combined with the Gabor features as the recognition features, which is classified with Euclidean distance or support vector machine. An extensive experimental investigation is conducted using AT&T face database covering face recognition under controlled/ideal conditions, different illumination conditions and different facial expressions. The recognition ratio is 87% when only Gabor feature, including three exemplar images per person are available. The recognition ratio is 95.25% when Gabor feature is combined with the unit-linking PCNN time signature while incurring little increase to the processing time since the dimension of the unit-linking PCNN time signature is low.

It needs set parameters on image segmentation based on PCNN (Pulse Coupled Neural Network) now. This paper points out the new method for medical image segmentation based on improved PCNN and Tsallis entropy. The new methods can automatically segment the medical images without selecting the PCNN parameters. It gets the best results with combining with the Tsallis entropy. The new method is very useful for PCNN application in the medical images segmentation.

In this paper, a review of parameter optimization methods of pulse-coupled neural networks (PCNNs) is presented. Considering that PCNN has been used in image processing for many years, the aim of this paper was to provide an overview of the work that has been done and to serve as a useful reference for those who are looking for PCNN parameter optimization methods and those who are researching PCNN applications for a specific field. This paper first briefly reviews the PCNN model, including the standard PCNN and several variants of PCNN. Then, we emphasize the optimization methods for PCNN’s parameters, describing three types of parameter optimization methods in detail. Next, the paper summarizes the applications of the optimized models of PCNN with adaptive parameters in image segmentation, image fusion, image denoising and edge detection.

Image Fusion Algorithm Based on Simplified PCNN in Nonsubsampled Contourlet Transform Domain

Pulse Coupled Neural Network(PCNN) is widely used in the field of image processing, but it is a difficult task to define the relative parameters properly in the research of the applications of PCNN. So far the determination of parameters of its model needs a lot of experiments. To deal with the above problem, a document segmentation based on the improved PCNN is proposed. It uses the maximum entropy function as the fitness function of bacterial foraging optimization algorithm, adopts bacterial foraging optimization algorithm to search the optimal parameters, and eliminates the trouble of manually set the experiment parameters. Experimental results show that the proposed algorithm can effectively complete document segmentation. And result of the segmentation is better than the contrast algorithms.

Image analysis for airborne reconnaissance and missile applications

In order to overcome the lacking of Shift invariance in Contourlet Transform, enable the image fusion to be in accord with human vision properties, Nonsubsampled Contourlet Transform (NSCT) and Pulse Coupled Neural Networks(PCNN) were used jointly in image fusion algorithms. Original images were decomposed to get the coefficients of low frequency sub bands and high frequency sub bands. The coefficients of low and high frequency sub bands were processed by a modified PCNN. Matching degree of original images is defined and used in fusion rules. Fusion image was obtained by NSCT inverse transformation. Experimental result shows this method is better than Wavelet, Contourlet and traditional PCNN methods, it has bigger mutual information, so the fusion image include more original image's information.

License plate segmentation is a key technology in the process of license plate location and recognition. How to realize automatic segmentation of license plate image under complex illumination conditions has been a hot issue in intelligent transportation system (ITS). This paper deals with license plate image segmentation under a variety of lighting conditions. Based on the adaptive segmentation of license plate images by the Pulse Coupled Neural Network (PCNN), the relationship between the license plate image contrast and the PCNN iteration entropy is analyzed. An adaptive segmentation algorithm for license plate image using Deep Neural Network (DNN) to select the optimal result is proposed, and the selected segmentation image is filtered by the connected domain, which lays a foundation for subsequent license plate location, character segmentation and recognition. Simulation experiments show that the proposed algorithm performs better license plate segmentation and optimal selection for license plate images under various lighting conditions.

In order to acquire a kind of stable and efficient feature sequences to identify different shape of seal images in different angles. Pulse Coupled Neural Networks (PCNN) are adopted to extract the energy logarithmic sequences of seal images, the input image is a binary image, different shape of seal images used as input data of PCNN network to acquire their energy logarithmic sequence as the standard sequence. Then the same flows are used to match the logarithmic sequences of images to be recognized with the standard sequences. In addition, angle rotated seal images also be recognized as identified images. Statistical results analyzed are based on Pearson correlation coefficient. The experimental results of different shapes stamp statistics show that using Pearson correlation coefficient and for statistical experiments compared the sequence that obtained more desirable results. Through many seals experiments proved that the result of Pearson correlation coefficient can reach more than 0.99. The energy logarithmic sequence of different shape of seal images can be used as the feature sequences, which is not impact by the seal’s chop angles, and the feature has a certain stability.

To calculate the similarity or dissimilarity of DNA sequences, a new method is proposed based on pulse coupled neural network (PCNN) model. First, according to the characteristics of PCNN model, we encode DNA primary sequences using a simple coding method. Then we use PCNN model to extract the entropy sequence (ES) of the encoded DNA sequence; the ES expresses the features of the DNA sequences. At last, we calculate the similarity of the ES by Euclidean distance to get the similarity of DNA sequences. We take several sets of data to test our method. The experimental results demonstrate that our method is effective.

An adaptive filter was proposed to detect and remove pepper and salt noise in an image based on Pulse Coupled Neural Network(PCNN) firing matrix.The PCNN was simplified and a unidirectional decaying threshold was proposed to avoid complex parameter selection and improve processing speed.The noise-polluted pixels were detected through analyzing the PCNN firing matrix,and then only the noisy pixels were filtered by a median filter while protecting image edges and details.The window size of the filter and the filtering time were adaptively determined by calculating the noise intensity of the contaminated image.The experimental results show that the proposed method performs better in removing noise while conserving detailed information than traditional filters do.