An improved pulse coupled neural networks model for semantic IoT

In recent years,the Internet of Things(IoT)has gradually developed applications such as collecting sensory data and building intelligent services,which has led to an explosion in mobile data traffic.Meanwhile,with the rapid development of artificial intelligence,semantic communication has attracted great attention as a new communication paradigm.However,for IoT devices,however,processing image information efficiently in real time is an essential task for the rapid transmission of semantic information.With the increase of model parameters in deep learning methods,the model inference time in sensor devices continues to increase.In contrast,the Pulse Coupled Neural Network(PCNN)has fewer parameters,making it more suitable for processing real-time scene tasks such as image segmentation,which lays the foundation for real-time,effective,and accurate image transmission.However,the parameters of PCNN are determined by trial and error,which limits its application.To overcome this limitation,an Improved Pulse Coupled Neural Networks(IPCNN)model is proposed in this work.The IPCNN constructs the connection between the static properties of the input image and the dynamic properties of the neurons,and all its parameters are set adaptively,which avoids the inconvenience of manual setting in traditional methods and improves the adaptability of parameters to different types of images.Experimental segmentation results demonstrate the validity and efficiency of the proposed self-adaptive parameter setting method of IPCNN on the gray images and natural images from the Matlab and Berkeley Segmentation Datasets.The IPCNN method achieves a better segmentation result without training,providing a new solution for the real-time transmission of image semantic information.

Anti-noise performance of the pulse coupled neural network applied in discrimination of neutron and gamma-ray

In this study,the anti-noise performance of a pulse-coupled neural network(PCNN)was investigated in the neutron and gamma-ray(n-γ)discrimination field.The experiments were conducted in two groups.In the first group,radiation pulse signals were pre-processed using a Fourier filter to reduce the original noise in the signals,whereas in the second group,the original noise was left untouched to simulate an extremely high-noise scenario.For each part,artificial Gaussian noise with different intensity levels was added to the signals prior to the discrimination process.In the aforementioned conditions,the performance of the PCNN was evaluated and compared with five other commonly used methods of n-γdiscrimination:(1)zero crossing,(2)charge comparison,(3)vector projection,(4)falling edge percentage slope,and(5)frequency gradient analysis.The experimental results showed that the PCNN method significantly outperforms other methods with outstanding FoM-value at all noise levels.Furthermore,the fluctuations in FoM-value of PCNN were significantly better than those obtained via other methods at most noise levels and only slightly worse than those obtained via the charge comparison and zerocrossing methods under extreme noise conditions.Additionally,the changing patterns and fluctuations of the FoMvalue were evaluated under different noise conditions.Hence,based on the results,the parameter selection strategy of the PCNN was presented.In conclusion,the PCNN method is suitable for use in high-noise application scenarios for n-γdiscrimination because of its stability and remarkable discrimination performance.It does not rely on strict parameter settings and can realize satisfactory performance over a wide parameter range.

Irregular Segmented Region Compression Coding Based on Pulse Coupled Neural Network

An irregular segmented region coding algorithm based on pulse coupled neural network(PCNN) is presented. PCNN has the property of pulse-coupled and changeable threshold, through which these adjacent pixels with approximate gray values can be activated simultaneously. One can draw a conclusion that PCNN has the advantage of realizing the regional segmentation, and the details of original image can be achieved by the parameter adjustment of segmented images, and at the same time, the trivial segmented regions can be avoided. For the better approximation of irregular segmented regions, the Gram-Schmidt method, by which a group of orthonormal basis functions is constructed from a group of linear independent initial base functions, is adopted. Because of the orthonormal reconstructing method, the quality of reconstructed image can be greatly improved and the progressive image transmission will also be possible.

Image edge detection based on pulse coupled neural network and modulus maxima in non-subsampled contourlet domain

Edge is the intrinsic geometric structure of an image. Edge detection methods are the key technologies in the lleld of image processing. In this paper, a multi-scale image edge detection method is proposed to effectively extract image geometric features. A source image is decomposed into the high frequency directional sub-bands coefficients and the low frequency sub-bands coefficients by non-subampled contourlet transform （NSCT）. The high frequency sub-bands coefficients are used to detect the abundant details of the image edges by the modulus maxima （MM） algorithm. The low frequency sub-band coefficients are used to detect the basic contour line of the image edges by the pulse coupled neural network （PCNN）. The final edge detection image is reconstructed with detected edge information at different scales and different directional sub-bands in the NSCT domain. Experimental results demonstrate that the proposed method outperforms several state-of-art image edge detection methods in both visual effects and objective evaluation.

Pulse Coupled Neural Network Edge-Based Algorithm for Image Text Locating

This paper presents a method for locating text based on a simplified pulse coupled neural network （PCNN）. The PCNN generates a firings map in a similar way to the human visual system with non-linear image processing. The PCNN is used to segment the original image into different planes and edges detected using both the PCNN firings map and a phase congruency detector. The different edges are integrated using an automatically adjusted weighting coefficient. Both the simplified PCNN and the phase congruency energy model in the frequency domain imitate the human visual system. This paper shows how to use PCNN by changing the compute space from the spatial domain to the frequency domain for solving the text location problem. The algorithm is a simplified PCNN edge-based （PCNNE） algorithm. Three comparison tests are used to evaluate the algorithm. Tests on large data sets show PCNNE efficiently detects texts with various colors, font sizes, positions, and uneven illumination. This method outperforms several traditional methods both in text detection rate and text detection accuracy.

Filtering images contaminated with pep and salt type noise with pulse-coupled neural networks

Pulse coupled neural network (PCNN) has a specific feature that the fire of one neuron can capture its adjacent neurons to fire due to their spatial proximity and intensity similarity. In this paper, it is indicated that this feature itself is a very good mechanism for image filtering when the image is damaged with pep and salt (PAS) type noise. An adaptive filtering method, in which the noisy pixels are first located and then filtered based on the output of the PCNN, is presented. The threshold function of a neuron in the PCNN is designed when it is used for filtering random PAS and extreme PAS noise contaminated image respectively. The filtered image has no distortion for noisy pixels and only less mistiness for non-noisy pixels, compared with the conventional window-based filtering method. Excellent experimental results show great effectiveness and efficiency of the proposed method, especially for heavy-noise contaminated images.

Automated retinal blood vessels segmentation based on simplified PCNN and fast 2D-Otsu algorithm

According to the characteristics of dynamic firing in pulse coupled neural network (PCNN) and regional configuration in retinal blood vessel network, a new method combined with simplified PCNN and fast 2D-Otsu algorithm was proposed for automated retinal blood vessels segmentation. Firstly, 2D Gaussian matched filter was used to enhance the retinal images and simplified PCNN was employed to segment the blood vessels by firing neighborhood neurons. Then, fast 2D-Otsu algorithm was introduced to search the best segmentation results and iteration times with less computation time. Finally, the whole vessel network was obtained via analyzing the regional connectivity. Experiments implemented on the public Hoover database indicate that this new method gets a 0.803 5 true positive rate and a 0.028 0 false positive rate on an average. According to the test results, compared with Hoover algorithm and method of PCNN and 1D-Otsu, the proposed method shows much better performance.

Numerical simulation of direct shear tests on mechanical properties of talus deposits based on self-adaptive PCNN digital image processing

The macro mechanical properties of materials with characteristics of large scale and complicated structural composition can be analyzed through its reconstructed meso-structures.In this work,the meso-structures of talus deposits that widely exist in the hydro-power engineering in the southwest of China were first reconstructed by small particles according to the in-situ photographs based on the self-adaptive PCNN digital image processing,and then numerical direct shear tests were carried out for studying the mechanical properties of talus deposits.Results indicate that the reconstructed meso-structures of talus deposits are more consistent with the actual situation because the self-adaptive PCNN digital image processing has a higher discrimination in the details of soil-rock segmentation.The existence and random distribution of rock blocks make the initial shear stiffness,the peak strength and the residual strength higher than those of the "pure soil" with particle size less than 1.25 cm apparently,but reduce the displacements required for the talus deposits reaching its peak shear strength.The increase of rock proportion causes a significant improvement in the internal friction angle of talus deposit,which to a certain degree leads to the characteristics of shear stress-displacement curves having a changing trend from the plastic strain softening deformation to the nonlinear strain hardening deformation,while an unconspicuous increase in cohesion.The uncertainty and heterogeneity of rock distributions cause the differences of rock proportion within shear zone,leading to a relatively strong fluctuation in peak strengths during the shear process,while movement features of rock blocks,such as translation,rotation and crossing,expand the scope of shear zone,increase the required shear force,and also directly lead to the misjudgment that the lower shear strength is obtained from the samples with high rock proportion.That,however,just explains the reason why the shear strength gained from a small amount of indoor test data is not consistent with engineering practice.

PCNN based image processing and feature extraction of dual-bypass gas metal arc weld pool

In manual welding process, skilled welders can adjust the welding parameters to ensure the weld quality through their observation of the weld pool surface. In order to acquire useful information of the weld pool for control of the welding process and realizing the automatic welding, the measurement system of DB-GMA W process was established and the weld pool image was obtained by passive vision. Then, three image processing algorithms, Sobel, Canny, and pulse coupled neural network （PCNN） were detailed and applied to extracting the edge of the DB-GMA weld pool. In addition, a scheme was proposed for calculating the length, maximum width and superficial area of the weld pool under different welding conditions. The compared results show that the PCNN algorithm can be used for extracting the edge of the weld pool and the obtained information is more useful and accurate. The calculated results coincide with the actual measurement well, which demonstrates that the proposed algorithm is effective, its imaging processing time is required only 20 ms, which can completely meet the requirement of real-time control.

Shadow detection combining characters of human vision

A shadow detection method using pulse couple neural network inspired by the characters of human visual system is proposed.More precisely,lateral inhibition of human vision and coefficient of variation are combined together to improve the pulse couple neural network.Shadow detection is considered to be a shadow region segmentation problem.Experiment shows that the presented method is consistent with human vision compared to shadow detection methods based on HSV and pulse couple neural network(PCNN) by both subjective and objective assessments.

基于PCNN图像分割的医学图像融合算法

为充分提取源图像间的互补信息,改进传统的图像融合算法在亮度维持、能量保留、边缘信息保持等方面的不足,本文提出了基于脉冲耦合神经网络(pulse coupled neural network, PCNN)图像分割的医学图像融合算法。该算法综合了非下采样剪切波变换(non-subsampled shearlet transform, NSST)与PCNN。首先,选取标准差较大的源图像作为被分割图像,标准差较小的源图像作为参照图像,将源图像进行NSST分解,获取源图像低频子带系数和高频子带系数;在低频融合中,利用参数自适应的PCNN对被分割图像的低频子带进行分割,根据分割结果获取融合低频子带系数;在高频融合中,采用以区域能量和与拉普拉斯能量和两者的乘积作为判断函数,获取融合高频子带系数;利用NSST逆变换获取融合图像。最后,应用本文提出的算法,对脑萎缩、急性中风和高血压性脑病等3组电脑断层扫描/磁共振成像(computerized tomography/magnetic resonance imaging, CT/MRI)图像进行了融合仿真,并将仿真结果与2018年后国际刊上提出的5种算法的融合图像进行比较。结果表明,应用本文提出的融合算法得到的图像,有效地增强了不同模态间的信息互补,保持了融合图像与源图像具有相同明亮程度,又保留了源图像低亮度部分的边缘信息,更加符合人眼视觉特性,具有更高的客观评价指标。

Medical Image Segmentation using PCNN based on Multi-feature Grey Wolf Optimizer Bionic Algorithm

Medical image segmentation is a challenging task especially in multimodality medical image analysis.In this paper,an improved pulse coupled neural network based on multiple hybrid features grey wolf optimizer(MFGWO-PCNN)is proposed for multimodality medical image segmentation.Specifically,a two-stage medical image segmentation method based on bionic algorithm is presented,including image fusion and image segmentation.The image fusion stage fuses rich information from different modalities by utilizing a multimodality medical image fusion model based on maximum energy region.In the stage of image segmentation,an improved PCNN model based on MFGWO is proposed,which can adaptively set the parameters of PCNN according to the features of the image.Two modalities of FLAIR and TIC brain MRIs are applied to verify the effectiveness of the proposed MFGWO-PCNN algorithm.The experimental results demonstrate that the proposed method outperforms the other seven algorithms in subjective vision and objective evaluation indicators.

Improved image filter based on SPCNN

By extraction of the thoughts of non-linear model and adaptive model match, an improved Nagao filter is brought. Meanwhile a technique based on simplified pulse coupled neural network and used for noise positioning, is put forward. Combining the two methods above, we acquire a new method that can restore images corrupted by salt and pepper noise. Experiments show that this method is more preferable than other popular ones, and still works well while noise density fluctuates severely.

Image copy-move forgery passive detection based on improved PCNN and self-selected sub-images

Image forgery detection remains a challenging problem.For the most common copy-move forgery detection,the robustness and accuracy of existing methods can still be further improved.To the best of our knowledge,we are the first to propose an image copy-move forgery passive detection method by combining the improved pulse coupled neural network(PCNN)and the self-selected sub-images.Our method has the following steps:First,contour detection is performed on the input color image,and bounding boxes are drawn to frame the contours to form suspected forgery sub-images.Second,by improving PCNN to perform feature extraction of sub-images,the feature invariance of rotation,scaling,noise adding,and so on can be achieved.Finally,the dual feature matching is used to match the features and locate the forgery regions.What’s more,the self-selected sub-images can quickly obtain suspected forgery sub-images and lessen the workload of feature extraction,and the improved PCNN can extract image features with high robustness.Through experiments on the standard image forgery datasets CoMoFoD and CASIA,it is effectively verified that the robustness score and accuracy of proposed method are much higher than the current best method,which is a more efficient image copy-move forgery passive detection method.