Infrared Image Denoising based on Simplified Pulse Coupled Neural Network

نویسندگان

  • Xinxiang Liu
  • Gang Liu
  • Guangyu Wang
  • Ningning Yu
  • Yonggang Liu
چکیده

For the problem of being prone to result in image blur and losing of edge information, and according to the characteristics of ambiguous target and low contrast in the common infrared image preprocessing algorithm, a method of infrared image denoising by using simplified pulse coupled neural network was proposed in this paper. The improved selection of neuron joining strength which was relation to the neighborhood pixel gray value facilitated denoising. The computational method of threshold decaying exponent was simplified, which made it depend on the threshold amplitude and the optimal value of threshold amplitude can be obtained automatically. Experimental results showed that this method can improve the optimization efficiency of the parameters of pulse coupled neural network, not only could effectively filter out the noise, but also could maximally preserve image details.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

SAR Image Change Detection Method Based on Pulse-Coupled Neural Network

The study proposes a new algorithm for change detection of SAR images based on segmentation to improve the accuracy of the SAR image change detection. The ratio method is used to acquire the difference image (DI). Then, the global dictionary is applied to address the image denoising problem. Finally, change mask is obtained by pulse-coupled neural network (PCNN). The results of the experiment s...

متن کامل

Locust Image Segmentation Using Pulse-coupled Neural Network

The main objective of this study was to evaluate the feasibility of identifying locusts by the image segmentation method based on pulse-coupled neural network (PCNN). Segmentation results by simplified PCNN and traditional morphology open operation method were given. The simulation results demonstrated that the PCNN was powerful enough to perform the detecting.

متن کامل

Physiologically motivated image fusion for object detection using a pulse coupled neural network

This paper presents the first physiologically motivated pulse coupled neural network (PCNN)-based image fusion network for object detection. Primate vision processing principles, such as expectation driven filtering, state dependent modulation, temporal synchronization, and multiple processing paths are applied to create a physiologically motivated image fusion network. PCNN's are used to fuse ...

متن کامل

Color Image Segmentation Using Pulse-Coupled Neural Network for Locusts Detection

Pulse-coupled neural network (PCNN) is different from traditional artificial neural networks, which can be applied in many fields, such as image processing. A crucial step in developing automated locust detection system is image segmentation, which aims to identify locusts from images. In this study, a simplified PCNN algorithm was proposed for this purpose. Color images are either converted to...

متن کامل

A Convolutional Neural Network based on Adaptive Pooling for Classification of Noisy Images

Convolutional neural network is one of the effective methods for classifying images that performs learning using convolutional, pooling and fully-connected layers. All kinds of noise disrupt the operation of this network. Noise images reduce classification accuracy and increase convolutional neural network training time. Noise is an unwanted signal that destroys the original signal. Noise chang...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2016