研究目的
This paper studies the problem on the edge detection of infrared image.
研究成果
Based on the constructed spiking neural network and the characteristics of spiking neuron, a new algorithm has been designed to realize the edge detection of infrared image. Numerical simulations demonstrate the effectiveness of the given algorithm.
研究不足
The paper does not explicitly mention the limitations of the research.
1:Experimental Design and Method Selection:
A kind of spiking neural network is constructed for the edge detection of infrared image. The method utilizes the characteristics of the spiking neuron to achieve edge detection.
2:Sample Selection and Data Sources:
The infrared image of high-voltage insulator is used to verify the effectiveness of the proposed algorithm.
3:List of Experimental Equipment and Materials:
Not explicitly mentioned in the paper.
4:Experimental Procedures and Operational Workflow:
The input of neuron is the gray value of pixel, and the output is defined based on the sum of related synapse responses. The output threshold is set to determine edge points.
5:Data Analysis Methods:
The effect evaluation of edge detection image is conducted based on the 4-connected and 8-connected parts of the image, with the value of C/B used to evaluate the edge connection degree.
独家科研数据包,助您复现前沿成果,加速创新突破
获取完整内容