Image enhancement algorithm based on improved lateral inhibition network

Yun, Haijiao; Wu, Zhiyong; Wang, Guanjun; Gang, Tong; Yang, Hua

doi:10.1016/j.infrared.2016.03.004

Cited by 8 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the model is lightweight in scale, explicitly imposing inhibitory adjustment on features is considered to help alleviate the representational burden of deep models and improve their SR performance. For improving the quality of the image, based on an improved lateral inhibition network is proposed [ 25 ]. To realize enhanced contrast and improved edge definition in images, it built a lateral inhibition network in conjunction with biological visual perception and proposed the adaptive lateral inhibition coefficient.…”

Section: Related Workmentioning

confidence: 99%

A Parallel Spiking Neural Network Based on Adaptive Lateral Inhibition Mechanism for Objective Recognition

Dong

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Spiking neural network (SNN) has attracted extensive attention in the field of machine learning because of its biological interpretability and low power consumption. However, the accuracy of pattern recognition cannot completely surpass deep neural networks (DNNs). The main reason is that the inherent nondifferentiability of spiking neurons makes SNN unable to be trained directly by the gradient descent algorithm, and there is also no unified training algorithm for SNN. Inspired by the biological vision system, this paper proposes a parallel convolution SNN structure combined with an adaptive lateral inhibition mechanism. And, a way of dynamically evolving the time constant with the training of SNN is proposed to ensure the diversity of neurons. This paper verifies the effectiveness of the proposed methods on static datasets and neuromorphic datasets and extends it to the recognition of breast tumors. Experimental results show that the SNN has obvious advantages in dynamical datasets. For breast tumors, it is also an edge-based task, because the edge of a medical image contains the most important information in the image. This kind of information can provide great help for the noninvasive and accurate diagnosis of diseases. The Experimental results show that the proposed method is very close to the recognition results of DNNs on static datasets, and its performance on neuromorphic datasets exceeds that of DNNs.

show abstract

Section: Related Workmentioning

confidence: 99%