基于非经典感受野多尺度机制的图像分析方法

Multi-scale image analysis based on Non-Classical receptive field mechanism

神经生理学研究表明,生物视觉系统比机器视觉系统在视觉信息上更加高效,这种信息处理的高效性归功于人类视觉神经中存在的多层神经网络。作为人类视觉系统的初级处理阶段,神经节细胞非经典感受野的尺寸大小可以根据外界刺激的性质进行自动调节,这种机制利用在图像处理技术上能够达到多尺度图像分析的目的。文中提出一个基于非经典感受野的多尺度图像分析方法,通过非经典感受野的自动调整机制,保留了图像的关键信息,减少了视觉系统进一步阶段的冗余信息。并通过与N-cut算法的对比和轮廓检测的实验表明这种多尺度规模图像分析模型能够给后期的图像处理任务带来一定程度的提升。

In the real world,the biological visual system is more efficient than the machine visual system in analyzing visual information.Physiology theory shows that this efficiency owes to the multi-layer neural network in human visual system,in which every layer accomplishes different tasks and is related with other layers.The low-level stages of the human visual system,especially the retina,can provide certain scale information for the high-level stages of visual system through using the non-classical receptive field(nCRF)mechanism.This mechanism that the nCRF size can be adjusted automatically by ganglion cell(GC)can achieve a multi-scale image analysis.The results,reflecting the distribution of the image information,can be shared by several algorithms or processes solving different visual tasks,such as contour detection and image segmentation.A model of multi-scale image analysis based on GC was proposed in this paper,which retains the key information and reduces the redundancy information for the further stages of the visual system.The experimental results on N-cut algorithm and contour detection show that this multi-scale image analysis model provides distinctive improvement for these image processing tasks.