首页>
外国专利>
APPARATUS AND METHOD FOR SEGMENTING OF SEMANTIC IMAGE USING FULLY CONVOLUTIONAL NEURAL NETWORK BASED ON MULTI SCALE IMAGE AND MULTI SCALE DILATED CONVOLUTION
APPARATUS AND METHOD FOR SEGMENTING OF SEMANTIC IMAGE USING FULLY CONVOLUTIONAL NEURAL NETWORK BASED ON MULTI SCALE IMAGE AND MULTI SCALE DILATED CONVOLUTION
展开▼
机译:基于多尺度图像和多尺度膨胀卷积的全卷积神经网络分割语义图像的装置和方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present invention relates to a semantic image segmentation apparatus and method using a multi-scale image and a multi-scale extended convolution-based full convolutional neural network, and the full-convolution cascade architecture of the extended convolution and a multi-scale image as input. The present invention relates to a semantic image segmentation apparatus and method using a multi-scale image and a multi-scale extended convolution-based fully convolutional neural network that enable quick and accurate segmentation of a meaningful part from a specific image through a neural network.
展开▼