很早以前,人们就已经了解这一过程的大致情形。二十世纪80年代末,现就职于纽约大学的雅安?勒存率先涉足计算机视觉研究,试图模拟人脑视觉皮层内神经元层层递进的布线方式。
He has been tweaking his convolutional neural networks ever since.
从那时起,他就一直在调整和改良他的卷积神经网络。
Seeing is believing
眼见为实
A ConvNet begins by swiping a number of software filters, each several pixels across, overthe image, pixel by pixel.
卷积神经网络首先用几个软件滤光器,对图像逐一像素地进行扫描,每个滤光器只能通过几个像素。
Like the brain s primary visual cortex, these filters look for simple features such as edges.
就像大脑的初级视觉皮层,这些滤光器只负责收集物体边缘等简单图像特征。
The upshot is a set of feature maps, one for each filter, showing which patches of theoriginal image contain the sought-after element.
结果得到一组特征图,每一张特征图对应一个滤光器,显示出原始图像中的哪些块包含要筛选到的要素。
A series of transformations is then performed on each map in order to enhance it andimprove the contrast.
【2015考研英语阅读计算机模拟视觉】相关文章:
★ 2013年6月英语六级考试备考深度阅读试题模拟与解析(5)
最新
2016-10-18
2016-10-11
2016-10-11
2016-10-08
2016-09-30
2016-09-30