首页|Patent Issued for Generating domain specific language expressions based on image s (USPTO 12147766)
Patent Issued for Generating domain specific language expressions based on image s (USPTO 12147766)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
From the background information supplied by the inventors, news correspondents o btained the followingquote: “Identification of plant traits in digital imagery has numerous applications. One exampleapplication is detection, classification, and/or segmentation of unwanted and/or invasive plants, such asweeds. Another example application is detection, classification, and/or segmentation of plant d isease. Yetanother example application is detection, classification, and/or seg mentation of other types of plant traits,such as plant genus or species (either of which may fall under the definition of plant “type”), phenotypictraits (e.g ., gender, strain), and so forth. Various types of machine learning models can b e trained tosegment and/or recognize various types of plant traits in digital i mages. Convolutional neural networksare one popular example. However, the accur acy of these machine learning models depends largely on theamount of training d ata used to train them. Manually annotating training images on a pixel-wise basi sand/or using bounding shapes can be prohibitively costly. Moreover, images of plants having some traitsmay not be as widely available or easily acquired as i mages of plants having other traits.”
NETL
NSTL
