首页|Patent Application Titled 'Generating Domain Specific Language Expressions Based On Images' Published Online (USPTO 20240134936)
Patent Application Titled 'Generating Domain Specific Language Expressions Based On Images' Published Online (USPTO 20240134936)
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
Reporters obtained the following quote from the background information supplied by the inventors: “Identification of plant traits in digital imagery has numerou s applications. One example application is detection, classification, and/or seg mentation of unwanted and/or invasive plants, such as weeds. Another example app lication is detection, classification, and/or segmentation of plant disease. Yet another example application is detection, classification, and/or segmentation o f other types of plant traits, such as plant genus or species (either of which m ay fall under the definition of plant “type”), phenotypic traits (e.g., gender, strain), and so forth. Various types of machine learning models can be trained t o segment and/or recognize various types of plant traits in digital images. Conv olutional neural networks are one popular example. However, the accuracy of thes e machine learning models depends largely on the amount of training data used to train them. Manually annotating training images on a pixel-wise basis and/or us ing bounding shapes can be prohibitively costly. Moreover, images of plants havi ng some traits may not be as widely available or easily acquired as images of pl ants having other traits.”
NETL
NSTL
