Techniques for determining settings for a content capture device
摘要
說(shuō)明書(shū)
In one illustrative example, the second weighting model may utilize one or more neural networks (e.g., a multilayer perceptron) to determine a weight array. In some examples, the second weighting model may create a neural network for each of one or more identified objects in an image. In such examples, inputs to a neural network may include weights similar to those described above for weight arrays. In one illustrative example, the weights may include: Object Priority—{0.1 . . . 1}; Object Size—Small, Medium or Large {0.5, 0.75, 1}; Object Distance—Near, Mid or Far {0.5, 0.75, 1}; Metering—Edge to Center {0.9 . . . 1}; Focus Reticle—In, Near or Out {0.5, 0.75 or 1}; and Eye Gaze—“At the vector”, “near the vector” or “out of the vector” {0.5, 0.75, 1}.
In the example above, the object priority weight may indicate a priority of an object. The priority of the object may be between 0 and 1. In some examples, the priority may be defined by a table as described above with respect to
The object size weight may indicate a size of an object, The size of the object may be one of an enumerated set (e.g., small, medium, or large). In some examples, a size that corresponds to each one of the enumerated set may be predefined (e.g., if an object is included in three or less pixel groups, the object is small and receives a weight of 0.5; if an object is included in four to six pixel groups, the object is medium and receives a weight of 0.75; and if an object is included in six or more pixel groups, the object is large and receives a weight of 1). In other examples, the size of the object may merely be the number of pixel groups that the object is included in.
該功能需要專(zhuān)業(yè)版企業(yè)版VIP權(quán)限，您可以：
掃描加專(zhuān)利匯官方微信交流群
