Azure-Samples / Azure-Samples/document-intelligence-code-samples

Layout Model: Extract images from within images

未关闭
#116 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看
主要语言
C#
星标
201
派生
115
PR 合并指标
30 天内没有已合并 PR

描述

I have extracted images ("figures") with the Layout model successfully, but within some images there are some nested images like in this example:

Image

The pink frame surrounds a detected image but within that image, there is another image (the green leaves symbol) that is not detected by the Layout model.

The respective code example also knows just one "hierarchy" and it seems it only detects the "outer" image but not the Inner" image (i.e. the greens leave pic):

```
if result.figures:
for figures_idx,figures in enumerate(result.figures):
print(f"Figure # {figures_idx} has the following spans:{figures.spans}")
for region in figures.bounding_regions:
print(f"Figure # {figures_idx} location on page:{region.page_number} is within bounding polygon '{region.polygon}'")
```

I would like to extract the green leaves image inside the "outer" image as well.

Is that possible?

贡献指南

打开贡献指南

调研方向

未指定文件或测试。首先查看 issue #116 中的 Layout model 图示示例,并确定模型是否会暴露嵌套图像;完成意味着确定是否可以提取内部的绿叶图像,并记录或实现受支持的行为。

由索引模型根据 Issue 内容生成。

评估

技术栈
azure
领域
ai
Issue 类型
功能
难度
5/5
预计耗时
一周以上
活跃度
停滞
描述清晰度
需要澄清
新手友好度
25/100

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。