本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。

# 建立影像的藍圖
<a name="bda-idp-images"></a>

Amazon Bedrock Data Automation (BDA) 可讓您建立影像模態的自訂藍圖。您可以使用藍圖，來定義輸入檔案所需的輸出格式和擷取邏輯。您可以透過建立自訂藍圖，量身打造可滿足特定需求的 BDA 輸出。您可以在單一專案中套用單一影像藍圖。

## 定義影像的資料欄位
<a name="bda-images-defining-data-fields"></a>

BDA 可讓您透過建立藍圖，定義要從影像中識別的特定欄位。這可作為一組指示，引導 BDA 了解要從影像中擷取和產生的資訊。

### 廣告影像的藍圖欄位範例
<a name="w2aac32c10c14c11b9b5b5"></a>

以下是一些可用來分析廣告影像的藍圖欄位範例。




|  |  |  |  | 
| --- |--- |--- |--- |
| 欄位 | 指示 | 擷取類型 | Type | 
| product\_type | What is the primary product or service being advertised? Ex: Clothing, Electronics, Food & Beverage | inferred | string | 
| product\_placement | How is the product placed in the advertisement image, e.g., centered, in the background, held by a person, etc.? | inferred | string | 
| product\_size | Product size is small if size is less than 30% of the image, medium if it is between 30 to 60%, and large if it is larger than 60% of the image | inferred | string | 
| image\_style | Classify the image style of the ad. For example, product image, lifestyle, portrait, retro, infographic, none of the above. | inferred | string | 
| image\_background | Background can be" solid color, natural landscape, indoor, outdoor, or abstract.  | inferred | string | 
| promotional\_offer | Does the advertisement include any discounts, offers, or promotional messages? | inferred | boolean | 

### 可用於媒體搜尋的藍圖欄位範例
<a name="w2aac32c10c14c11b9b5b7"></a>

以下是一些藍圖欄位範例，示範如何從影像產生中繼資料以進行媒體搜尋。




|  |  |  |  | 
| --- |--- |--- |--- |
| 欄位 | 指示 | 擷取類型 | Type | 
| person\_counting | How many people are in the image? | inferred | number | 
| indoor\_outdoor\_classification | Is the image indoor or outdoor? | inferred | string | 
| scene\_classification | Classify the setting or environment of the image. Ex: Urban, Rural, Natural, Historical, Residential, Commercial, Recreational, Public Spaces | inferred | string | 
| animal\_identification | Does the image contain any animals? | inferred | boolean | 
| animal\_type | What type of animals are present in the image? | inferred | string | 
| color\_identification | Is the image in color or black and white? | inferred | string | 
| vehicle\_identification | Is there any vehicle visible in the image? | inferred | string | 
| vehicle\_type | What type of vehicle is present in the image? | inferred | string | 
| watermark\_identification | Is there any watermark visible in the image? | inferred | boolean |