---
title: "Detect salient regions"
method: POST
path: "/v1/apple/saliency"
tags: ["Apple"]
---

# Detect salient regions

`POST /v1/apple/saliency`

## Request

- Base URL: `http://localhost:9998`
- URL: `http://localhost:9998/v1/apple/saliency`
- Auth: HTTP bearer

Generates attention-based or objectness-based saliency analysis.
Returns bounding boxes of visually significant regions.

## Request body

- object
  - `image` string, required: Base64-encoded image data (PNG, JPEG, TIFF, HEIC)
  - `type` 'attention' | 'objectness'

## Response `200`

Salient regions

- object
  - `type` string
  - `salient_objects` object[]
    - `bounding_box` BoundingBox: Normalized coordinates (0–1), bottom-left origin
      - `x` number, required
      - `y` number, required
      - `width` number, required
      - `height` number, required
    - `confidence` number

## Other responses

- `400`: Invalid request

---

[API](https://skmtc.dev/modelpiper/apis/toolpiper-api.md) · [All operations](https://skmtc.dev/modelpiper/apis/toolpiper-api/llms.txt) · [OpenAPI document](https://skmtc.dev/modelpiper/apis/toolpiper-api/revisions/6722bf56385c?raw)