|
1307 | 1307 | "shape": "ServiceQuotaExceededException" |
1308 | 1308 | } |
1309 | 1309 | ], |
1310 | | - "documentation": "<p>Detects faces in the input image and adds them to the specified collection. </p> <p>Amazon Rekognition doesn't save the actual faces that are detected. Instead, the underlying detection algorithm first detects the faces in the input image. For each face, the algorithm extracts facial features into a feature vector, and stores it in the backend database. Amazon Rekognition uses feature vectors when it performs face match and search operations using the <a>SearchFaces</a> and <a>SearchFacesByImage</a> operations.</p> <p>For more information, see Adding Faces to a Collection in the Amazon Rekognition Developer Guide.</p> <p>To get the number of faces in a collection, call <a>DescribeCollection</a>. </p> <p>If you're using version 1.0 of the face detection model, <code>IndexFaces</code> indexes the 15 largest faces in the input image. Later versions of the face detection model index the 100 largest faces in the input image. </p> <p>If you're using version 4 or later of the face model, image orientation information is not returned in the <code>OrientationCorrection</code> field. </p> <p>To determine which version of the model you're using, call <a>DescribeCollection</a> and supply the collection ID. You can also get the model version from the value of <code>FaceModelVersion</code> in the response from <code>IndexFaces</code> </p> <p>For more information, see Model Versioning in the Amazon Rekognition Developer Guide.</p> <p>If you provide the optional <code>ExternalImageId</code> for the input image you provided, Amazon Rekognition associates this ID with all faces that it detects. When you call the <a>ListFaces</a> operation, the response returns the external ID. You can use this external image ID to create a client-side index to associate the faces with each image. You can then use the index to find all faces in an image.</p> <p>You can specify the maximum number of faces to index with the <code>MaxFaces</code> input parameter. This is useful when you want to index the largest faces in an image and don't want to index smaller faces, such as those belonging to people standing in the background.</p> <p>The <code>QualityFilter</code> input parameter allows you to filter out detected faces that don’t meet a required quality bar. The quality bar is based on a variety of common use cases. By default, <code>IndexFaces</code> chooses the quality bar that's used to filter faces. You can also explicitly choose the quality bar. Use <code>QualityFilter</code>, to set the quality bar by specifying <code>LOW</code>, <code>MEDIUM</code>, or <code>HIGH</code>. If you do not want to filter detected faces, specify <code>NONE</code>. </p> <note> <p>To use quality filtering, you need a collection associated with version 3 of the face model or higher. To get the version of the face model associated with a collection, call <a>DescribeCollection</a>. </p> </note> <p>Information about faces detected in an image, but not indexed, is returned in an array of <a>UnindexedFace</a> objects, <code>UnindexedFaces</code>. Faces aren't indexed for reasons such as:</p> <ul> <li> <p>The number of faces detected exceeds the value of the <code>MaxFaces</code> request parameter.</p> </li> <li> <p>The face is too small compared to the image dimensions.</p> </li> <li> <p>The face is too blurry.</p> </li> <li> <p>The image is too dark.</p> </li> <li> <p>The face has an extreme pose.</p> </li> <li> <p>The face doesn’t have enough detail to be suitable for face search.</p> </li> </ul> <p>In response, the <code>IndexFaces</code> operation returns an array of metadata for all detected faces, <code>FaceRecords</code>. This includes: </p> <ul> <li> <p>The bounding box, <code>BoundingBox</code>, of the detected face. </p> </li> <li> <p>A confidence value, <code>Confidence</code>, which indicates the confidence that the bounding box contains a face.</p> </li> <li> <p>A face ID, <code>FaceId</code>, assigned by the service for each face that's detected and stored.</p> </li> <li> <p>An image ID, <code>ImageId</code>, assigned by the service for the input image.</p> </li> </ul> <p>If you request all facial attributes (by using the <code>detectionAttributes</code> parameter), Amazon Rekognition returns detailed facial attributes, such as facial landmarks (for example, location of eye and mouth) and other facial attributes. If you provide the same image, specify the same collection, and use the same external ID in the <code>IndexFaces</code> operation, Amazon Rekognition doesn't save duplicate face metadata.</p> <p/> <p>The input image is passed either as base64-encoded image bytes, or as a reference to an image in an Amazon S3 bucket. If you use the AWS CLI to call Amazon Rekognition operations, passing image bytes isn't supported. The image must be formatted as a PNG or JPEG file. </p> <p>This operation requires permissions to perform the <code>rekognition:IndexFaces</code> action.</p>" |
| 1310 | + "documentation": "<p>Detects faces in the input image and adds them to the specified collection. </p> <p>Amazon Rekognition doesn't save the actual faces that are detected. Instead, the underlying detection algorithm first detects the faces in the input image. For each face, the algorithm extracts facial features into a feature vector, and stores it in the backend database. Amazon Rekognition uses feature vectors when it performs face match and search operations using the <a>SearchFaces</a> and <a>SearchFacesByImage</a> operations.</p> <p>For more information, see Adding Faces to a Collection in the Amazon Rekognition Developer Guide.</p> <p>To get the number of faces in a collection, call <a>DescribeCollection</a>. </p> <p>If you're using version 1.0 of the face detection model, <code>IndexFaces</code> indexes the 15 largest faces in the input image. Later versions of the face detection model index the 100 largest faces in the input image. </p> <p>If you're using version 4 or later of the face model, image orientation information is not returned in the <code>OrientationCorrection</code> field. </p> <p>To determine which version of the model you're using, call <a>DescribeCollection</a> and supply the collection ID. You can also get the model version from the value of <code>FaceModelVersion</code> in the response from <code>IndexFaces</code> </p> <p>For more information, see Model Versioning in the Amazon Rekognition Developer Guide.</p> <p>If you provide the optional <code>ExternalImageId</code> for the input image you provided, Amazon Rekognition associates this ID with all faces that it detects. When you call the <a>ListFaces</a> operation, the response returns the external ID. You can use this external image ID to create a client-side index to associate the faces with each image. You can then use the index to find all faces in an image.</p> <p>You can specify the maximum number of faces to index with the <code>MaxFaces</code> input parameter. This is useful when you want to index the largest faces in an image and don't want to index smaller faces, such as those belonging to people standing in the background.</p> <p>The <code>QualityFilter</code> input parameter allows you to filter out detected faces that don’t meet a required quality bar. The quality bar is based on a variety of common use cases. By default, <code>IndexFaces</code> chooses the quality bar that's used to filter faces. You can also explicitly choose the quality bar. Use <code>QualityFilter</code>, to set the quality bar by specifying <code>LOW</code>, <code>MEDIUM</code>, or <code>HIGH</code>. If you do not want to filter detected faces, specify <code>NONE</code>. </p> <note> <p>To use quality filtering, you need a collection associated with version 3 of the face model or higher. To get the version of the face model associated with a collection, call <a>DescribeCollection</a>. </p> </note> <p>Information about faces detected in an image, but not indexed, is returned in an array of <a>UnindexedFace</a> objects, <code>UnindexedFaces</code>. Faces aren't indexed for reasons such as:</p> <ul> <li> <p>The number of faces detected exceeds the value of the <code>MaxFaces</code> request parameter.</p> </li> <li> <p>The face is too small compared to the image dimensions.</p> </li> <li> <p>The face is too blurry.</p> </li> <li> <p>The image is too dark.</p> </li> <li> <p>The face has an extreme pose.</p> </li> <li> <p>The face doesn’t have enough detail to be suitable for face search.</p> </li> </ul> <p>In response, the <code>IndexFaces</code> operation returns an array of metadata for all detected faces, <code>FaceRecords</code>. This includes: </p> <ul> <li> <p>The bounding box, <code>BoundingBox</code>, of the detected face. </p> </li> <li> <p>A confidence value, <code>Confidence</code>, which indicates the confidence that the bounding box contains a face.</p> </li> <li> <p>A face ID, <code>FaceId</code>, assigned by the service for each face that's detected and stored.</p> </li> <li> <p>An image ID, <code>ImageId</code>, assigned by the service for the input image.</p> </li> </ul> <p>If you request all facial attributes (by using the <code>detectionAttributes</code> parameter), Amazon Rekognition returns detailed facial attributes, such as facial landmarks (for example, location of eye and mouth) and other facial attributes. If you provide the same image, specify the same collection, use the same external ID, and use the same model version in the <code>IndexFaces</code> operation, Amazon Rekognition doesn't save duplicate face metadata.</p> <p/> <p>The input image is passed either as base64-encoded image bytes, or as a reference to an image in an Amazon S3 bucket. If you use the AWS CLI to call Amazon Rekognition operations, passing image bytes isn't supported. The image must be formatted as a PNG or JPEG file. </p> <p>This operation requires permissions to perform the <code>rekognition:IndexFaces</code> action.</p>" |
1311 | 1311 | }, |
1312 | 1312 | "ListCollections": { |
1313 | 1313 | "name": "ListCollections", |
|
2752 | 2752 | }, |
2753 | 2753 | "FaceModelVersion": { |
2754 | 2754 | "shape": "String", |
2755 | | - "documentation": "<p>Version number of the face detection model associated with the collection you are creating.</p>" |
| 2755 | + "documentation": "<p>Latest face model being used with the collection. For more information, see <a href=\"https://docs.aws.amazon.com/rekognition/latest/dg/face-detection-model.html\">Model versioning</a>.</p>" |
2756 | 2756 | } |
2757 | 2757 | } |
2758 | 2758 | }, |
|
3839 | 3839 | "Confidence": { |
3840 | 3840 | "shape": "Percent", |
3841 | 3841 | "documentation": "<p>Confidence level that the bounding box contains a face (and not a different object such as a tree).</p>" |
| 3842 | + }, |
| 3843 | + "IndexFacesModelVersion": { |
| 3844 | + "shape": "IndexFacesModelVersion", |
| 3845 | + "documentation": "<p> The version of the face detect and storage model that was used when indexing the face vector. </p>" |
3842 | 3846 | } |
3843 | 3847 | }, |
3844 | 3848 | "documentation": "<p>Describes the face properties such as the bounding box, face ID, image ID of the input image, and external image ID that you assigned. </p>" |
|
4626 | 4630 | }, |
4627 | 4631 | "documentation": "<p>Identifies face image brightness and sharpness. </p>" |
4628 | 4632 | }, |
| 4633 | + "IndexFacesModelVersion": { |
| 4634 | + "type": "string", |
| 4635 | + "pattern": "[0-9\\.]+" |
| 4636 | + }, |
4629 | 4637 | "IndexFacesRequest": { |
4630 | 4638 | "type": "structure", |
4631 | 4639 | "required": [ |
|
4672 | 4680 | }, |
4673 | 4681 | "FaceModelVersion": { |
4674 | 4682 | "shape": "String", |
4675 | | - "documentation": "<p>The version number of the face detection model that's associated with the input collection (<code>CollectionId</code>).</p>" |
| 4683 | + "documentation": "<p>Latest face model being used with the collection. For more information, see <a href=\"https://docs.aws.amazon.com/rekognition/latest/dg/face-detection-model.html\">Model versioning</a>.</p>" |
4676 | 4684 | }, |
4677 | 4685 | "UnindexedFaces": { |
4678 | 4686 | "shape": "UnindexedFaces", |
|
4913 | 4921 | }, |
4914 | 4922 | "FaceModelVersions": { |
4915 | 4923 | "shape": "FaceModelVersionList", |
4916 | | - "documentation": "<p>Version numbers of the face detection models associated with the collections in the array <code>CollectionIds</code>. For example, the value of <code>FaceModelVersions[2]</code> is the version number for the face detection model used by the collection in <code>CollectionId[2]</code>.</p>" |
| 4924 | + "documentation": "<p>Latest face models being used with the corresponding collections in the array. For more information, see <a href=\"https://docs.aws.amazon.com/rekognition/latest/dg/face-detection-model.html\">Model versioning</a>. For example, the value of <code>FaceModelVersions[2]</code> is the version number for the face detection model used by the collection in <code>CollectionId[2]</code>.</p>" |
4917 | 4925 | } |
4918 | 4926 | } |
4919 | 4927 | }, |
|
5042 | 5050 | }, |
5043 | 5051 | "FaceModelVersion": { |
5044 | 5052 | "shape": "String", |
5045 | | - "documentation": "<p>Version number of the face detection model associated with the input collection (<code>CollectionId</code>).</p>" |
| 5053 | + "documentation": "<p>Latest face model being used with the collection. For more information, see <a href=\"https://docs.aws.amazon.com/rekognition/latest/dg/face-detection-model.html\">Model versioning</a>.</p>" |
5046 | 5054 | } |
5047 | 5055 | } |
5048 | 5056 | }, |
|
5783 | 5791 | }, |
5784 | 5792 | "FaceModelVersion": { |
5785 | 5793 | "shape": "String", |
5786 | | - "documentation": "<p>Version number of the face detection model associated with the input collection (<code>CollectionId</code>).</p>" |
| 5794 | + "documentation": "<p>Latest face model being used with the collection. For more information, see <a href=\"https://docs.aws.amazon.com/rekognition/latest/dg/face-detection-model.html\">Model versioning</a>.</p>" |
5787 | 5795 | } |
5788 | 5796 | } |
5789 | 5797 | }, |
|
5825 | 5833 | }, |
5826 | 5834 | "FaceModelVersion": { |
5827 | 5835 | "shape": "String", |
5828 | | - "documentation": "<p>Version number of the face detection model associated with the input collection (<code>CollectionId</code>).</p>" |
| 5836 | + "documentation": "<p>Latest face model being used with the collection. For more information, see <a href=\"https://docs.aws.amazon.com/rekognition/latest/dg/face-detection-model.html\">Model versioning</a>.</p>" |
5829 | 5837 | } |
5830 | 5838 | } |
5831 | 5839 | }, |
|
0 commit comments