AWS SDK を使用して Amazon Rekognition でイメージ内の要素を検出して表示する - AWS SDK コード例

Doc AWS SDK Examples リポジトリには、他にも SDK の例があります。 AWS GitHub

翻訳は機械翻訳により提供されています。提供された翻訳内容と英語版の間で齟齬、不一致または矛盾がある場合、英語版が優先します。

AWS SDK を使用して Amazon Rekognition でイメージ内の要素を検出して表示する

次のコードサンプルは、以下の操作方法を示しています。

  • Amazon Rekognition を使用してイメージから要素を検出します。

  • イメージを表示し、検出された要素の周囲に境界ボックスを描画します。

詳細については、境界ボックスの表示 を参照してください。

Python
SDK for Python (Boto3)
注記

の詳細については、「」を参照してください GitHub。AWS コード例リポジトリ で全く同じ例を見つけて、設定と実行の方法を確認してください。

Amazon Rekognition 関数をラップするクラスを作成します。

import logging from pprint import pprint import boto3 from botocore.exceptions import ClientError import requests from rekognition_objects import ( RekognitionFace, RekognitionCelebrity, RekognitionLabel, RekognitionModerationLabel, RekognitionText, show_bounding_boxes, show_polygons, ) logger = logging.getLogger(__name__) class RekognitionImage: """ Encapsulates an Amazon Rekognition image. This class is a thin wrapper around parts of the Boto3 Amazon Rekognition API. """ def __init__(self, image, image_name, rekognition_client): """ Initializes the image object. :param image: Data that defines the image, either the image bytes or an Amazon S3 bucket and object key. :param image_name: The name of the image. :param rekognition_client: A Boto3 Rekognition client. """ self.image = image self.image_name = image_name self.rekognition_client = rekognition_client @classmethod def from_file(cls, image_file_name, rekognition_client, image_name=None): """ Creates a RekognitionImage object from a local file. :param image_file_name: The file name of the image. The file is opened and its bytes are read. :param rekognition_client: A Boto3 Rekognition client. :param image_name: The name of the image. If this is not specified, the file name is used as the image name. :return: The RekognitionImage object, initialized with image bytes from the file. """ with open(image_file_name, "rb") as img_file: image = {"Bytes": img_file.read()} name = image_file_name if image_name is None else image_name return cls(image, name, rekognition_client) @classmethod def from_bucket(cls, s3_object, rekognition_client): """ Creates a RekognitionImage object from an Amazon S3 object. :param s3_object: An Amazon S3 object that identifies the image. The image is not retrieved until needed for a later call. :param rekognition_client: A Boto3 Rekognition client. :return: The RekognitionImage object, initialized with Amazon S3 object data. """ image = {"S3Object": {"Bucket": s3_object.bucket_name, "Name": s3_object.key}} return cls(image, s3_object.key, rekognition_client) def detect_faces(self): """ Detects faces in the image. :return: The list of faces found in the image. """ try: response = self.rekognition_client.detect_faces( Image=self.image, Attributes=["ALL"] ) faces = [RekognitionFace(face) for face in response["FaceDetails"]] logger.info("Detected %s faces.", len(faces)) except ClientError: logger.exception("Couldn't detect faces in %s.", self.image_name) raise else: return faces def detect_labels(self, max_labels): """ Detects labels in the image. Labels are objects and people. :param max_labels: The maximum number of labels to return. :return: The list of labels detected in the image. """ try: response = self.rekognition_client.detect_labels( Image=self.image, MaxLabels=max_labels ) labels = [RekognitionLabel(label) for label in response["Labels"]] logger.info("Found %s labels in %s.", len(labels), self.image_name) except ClientError: logger.info("Couldn't detect labels in %s.", self.image_name) raise else: return labels def recognize_celebrities(self): """ Detects celebrities in the image. :return: A tuple. The first element is the list of celebrities found in the image. The second element is the list of faces that were detected but did not match any known celebrities. """ try: response = self.rekognition_client.recognize_celebrities(Image=self.image) celebrities = [ RekognitionCelebrity(celeb) for celeb in response["CelebrityFaces"] ] other_faces = [ RekognitionFace(face) for face in response["UnrecognizedFaces"] ] logger.info( "Found %s celebrities and %s other faces in %s.", len(celebrities), len(other_faces), self.image_name, ) except ClientError: logger.exception("Couldn't detect celebrities in %s.", self.image_name) raise else: return celebrities, other_faces def compare_faces(self, target_image, similarity): """ Compares faces in the image with the largest face in the target image. :param target_image: The target image to compare against. :param similarity: Faces in the image must have a similarity value greater than this value to be included in the results. :return: A tuple. The first element is the list of faces that match the reference image. The second element is the list of faces that have a similarity value below the specified threshold. """ try: response = self.rekognition_client.compare_faces( SourceImage=self.image, TargetImage=target_image.image, SimilarityThreshold=similarity, ) matches = [ RekognitionFace(match["Face"]) for match in response["FaceMatches"] ] unmatches = [RekognitionFace(face) for face in response["UnmatchedFaces"]] logger.info( "Found %s matched faces and %s unmatched faces.", len(matches), len(unmatches), ) except ClientError: logger.exception( "Couldn't match faces from %s to %s.", self.image_name, target_image.image_name, ) raise else: return matches, unmatches def detect_moderation_labels(self): """ Detects moderation labels in the image. Moderation labels identify content that may be inappropriate for some audiences. :return: The list of moderation labels found in the image. """ try: response = self.rekognition_client.detect_moderation_labels( Image=self.image ) labels = [ RekognitionModerationLabel(label) for label in response["ModerationLabels"] ] logger.info( "Found %s moderation labels in %s.", len(labels), self.image_name ) except ClientError: logger.exception( "Couldn't detect moderation labels in %s.", self.image_name ) raise else: return labels def detect_text(self): """ Detects text in the image. :return The list of text elements found in the image. """ try: response = self.rekognition_client.detect_text(Image=self.image) texts = [RekognitionText(text) for text in response["TextDetections"]] logger.info("Found %s texts in %s.", len(texts), self.image_name) except ClientError: logger.exception("Couldn't detect text in %s.", self.image_name) raise else: return texts

境界ボックスとポリゴンを描画するヘルパー関数を作成します。

import io import logging from PIL import Image, ImageDraw logger = logging.getLogger(__name__) def show_bounding_boxes(image_bytes, box_sets, colors): """ Draws bounding boxes on an image and shows it with the default image viewer. :param image_bytes: The image to draw, as bytes. :param box_sets: A list of lists of bounding boxes to draw on the image. :param colors: A list of colors to use to draw the bounding boxes. """ image = Image.open(io.BytesIO(image_bytes)) draw = ImageDraw.Draw(image) for boxes, color in zip(box_sets, colors): for box in boxes: left = image.width * box["Left"] top = image.height * box["Top"] right = (image.width * box["Width"]) + left bottom = (image.height * box["Height"]) + top draw.rectangle([left, top, right, bottom], outline=color, width=3) image.show() def show_polygons(image_bytes, polygons, color): """ Draws polygons on an image and shows it with the default image viewer. :param image_bytes: The image to draw, as bytes. :param polygons: The list of polygons to draw on the image. :param color: The color to use to draw the polygons. """ image = Image.open(io.BytesIO(image_bytes)) draw = ImageDraw.Draw(image) for polygon in polygons: draw.polygon( [ (image.width * point["X"], image.height * point["Y"]) for point in polygon ], outline=color, ) image.show()

Amazon Rekognition から返されたオブジェクトを解析するクラスを作成します。

class RekognitionFace: """Encapsulates an Amazon Rekognition face.""" def __init__(self, face, timestamp=None): """ Initializes the face object. :param face: Face data, in the format returned by Amazon Rekognition functions. :param timestamp: The time when the face was detected, if the face was detected in a video. """ self.bounding_box = face.get("BoundingBox") self.confidence = face.get("Confidence") self.landmarks = face.get("Landmarks") self.pose = face.get("Pose") self.quality = face.get("Quality") age_range = face.get("AgeRange") if age_range is not None: self.age_range = (age_range.get("Low"), age_range.get("High")) else: self.age_range = None self.smile = face.get("Smile", {}).get("Value") self.eyeglasses = face.get("Eyeglasses", {}).get("Value") self.sunglasses = face.get("Sunglasses", {}).get("Value") self.gender = face.get("Gender", {}).get("Value", None) self.beard = face.get("Beard", {}).get("Value") self.mustache = face.get("Mustache", {}).get("Value") self.eyes_open = face.get("EyesOpen", {}).get("Value") self.mouth_open = face.get("MouthOpen", {}).get("Value") self.emotions = [ emo.get("Type") for emo in face.get("Emotions", []) if emo.get("Confidence", 0) > 50 ] self.face_id = face.get("FaceId") self.image_id = face.get("ImageId") self.timestamp = timestamp def to_dict(self): """ Renders some of the face data to a dict. :return: A dict that contains the face data. """ rendering = {} if self.bounding_box is not None: rendering["bounding_box"] = self.bounding_box if self.age_range is not None: rendering["age"] = f"{self.age_range[0]} - {self.age_range[1]}" if self.gender is not None: rendering["gender"] = self.gender if self.emotions: rendering["emotions"] = self.emotions if self.face_id is not None: rendering["face_id"] = self.face_id if self.image_id is not None: rendering["image_id"] = self.image_id if self.timestamp is not None: rendering["timestamp"] = self.timestamp has = [] if self.smile: has.append("smile") if self.eyeglasses: has.append("eyeglasses") if self.sunglasses: has.append("sunglasses") if self.beard: has.append("beard") if self.mustache: has.append("mustache") if self.eyes_open: has.append("open eyes") if self.mouth_open: has.append("open mouth") if has: rendering["has"] = has return rendering class RekognitionCelebrity: """Encapsulates an Amazon Rekognition celebrity.""" def __init__(self, celebrity, timestamp=None): """ Initializes the celebrity object. :param celebrity: Celebrity data, in the format returned by Amazon Rekognition functions. :param timestamp: The time when the celebrity was detected, if the celebrity was detected in a video. """ self.info_urls = celebrity.get("Urls") self.name = celebrity.get("Name") self.id = celebrity.get("Id") self.face = RekognitionFace(celebrity.get("Face")) self.confidence = celebrity.get("MatchConfidence") self.bounding_box = celebrity.get("BoundingBox") self.timestamp = timestamp def to_dict(self): """ Renders some of the celebrity data to a dict. :return: A dict that contains the celebrity data. """ rendering = self.face.to_dict() if self.name is not None: rendering["name"] = self.name if self.info_urls: rendering["info URLs"] = self.info_urls if self.timestamp is not None: rendering["timestamp"] = self.timestamp return rendering class RekognitionPerson: """Encapsulates an Amazon Rekognition person.""" def __init__(self, person, timestamp=None): """ Initializes the person object. :param person: Person data, in the format returned by Amazon Rekognition functions. :param timestamp: The time when the person was detected, if the person was detected in a video. """ self.index = person.get("Index") self.bounding_box = person.get("BoundingBox") face = person.get("Face") self.face = RekognitionFace(face) if face is not None else None self.timestamp = timestamp def to_dict(self): """ Renders some of the person data to a dict. :return: A dict that contains the person data. """ rendering = self.face.to_dict() if self.face is not None else {} if self.index is not None: rendering["index"] = self.index if self.bounding_box is not None: rendering["bounding_box"] = self.bounding_box if self.timestamp is not None: rendering["timestamp"] = self.timestamp return rendering class RekognitionLabel: """Encapsulates an Amazon Rekognition label.""" def __init__(self, label, timestamp=None): """ Initializes the label object. :param label: Label data, in the format returned by Amazon Rekognition functions. :param timestamp: The time when the label was detected, if the label was detected in a video. """ self.name = label.get("Name") self.confidence = label.get("Confidence") self.instances = label.get("Instances") self.parents = label.get("Parents") self.timestamp = timestamp def to_dict(self): """ Renders some of the label data to a dict. :return: A dict that contains the label data. """ rendering = {} if self.name is not None: rendering["name"] = self.name if self.timestamp is not None: rendering["timestamp"] = self.timestamp return rendering class RekognitionModerationLabel: """Encapsulates an Amazon Rekognition moderation label.""" def __init__(self, label, timestamp=None): """ Initializes the moderation label object. :param label: Label data, in the format returned by Amazon Rekognition functions. :param timestamp: The time when the moderation label was detected, if the label was detected in a video. """ self.name = label.get("Name") self.confidence = label.get("Confidence") self.parent_name = label.get("ParentName") self.timestamp = timestamp def to_dict(self): """ Renders some of the moderation label data to a dict. :return: A dict that contains the moderation label data. """ rendering = {} if self.name is not None: rendering["name"] = self.name if self.parent_name is not None: rendering["parent_name"] = self.parent_name if self.timestamp is not None: rendering["timestamp"] = self.timestamp return rendering class RekognitionText: """Encapsulates an Amazon Rekognition text element.""" def __init__(self, text_data): """ Initializes the text object. :param text_data: Text data, in the format returned by Amazon Rekognition functions. """ self.text = text_data.get("DetectedText") self.kind = text_data.get("Type") self.id = text_data.get("Id") self.parent_id = text_data.get("ParentId") self.confidence = text_data.get("Confidence") self.geometry = text_data.get("Geometry") def to_dict(self): """ Renders some of the text data to a dict. :return: A dict that contains the text data. """ rendering = {} if self.text is not None: rendering["text"] = self.text if self.kind is not None: rendering["kind"] = self.kind if self.geometry is not None: rendering["polygon"] = self.geometry.get("Polygon") return rendering

ラッパークラスを使用して、イメージ内の要素を検出し、その境界ボックスを表示します。この例で使用されているイメージは、手順やコード GitHub とともに にあります。

def usage_demo(): print("-" * 88) print("Welcome to the Amazon Rekognition image detection demo!") print("-" * 88) logging.basicConfig(level=logging.INFO, format="%(levelname)s: %(message)s") rekognition_client = boto3.client("rekognition") street_scene_file_name = ".media/pexels-kaique-rocha-109919.jpg" celebrity_file_name = ".media/pexels-pixabay-53370.jpg" one_girl_url = "https://dhei5unw3vrsx.cloudfront.net/images/source3_resized.jpg" three_girls_url = "https://dhei5unw3vrsx.cloudfront.net/images/target3_resized.jpg" swimwear_object = boto3.resource("s3").Object( "console-sample-images-pdx", "yoga_swimwear.jpg" ) book_file_name = ".media/pexels-christina-morillo-1181671.jpg" street_scene_image = RekognitionImage.from_file( street_scene_file_name, rekognition_client ) print(f"Detecting faces in {street_scene_image.image_name}...") faces = street_scene_image.detect_faces() print(f"Found {len(faces)} faces, here are the first three.") for face in faces[:3]: pprint(face.to_dict()) show_bounding_boxes( street_scene_image.image["Bytes"], [[face.bounding_box for face in faces]], ["aqua"], ) input("Press Enter to continue.") print(f"Detecting labels in {street_scene_image.image_name}...") labels = street_scene_image.detect_labels(100) print(f"Found {len(labels)} labels.") for label in labels: pprint(label.to_dict()) names = [] box_sets = [] colors = ["aqua", "red", "white", "blue", "yellow", "green"] for label in labels: if label.instances: names.append(label.name) box_sets.append([inst["BoundingBox"] for inst in label.instances]) print(f"Showing bounding boxes for {names} in {colors[:len(names)]}.") show_bounding_boxes( street_scene_image.image["Bytes"], box_sets, colors[: len(names)] ) input("Press Enter to continue.") celebrity_image = RekognitionImage.from_file( celebrity_file_name, rekognition_client ) print(f"Detecting celebrities in {celebrity_image.image_name}...") celebs, others = celebrity_image.recognize_celebrities() print(f"Found {len(celebs)} celebrities.") for celeb in celebs: pprint(celeb.to_dict()) show_bounding_boxes( celebrity_image.image["Bytes"], [[celeb.face.bounding_box for celeb in celebs]], ["aqua"], ) input("Press Enter to continue.") girl_image_response = requests.get(one_girl_url) girl_image = RekognitionImage( {"Bytes": girl_image_response.content}, "one-girl", rekognition_client ) group_image_response = requests.get(three_girls_url) group_image = RekognitionImage( {"Bytes": group_image_response.content}, "three-girls", rekognition_client ) print("Comparing reference face to group of faces...") matches, unmatches = girl_image.compare_faces(group_image, 80) print(f"Found {len(matches)} face matching the reference face.") show_bounding_boxes( group_image.image["Bytes"], [[match.bounding_box for match in matches]], ["aqua"], ) input("Press Enter to continue.") swimwear_image = RekognitionImage.from_bucket(swimwear_object, rekognition_client) print(f"Detecting suggestive content in {swimwear_object.key}...") labels = swimwear_image.detect_moderation_labels() print(f"Found {len(labels)} moderation labels.") for label in labels: pprint(label.to_dict()) input("Press Enter to continue.") book_image = RekognitionImage.from_file(book_file_name, rekognition_client) print(f"Detecting text in {book_image.image_name}...") texts = book_image.detect_text() print(f"Found {len(texts)} text instances. Here are the first seven:") for text in texts[:7]: pprint(text.to_dict()) show_polygons( book_image.image["Bytes"], [text.geometry["Polygon"] for text in texts], "aqua" ) print("Thanks for watching!") print("-" * 88)