Vision- grabbing source image uri in each AnnotateImageResponse from batch_annotate_images - google-cloud-platform

Question

Images are uploaded in google bucket. Code given below is running fine. It's in python3. I am trying to catch each image_uri for corresponding AnnotateImageResponse so that I can save responses in database with corresponding image uris. How can I grab input image_uri for each response? Because in each response, source image uri data not available. I may be wrong but I guess, while making requests in generate_request function, I may need to send image_uri as image_context, but not finding any good docs for that. please help.
Image files uploaded in google buckets are
'39149.7ae80cfb87bb228201e251f3e234ffde.jpg', 'anatomy_e.jpg'
def generate_request(input_image_uri):
if isinstance(input_image_uri, six.binary_type):
input_image_uri = input_image_uri.decode('utf-8')
source = {'image_uri': input_image_uri}
image = {'source': source}
features = [{"type_": vision.Feature.Type.LABEL_DETECTION},{"type_": vision.Feature.Type.FACE_DETECTION},{"type_": vision.Feature.Type.TEXT_DETECTION}]
requests = {"image": image, "features": features}
return requests
def sample_async_batch_annotate_images(input_uri):
client = vision.ImageAnnotatorClient()
requests = [
generate_request(input_uri.format(filename)) for filename in ['39149.7ae80cfb87bb228201e251f3e234ffde.jpg','anatomy_e.jpg',]
]
# below response is A BatchAnnotateFilesResponse instance.
response = client.batch_annotate_images(requests=requests)
for each in response.responses:
#each response is AnnotateImageResponse instance
print("each_response", each)
sample_async_batch_annotate_images('gs://imagevisiontest/{}')

Answer 1

I was a little bit confused on your sample_async_batch_annotate_images function since it was named asynchronous but you are not using the asynchronous method of Vision API. The response from batch_annotate_images does not return context that contains the source image_uri. Also the image_context is only used to refine your image detection like providing language hints, telling the API to search for products, etc.
I suggest using the asynchronous batch annotate method of the API as it will include context which is seen at the end of the response along with the source image_uri. Also the response is saved in the output_uri specified in the code.
I processed this image and I renamed it to image_text.jpeg for testing on batch_annotate_images and async_batch_annotate_images:
Code snippet used for batch_annotate_images:
from google.cloud import vision_v1
def sample_batch_annotate_images(
input_image_uri="gs://your_bucket_here/image_text.jpeg",
):
client = vision_v1.ImageAnnotatorClient()
source = {"image_uri": input_image_uri}
image = {"source": source}
features = [
{"type_": vision_v1.Feature.Type.LABEL_DETECTION},
{"type_": vision_v1.Feature.Type.IMAGE_PROPERTIES},
]
requests = [{"image": image, "features": features}]
response = client.batch_annotate_images(requests=requests)
print(response)
sample_batch_annotate_images()
Response from batch_annotate_images:
responses {
label_annotations {
mid: "/m/02wzbmj"
description: "Standing"
score: 0.9516521096229553
topicality: 0.9516521096229553
}
label_annotations {
mid: "/m/01mwkf"
description: "Monochrome"
score: 0.9407921433448792
topicality: 0.9407921433448792
}
label_annotations {
mid: "/m/01lynh"
description: "Stairs"
score: 0.9399806261062622
topicality: 0.9399806261062622
}
label_annotations {
mid: "/m/03scnj"
description: "Line"
score: 0.9328843951225281
topicality: 0.9328843951225281
}
label_annotations {
mid: "/m/012yh1"
description: "Style"
score: 0.9320641756057739
topicality: 0.9320641756057739
}
label_annotations {
mid: "/m/03d49p1"
description: "Monochrome photography"
score: 0.911144495010376
topicality: 0.911144495010376
}
label_annotations {
mid: "/m/01g6gs"
description: "Black-and-white"
score: 0.9031684994697571
topicality: 0.9031684994697571
}
label_annotations {
mid: "/m/019sc"
description: "Black"
score: 0.8788009881973267
topicality: 0.8788009881973267
}
label_annotations {
mid: "/m/030zfn"
description: "Parallel"
score: 0.8722482919692993
topicality: 0.8722482919692993
}
label_annotations {
mid: "/m/05wkw"
description: "Photography"
score: 0.8370979428291321
topicality: 0.8370979428291321
}
image_properties_annotation {
dominant_colors {
colors {
color {
red: 195.0
green: 195.0
blue: 195.0
}
score: 0.4464040696620941
pixel_fraction: 0.10618651658296585
}
colors {
color {
red: 117.0
green: 117.0
blue: 117.0
}
score: 0.16896472871303558
pixel_fraction: 0.1623961180448532
}
colors {
color {
red: 13.0
green: 13.0
blue: 13.0
}
score: 0.12974770367145538
pixel_fraction: 0.24307478964328766
}
colors {
color {
red: 162.0
green: 162.0
blue: 162.0
}
score: 0.11677403748035431
pixel_fraction: 0.09510618448257446
}
colors {
color {
red: 89.0
green: 89.0
blue: 89.0
}
score: 0.08708541840314865
pixel_fraction: 0.17659279704093933
}
colors {
color {
red: 225.0
green: 225.0
blue: 225.0
}
score: 0.05102387070655823
pixel_fraction: 0.012119113467633724
}
colors {
color {
red: 64.0
green: 64.0
blue: 64.0
}
score: 1.7074732738819876e-07
pixel_fraction: 0.2045244723558426
}
}
}
crop_hints_annotation {
crop_hints {
bounding_poly {
vertices {
x: 123
}
vertices {
x: 226
}
vertices {
x: 226
y: 182
}
vertices {
x: 123
y: 182
}
}
confidence: 0.4375000298023224
importance_fraction: 0.794996440410614
}
}
}
Code snippet used for async_batch_annotate_images (got the code in Vision API docs):
from google.cloud import vision_v1
def sample_async_batch_annotate_images(
input_image_uri="gs://your_bucket_here/image_text.jpeg",
output_uri="gs://your_bucket_here/",
):
"""Perform async batch image annotation."""
client = vision_v1.ImageAnnotatorClient()
source = {"image_uri": input_image_uri}
image = {"source": source}
features = [
{"type_": vision_v1.Feature.Type.LABEL_DETECTION},
{"type_": vision_v1.Feature.Type.IMAGE_PROPERTIES},
]
# Each requests element corresponds to a single image. To annotate more
# images, create a request element for each image and add it to
# the array of requests
requests = [{"image": image, "features": features}]
gcs_destination = {"uri": output_uri}
# The max number of responses to output in each JSON file
batch_size = 2
output_config = {"gcs_destination": gcs_destination,
"batch_size": batch_size}
operation = client.async_batch_annotate_images(requests=requests, output_config=output_config)
print("Waiting for operation to complete...")
response = operation.result(90)
# The output is written to GCS with the provided output_uri as prefix
gcs_output_uri = response.output_config.gcs_destination.uri
print("Output written to GCS with prefix: {}".format(gcs_output_uri))
sample_async_batch_annotate_images()
Response from async_batch_annotate_images:
{
"responses":[
{
"labelAnnotations":[
{
"mid":"/m/02wzbmj",
"description":"Standing",
"score":0.9516521,
"topicality":0.9516521
},
{
"mid":"/m/01mwkf",
"description":"Monochrome",
"score":0.94079214,
"topicality":0.94079214
},
{
"mid":"/m/01lynh",
"description":"Stairs",
"score":0.9399806,
"topicality":0.9399806
},
{
"mid":"/m/03scnj",
"description":"Line",
"score":0.9328844,
"topicality":0.9328844
},
{
"mid":"/m/012yh1",
"description":"Style",
"score":0.9320642,
"topicality":0.9320642
},
{
"mid":"/m/03d49p1",
"description":"Monochrome photography",
"score":0.9111445,
"topicality":0.9111445
},
{
"mid":"/m/01g6gs",
"description":"Black-and-white",
"score":0.9031685,
"topicality":0.9031685
},
{
"mid":"/m/019sc",
"description":"Black",
"score":0.878801,
"topicality":0.878801
},
{
"mid":"/m/030zfn",
"description":"Parallel",
"score":0.8722483,
"topicality":0.8722483
},
{
"mid":"/m/05wkw",
"description":"Photography",
"score":0.83709794,
"topicality":0.83709794
}
],
"imagePropertiesAnnotation":{
"dominantColors":{
"colors":[
{
"color":{
"red":195,
"green":195,
"blue":195
},
"score":0.44640407,
"pixelFraction":0.10618652
},
{
"color":{
"red":117,
"green":117,
"blue":117
},
"score":0.16896473,
"pixelFraction":0.16239612
},
{
"color":{
"red":13,
"green":13,
"blue":13
},
"score":0.1297477,
"pixelFraction":0.24307479
},
{
"color":{
"red":162,
"green":162,
"blue":162
},
"score":0.11677404,
"pixelFraction":0.095106184
},
{
"color":{
"red":89,
"green":89,
"blue":89
},
"score":0.08708542,
"pixelFraction":0.1765928
},
{
"color":{
"red":225,
"green":225,
"blue":225
},
"score":0.05102387,
"pixelFraction":0.0121191135
},
{
"color":{
"red":64,
"green":64,
"blue":64
},
"score":1.7074733e-07,
"pixelFraction":0.20452447
}
]
}
},
"cropHintsAnnotation":{
"cropHints":[
{
"boundingPoly":{
"vertices":[
{
"x":123
},
{
"x":226
},
{
"x":226,
"y":182
},
{
"x":123,
"y":182
}
]
},
"confidence":0.43750003,
"importanceFraction":0.79499644
}
]
},
"context":{
"uri":"gs://your_bucket_here/image_text.jpeg"
}
}
]
}