google-vision-sampler
Code examples for Google Vision API written in Python.
Description
Example codes has following features:
- Face Detection
- Landmark Detection
- Logo Detection
- Label Detection
- Text Detection
Requirement
- Python 3.x
- Credentials
Setup
To install necessary library, simply use pip:
pip install google-cloud-visionor,
pip install -r requirements.txtNext, set up to authenticate with the Cloud Vision API using your project's service account credentials. See the Vision API Client Libraries for more information. Then, set the GOOGLE_APPLICATION_CREDENTIALS environment variable to point to your downloaded service account credentials:
export GOOGLE_APPLICATION_CREDENTIALS=/path/to/your/credentials-key.jsonQuick Start: Running the Example
Face Detection
Face Detection demo using FACE_DETECTION feature.
$ python examples/face_detection.py images/face.jpg
Joy Likelihood: 1
Joy Likelihood: 5Label Detection
Label Detection demo using LABEL_DETECTION feature.
$ python examples/label_detection.py images/label.jpg
Labels:
laptop
electronic device
technology
netbook
computer keyboard
personal computer
gadgetLandmark Detection
Landmark Detection demo using LANDMARK_DETECTION feature.
$ python examples/landmark_detection.py images/landmark.jpg
Found landmark: Statue of LibertyLogo Detection
Logo Detection demo using LOGO_DETECTION feature.
$ python examples/logo_detection.py images/logo.jpg
Found logo: StarbucksText Detection
Text Detection demo using TEXT_DETECTION feature.
$ python examples/text_detection.py images/text.png
The Daily News
The martians have come at last
Lorem Ipsum is simply dummy Lorem Ipsum is simply dummy
text of the printing and typesettingext of the printing and typesetting
industry. Lorem Ipsum has been industry. Lorem Ipsum has been
the industry's standard dummy the industry's standard dummy
text ever since the 1500s, when text ever since the 1500s, whern
an unknown printer took a galley an unknown printer took a galley
of type and scrambled it to make of type and scrambled it to make
a type specimen book. It has a type specimen book. It has
survived not only five centuries survived not only five centuries
, but also the leap into electronic , but also the leap into electronic
...Image Sizing
To enable accurate image detection within the Google Cloud Vision API, images should generally be a minimum of 640 x 480 pixels (about 300k pixels). Full details for different types of Vision API Feature requests are shown below:
| Vision API Feature | Recommended Size | Notes |
|---|---|---|
| FACE_DETECTION | 1600 x 1200 | Distance between eyes is most important |
| LANDMARK_DETECTION | 640 x 480 | |
| LOGO_DETECTION | 640 x 480 | |
| LABEL_DETECTION | 640 x 480 | |
| TEXT_DETECTION | 1024 x 768 | OCR requires more resolution to detect characters |
| SAFE_SEARCH_DETECTION | 640 x 480 |