Description
Object detection model trained to detect document checkboxes one of the foremost architectures in the state-of-the-art, meticulously selected through benchmark evaluations and comparative analyses. Trained on an extensive and diverse dataset, this model has been finely tuned for precise document checkbox detection and classification within documents. Its efficacy has been verified through rigorous testing, demonstrating exceptional performance in document checkbox detection across a spectrum of document formats.
Predicted Entities
Unchecked, Checked.
Live Demo Open in Colab Copy S3 URI
How to use
binary_to_image = BinaryToImage() \
.setImageType(ImageType.TYPE_3BYTE_BGR)
check_box_detector = ImageCheckBoxDetector \
.pretrained("checkbox_detector_v1", "en", "clinical/ocr") \
.setInputCol("image") \
.setLabels(["No", "Yes"]) \
.setOutputLabels(["No", "Yes"]) \
.setScoreThreshold(0.1) \
.setOutputCol("regions") \
.setOutputFormat(DetectorOutputFormat.REGIONS)
draw_regions = ImageDrawRegions() \
.setInputCol("image") \
.setInputRegionsCol("regions") \
.setOutputCol("image_with_regions") \
.setRectColor(Color.green) \
.setRotated(False)
pipeline = PipelineModel(stages=[
binary_to_image,
check_box_detector,
draw_regions
])
imagePath = 'cboxes.png'
image_df = spark.read.format("binaryFile").load(imagePath).sort("path")
result = pipeline.transform(image_df)
val binary_to_image = BinaryToImage()
.setImageType(ImageType.TYPE_3BYTE_BGR)
val check_box_detector = ImageCheckBoxDetector
.pretrained("checkbox_detector_v1", "en", "clinical/ocr")
.setInputCol("image")
.setLabels(Array("No", "Yes"))
.setOutputLabels(Array("No", "Yes"))
.setScoreThreshold(0.1)
.setOutputCol("regions")
.setOutputFormat(DetectorOutputFormat.REGIONS)
val draw_regions = ImageDrawRegions()
.setInputCol("image")
.setInputRegionsCol("regions")
.setOutputCol("image_with_regions")
.setRectColor(Color.green)
.setRotated(False)
val pipeline = new PipelineModel().setStages(Array(
binary_to_image,
check_box_detector,
draw_regions))
val imagePath = "cboxes.png"
val image_df = spark.read.format("binaryFile").load(imagePath).sort("path")
val result = pipeline.transform(image_df)
Example
Input:
Checkbox Detection:
Checkbox to text:
Model Information
| Model Name: | checkbox_detector_v1 |
| Type: | ocr |
| Compatibility: | Visual NLP 5.1.2+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |