Optical character recognition (OCR)

An OCR pipeline detects text regions and recognizes their content. Each detected region is a top-level InferenceResult with a bounding_box, and the recognized text is carried on its sub_results. See SimplifiedPipeline for the shared setup.

Python

import denkflow

pipeline = denkflow.Pipeline.from_denkflow("path/to/model.denkflow", pat="YOUR-PAT")
simplified = denkflow.SimplifiedPipeline(pipeline)

results = simplified.run("path/to/image.jpg", confidence_threshold=0.5)

for image_result in results:
    for r in image_result.results:
        for sub in r.sub_results:
            if sub.text is not None:
                print(sub.text)

C / C++

DenkflowPipeline*              pipeline    = NULL;
DenkflowSimplifiedPipeline*    simplified  = NULL;
DenkflowImageInferenceResults* results     = NULL;
DenkflowHubLicenseSource*      license     = NULL;

handle_error(denkflow_hub_license_source_from_pat(&license, "YOUR-PAT", NULL, NULL),
	"denkflow_hub_license_source_from_pat");
handle_error(denkflow_pipeline_from_denkflow(&pipeline, "path/to/model.denkflow", (void*)license),
	"denkflow_pipeline_from_denkflow");
handle_error(denkflow_simplified_pipeline_new(&simplified, &pipeline),
	"denkflow_simplified_pipeline_new");
handle_error(denkflow_simplified_pipeline_run_from_file(&results, simplified, "path/to/image.jpg", 0.5f),
	"denkflow_simplified_pipeline_run_from_file");

for (size_t b = 0; b < results->image_results_length; ++b) {
	DenkflowImageInferenceResult* image_result = &results->image_results[b];
	for (size_t i = 0; i < image_result->results_length; ++i) {
		DenkflowInferenceResult* r = &image_result->results[i];
		for (size_t s = 0; s < r->sub_results_length; ++s) {
			if (r->sub_results[s].text != NULL) {
				printf("%s\n", r->sub_results[s].text);
			}
		}
	}
}

denkflow_inference_results_free(&results);
denkflow_simplified_pipeline_free(&simplified);
denkflow_free_object((void**)&license);