def extract_line_bounding_boxes()

in src/co_op_translator/core/vision/image_translator.py [0:0]

• 28 lines of code
• 6 McCabe index (conditional complexity)

    def extract_line_bounding_boxes(self, image_path):
        """
        Extract line bounding boxes from an image using Azure Analysis Client.

        Args:
            image_path (str): Path to the image file.

        Returns:
            list: List of dictionaries containing text, bounding box coordinates, and confidence scores.

        Raises:
            Exception: If the OCR operation did not succeed.
        """
        image_analysis_client = self.get_image_analysis_client()
        with open(image_path, "rb") as image_stream:
            image_data = image_stream.read()
            result = image_analysis_client.analyze(
                image_data=image_data,
                visual_features=[VisualFeatures.READ],
            )

        if result.read is not None and result.read.blocks:
            line_bounding_boxes = []
            for line in result.read.blocks[0].lines:
                bounding_box = []
                for point in line.bounding_polygon:
                    bounding_box.append(point.x)
                    bounding_box.append(point.y)
                line_bounding_boxes.append(
                    {
                        "text": line.text,
                        "bounding_box": bounding_box,
                        "confidence": line.words[0].confidence if line.words else None,
                    }
                )
            logger.info(
                f"Extracted {len(line_bounding_boxes)} bounding boxes from {image_path}"
            )
            return line_bounding_boxes
        else:
            raise Exception("No text was recognized in the image.")