Add Dynamsoft Capture Vision example for MRZ detection

examples/official/README.md

@@ -0,0 +1,26 @@
+# Dynamsoft Capture Vision SDK for MRZ Detection
+This repository contains example code for using the Dynamsoft Capture Vision SDK to detect **Machine Readable Zone (MRZ)** in passport, ID card and Visa images.
+
+## Prerequisites
+- [Dynamsoft Capture Vision Trial License](https://www.dynamsoft.com/customer/license/trialLicense/?product=dcv&package=cross-platform)
+
+    ```python
+    errorCode, errorMsg = LicenseManager.init_license(
+        "LICENSE-KEY")
+    ```
+
+- SDK Installation
+
+    ```bash
+    pip install -r requirements.txt
+    ```
+
+## Supported Platforms
+- Windows
+- Linux
+- macOS
+
+
+## Examples
+- [camera.py](./camera.py): Detect MRZ from a camera video stream.
+- [file.py](./file.py): Detect MRZ from an image file and display the results in a window.

examples/official/camera.py

@@ -0,0 +1,100 @@
+from dynamsoft_capture_vision_bundle import *
+import cv2
+import numpy as np
+import queue
+from utils import *
+
+
+class FrameFetcher(ImageSourceAdapter):
+    def has_next_image_to_fetch(self) -> bool:
+        return True
+
+    def add_frame(self, imageData):
+        self.add_image_to_buffer(imageData)
+
+
+class MyCapturedResultReceiver(CapturedResultReceiver):
+    def __init__(self, result_queue):
+        super().__init__()
+        self.result_queue = result_queue
+
+    def on_captured_result_received(self, captured_result):
+        self.result_queue.put(captured_result)
+
+
+if __name__ == '__main__':
+    errorCode, errorMsg = LicenseManager.init_license(
+        "DLS2eyJoYW5kc2hha2VDb2RlIjoiMjAwMDAxLTE2NDk4Mjk3OTI2MzUiLCJvcmdhbml6YXRpb25JRCI6IjIwMDAwMSIsInNlc3Npb25QYXNzd29yZCI6IndTcGR6Vm05WDJrcEQ5YUoifQ==")
+    if errorCode != EnumErrorCode.EC_OK and errorCode != EnumErrorCode.EC_LICENSE_CACHE_USED:
+        print("License initialization failed: ErrorCode:",
+              errorCode, ", ErrorString:", errorMsg)
+    else:
+        vc = cv2.VideoCapture(0)
+        if not vc.isOpened():
+            print("Error: Camera is not opened!")
+            exit(1)
+
+        cvr = CaptureVisionRouter()
+        fetcher = FrameFetcher()
+        cvr.set_input(fetcher)
+
+        # Create a thread-safe queue to store captured items
+        result_queue = queue.Queue()
+
+        receiver = MyCapturedResultReceiver(result_queue)
+        cvr.add_result_receiver(receiver)
+
+        errorCode, errorMsg = cvr.start_capturing("ReadPassportAndId")
+
+        if errorCode != EnumErrorCode.EC_OK:
+            print("error:", errorMsg)
+
+        while True:
+            ret, frame = vc.read()
+            if not ret:
+                print("Error: Cannot read frame!")
+                break
+
+            fetcher.add_frame(convertMat2ImageData(frame))
+
+            if not result_queue.empty():
+                captured_result = result_queue.get_nowait()
+
+                items = captured_result.get_items()
+                for item in items:
+
+                    if item.get_type() == EnumCapturedResultItemType.CRIT_TEXT_LINE:
+                        text = item.get_text()
+                        line_results = text.split('\n')
+                        location = item.get_location()
+                        x1 = location.points[0].x
+                        y1 = location.points[0].y
+                        x2 = location.points[1].x
+                        y2 = location.points[1].y
+                        x3 = location.points[2].x
+                        y3 = location.points[2].y
+                        x4 = location.points[3].x
+                        y4 = location.points[3].y
+                        cv2.drawContours(
+                            frame, [np.intp([(x1, y1), (x2, y2), (x3, y3), (x4, y4)])], 0, (0, 255, 0), 2)
+
+                        delta = y3 - y1
+                        for line_result in line_results:
+                            cv2.putText(
+                                frame, line_result, (x1, y1), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 1, cv2.LINE_AA)
+                            y1 += delta
+
+                        del location
+
+                    elif item.get_type() == EnumCapturedResultItemType.CRIT_PARSED_RESULT:
+                        mrz_result = MRZResult(item)
+                        print(mrz_result.to_string())
+
+            if cv2.waitKey(1) & 0xFF == ord('q'):
+                break
+
+            cv2.imshow('frame', frame)
+
+        cvr.stop_capturing()
+        vc.release()
+        cv2.destroyAllWindows()

examples/official/file.py

@@ -0,0 +1,74 @@
+import sys
+from dynamsoft_capture_vision_bundle import *
+import os
+import cv2
+import numpy as np
+from utils import *
+
+if __name__ == '__main__':
+
+    print("**********************************************************")
+    print("Welcome to Dynamsoft Capture Vision - MRZ Sample")
+    print("**********************************************************")
+
+    error_code, error_message = LicenseManager.init_license(
+        "DLS2eyJoYW5kc2hha2VDb2RlIjoiMjAwMDAxLTE2NDk4Mjk3OTI2MzUiLCJvcmdhbml6YXRpb25JRCI6IjIwMDAwMSIsInNlc3Npb25QYXNzd29yZCI6IndTcGR6Vm05WDJrcEQ5YUoifQ==")
+    if error_code != EnumErrorCode.EC_OK and error_code != EnumErrorCode.EC_LICENSE_CACHE_USED:
+        print("License initialization failed: ErrorCode:",
+              error_code, ", ErrorString:", error_message)
+    else:
+        cvr_instance = CaptureVisionRouter()
+        while (True):
+            image_path = input(
+                ">> Input your image full path:\n"
+                ">> 'Enter' for sample image or 'Q'/'q' to quit\n"
+            ).strip('\'"')
+
+            if image_path.lower() == "q":
+                sys.exit(0)
+
+            if image_path == "":
+                image_path = "../../images/1.png"
+
+            if not os.path.exists(image_path):
+                print("The image path does not exist.")
+                continue
+            result = cvr_instance.capture(image_path, "ReadPassportAndId")
+            if result.get_error_code() != EnumErrorCode.EC_OK:
+                print("Error:", result.get_error_code(),
+                      result.get_error_string())
+            else:
+                cv_image = cv2.imread(image_path)
+
+                # Get the recognized text lines result
+                line_result = result.get_recognized_text_lines_result()
+
+                # Get the parsed result
+                parsed_result = result.get_parsed_result()
+                if parsed_result is None or len(parsed_result.get_items()) == 0:
+                    print("No parsed results.")
+                else:
+                    print_results(parsed_result)
+
+                items = line_result.get_items()
+                for item in items:
+                    location = item.get_location()
+                    x1 = location.points[0].x
+                    y1 = location.points[0].y
+                    x2 = location.points[1].x
+                    y2 = location.points[1].y
+                    x3 = location.points[2].x
+                    y3 = location.points[2].y
+                    x4 = location.points[3].x
+                    y4 = location.points[3].y
+                    del location
+
+                    cv2.drawContours(
+                        cv_image, [np.intp([(x1, y1), (x2, y2), (x3, y3), (x4, y4)])], 0, (0, 255, 0), 2)
+
+                cv2.imshow(
+                    "Original Image with Detected MRZ Zone", cv_image)
+                cv2.waitKey(0)
+                cv2.destroyAllWindows()
+
+    input("Press Enter to quit...")

examples/official/requirements.txt

@@ -0,0 +1,2 @@
+dynamsoft-capture-vision-bundle
+opencv-python

examples/official/utils.py

@@ -0,0 +1,138 @@
+from dynamsoft_capture_vision_bundle import *
+import numpy as np
+
+
+def convertImageData2Mat(normalized_image):
+    ba = bytearray(normalized_image.get_bytes())
+    width = normalized_image.get_width()
+    height = normalized_image.get_height()
+
+    channels = 3
+    if normalized_image.get_image_pixel_format() == EnumImagePixelFormat.IPF_BINARY:
+        channels = 1
+        all = []
+        skip = normalized_image.stride * 8 - width
+
+        index = 0
+        n = 1
+        for byte in ba:
+
+            byteCount = 7
+            while byteCount >= 0:
+                b = (byte & (1 << byteCount)) >> byteCount
+
+                if index < normalized_image.stride * 8 * n - skip:
+                    if b == 1:
+                        all.append(255)
+                    else:
+                        all.append(0)
+
+                byteCount -= 1
+                index += 1
+
+            if index == normalized_image.stride * 8 * n:
+                n += 1
+
+        mat = np.array(all, dtype=np.uint8).reshape(height, width, channels)
+        return mat
+
+    elif normalized_image.get_image_pixel_format() == EnumImagePixelFormat.IPF_GRAYSCALED:
+        channels = 1
+
+    mat = np.array(ba, dtype=np.uint8).reshape(height, width, channels)
+
+    return mat
+
+
+def convertMat2ImageData(mat):
+    if len(mat.shape) == 3:
+        height, width, channels = mat.shape
+        pixel_format = EnumImagePixelFormat.IPF_RGB_888
+    else:
+        height, width = mat.shape
+        channels = 1
+        pixel_format = EnumImagePixelFormat.IPF_GRAYSCALED
+
+    stride = width * channels
+    imagedata = ImageData(mat.tobytes(), width, height, stride, pixel_format)
+    return imagedata
+
+
+class MRZResult:
+    def __init__(self, item: ParsedResultItem):
+        self.doc_type = item.get_code_type()
+        self.raw_text = []
+        self.doc_id = None
+        self.surname = None
+        self.given_name = None
+        self.nationality = None
+        self.issuer = None
+        self.gender = None
+        self.date_of_birth = None
+        self.date_of_expiry = None
+        if self.doc_type == "MRTD_TD3_PASSPORT":
+            if item.get_field_value("passportNumber") != None and item.get_field_validation_status("passportNumber") != EnumValidationStatus.VS_FAILED:
+                self.doc_id = item.get_field_value("passportNumber")
+            elif item.get_field_value("documentNumber") != None and item.get_field_validation_status("documentNumber") != EnumValidationStatus.VS_FAILED:
+                self.doc_id = item.get_field_value("documentNumber")
+
+        line = item.get_field_value("line1")
+        if line is not None:
+            if item.get_field_validation_status("line1") == EnumValidationStatus.VS_FAILED:
+                line += ", Validation Failed"
+            self.raw_text.append(line)
+        line = item.get_field_value("line2")
+        if line is not None:
+            if item.get_field_validation_status("line2") == EnumValidationStatus.VS_FAILED:
+                line += ", Validation Failed"
+            self.raw_text.append(line)
+        line = item.get_field_value("line3")
+        if line is not None:
+            if item.get_field_validation_status("line3") == EnumValidationStatus.VS_FAILED:
+                line += ", Validation Failed"
+            self.raw_text.append(line)
+
+        if item.get_field_value("nationality") != None and item.get_field_validation_status("nationality") != EnumValidationStatus.VS_FAILED:
+            self.nationality = item.get_field_value("nationality")
+        if item.get_field_value("issuingState") != None and item.get_field_validation_status("issuingState") != EnumValidationStatus.VS_FAILED:
+            self.issuer = item.get_field_value("issuingState")
+        if item.get_field_value("dateOfBirth") != None and item.get_field_validation_status("dateOfBirth") != EnumValidationStatus.VS_FAILED:
+            self.date_of_birth = item.get_field_value("dateOfBirth")
+        if item.get_field_value("dateOfExpiry") != None and item.get_field_validation_status("dateOfExpiry") != EnumValidationStatus.VS_FAILED:
+            self.date_of_expiry = item.get_field_value("dateOfExpiry")
+        if item.get_field_value("sex") != None and item.get_field_validation_status("sex") != EnumValidationStatus.VS_FAILED:
+            self.gender = item.get_field_value("sex")
+        if item.get_field_value("primaryIdentifier") != None and item.get_field_validation_status("primaryIdentifier") != EnumValidationStatus.VS_FAILED:
+            self.surname = item.get_field_value("primaryIdentifier")
+        if item.get_field_value("secondaryIdentifier") != None and item.get_field_validation_status("secondaryIdentifier") != EnumValidationStatus.VS_FAILED:
+            self.given_name = item.get_field_value("secondaryIdentifier")
+
+    def to_string(self):
+        msg = (f"Raw Text:\n")
+        for index, line in enumerate(self.raw_text):
+            msg += (f"\tLine {index + 1}: {line}\n")
+        msg += (f"Parsed Information:\n"
+                f"\tDocumentType: {self.doc_type or ''}\n"
+                f"\tDocumentID: {self.doc_id or ''}\n"
+                f"\tSurname: {self.surname or ''}\n"
+                f"\tGivenName: {self.given_name or ''}\n"
+                f"\tNationality: {self.nationality or ''}\n"
+                f"\tIssuingCountryorOrganization: {self.issuer or ''}\n"
+                f"\tGender: {self.gender or ''}\n"
+                f"\tDateofBirth(YYMMDD): {self.date_of_birth or ''}\n"
+                f"\tExpirationDate(YYMMDD): {self.date_of_expiry or ''}\n")
+        return msg
+
+
+def print_results(result: ParsedResult) -> None:
+    tag = result.get_original_image_tag()
+    if isinstance(tag, FileImageTag):
+        print("File:", tag.get_file_path())
+    if result.get_error_code() != EnumErrorCode.EC_OK:
+        print("Error:", result.get_error_string())
+    else:
+        items = result.get_items()
+        print("Parsed", len(items), "MRZ Zones.")
+        for item in items:
+            mrz_result = MRZResult(item)
+            print(mrz_result.to_string())