optical character recognition using EasyOCR

EasyOCR/model/craft_mlt_25k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a5efbfb48b4081100544e75e1e2b57f8de3d84f213004b14b85fd4b3748db17
+size 83152330

EasyOCR/model/english_g2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2272681d9d67a04e2dff396b6e95077bc19001f8f6d3593c307b9852e1c29e8
+size 15143997

app.py

@@ -0,0 +1,61 @@
+
+import numpy as np
+import streamlit as st
+from PIL import Image, ImageOps
+import cv2
+from utils import OCR
+
+
+alert = False
+ocr = None
+
+st.title("Optical Character Recognition")
+
+tab_upload, tab_cam = st.tabs(['Upload', 'Camera'])
+
+with tab_upload:
+    image_upload = st.file_uploader(
+        label='Upload the Image', type=['jpg', 'jpeg', 'png'])
+
+with tab_cam:
+    image_webcam = st.camera_input(
+        label="Take a picture 📷")
+if image_upload:
+    image = Image.open(image_upload)
+elif image_webcam:
+    image = Image.open(image_webcam)
+else:
+    image = Image.open('./Images/sample_image_1.jpg')
+
+st.image(image=ImageOps.scale(image, factor=0.2))
+
+if st.button('Detect'):
+
+    try:
+        pass
+        ocr = OCR(image=image)
+
+    except:
+
+        st.warning(
+            " Please use a different image.", icon="⚠")
+        alert = True
+
+
+if ocr:
+    st.caption("✨Result")
+
+    try:
+        st.pyplot(fig=ocr.detection(), use_container_width=True)
+    except:
+        st.warning(
+            " Please use a different image", icon="⚠")
+
+
+else:
+    st.caption('Just click the Detect button')
+    if alert:
+        st.warning(
+            " Please use a different image.", icon="⚠")
+
+    st.image(image)

requirements.txt

@@ -0,0 +1,75 @@
+altair==5.0.1
+attrs==23.1.0
+blinker==1.6.2
+cachetools==5.3.1
+certifi==2023.7.22
+charset-normalizer==3.2.0
+click==8.1.6
+colorama==0.4.6
+contourpy==1.1.0
+cycler==0.11.0
+decorator==5.1.1
+easyocr==1.7.0
+filelock==3.12.2
+fonttools==4.42.0
+gitdb==4.0.10
+GitPython==3.1.32
+idna==3.4
+imageio==2.31.1
+importlib-metadata==6.8.0
+Jinja2==3.1.2
+jsonschema==4.19.0
+jsonschema-specifications==2023.7.1
+kiwisolver==1.4.4
+lazy_loader==0.3
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+matplotlib==3.7.2
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.1
+ninja==1.11.1
+numpy==1.25.2
+opencv-python-headless==4.8.0.74
+packaging==23.1
+pandas==2.0.3
+Pillow==9.5.0
+protobuf==4.23.4
+pyarrow==12.0.1
+pyclipper==1.3.0.post4
+pydeck==0.8.0
+Pygments==2.16.1
+Pympler==1.0.1
+pyparsing==3.0.9
+python-bidi==0.4.2
+python-dateutil==2.8.2
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+PyWavelets==1.4.1
+PyYAML==6.0.1
+referencing==0.30.2
+requests==2.31.0
+rich==13.5.2
+rpds-py==0.9.2
+scikit-image==0.21.0
+scipy==1.11.1
+shapely==2.0.1
+six==1.16.0
+smmap==5.0.0
+streamlit==1.25.0
+sympy==1.12
+tenacity==8.2.2
+tifffile==2023.7.18
+toml==0.10.2
+toolz==0.12.0
+torch==2.0.1
+torchaudio==2.0.2
+torchvision==0.15.2
+tornado==6.3.2
+typing_extensions==4.7.1
+tzdata==2023.3
+tzlocal==4.3.1
+urllib3==2.0.4
+validators==0.20.0
+watchdog==3.0.0
+zipp==3.16.2

utils.py

@@ -0,0 +1,110 @@
+import matplotlib.pyplot as plt
+import numpy as np
+import cv2
+import easyocr
+
+
+class OCR:
+    def __init__(self, image) -> None:
+        self.image = image
+        self.reader = easyocr.Reader(
+            lang_list=['en'],
+            gpu=False,
+            model_storage_directory='./EasyOCR/model/',
+            download_enabled=False,
+            user_network_directory='./EasyOCR/user_network/'
+        )
+
+    def detection(self):
+        img_arr = np.array(self.image, dtype=np.uint8)
+        response = self.reader.readtext(image=img_arr)
+        plot_inputs = []
+
+        for box, text, conf in response:
+            plot_inputs.append((text, np.array(box, dtype=np.float32)))
+
+        fig, ax = plt.subplots(nrows=1, ncols=1)
+        plot = self.drawAnnotations(
+            image=img_arr, predictions=plot_inputs, ax=ax)
+        return fig
+
+    def drawAnnotations(self, image, predictions, ax=None):
+        """Draw text annotations onto image.
+
+        Args:
+            image: The image on which to draw
+            predictions: The predictions as provided by `pipeline.recognize`.
+            ax: A matplotlib axis on which to draw.
+        """
+        if ax is None:
+            _, ax = plt.subplots()
+        ax.imshow(self.drawBoxes(image=image, boxes=predictions,
+                                 boxes_format="predictions"))
+        predictions = sorted(predictions, key=lambda p: p[1][:, 1].min())
+        left = []
+        right = []
+        for word, box in predictions:
+            if box[:, 0].min() < image.shape[1] / 2:
+                left.append((word, box))
+            else:
+                right.append((word, box))
+        ax.set_yticks([])
+        ax.set_xticks([])
+        for side, group in zip(["left", "right"], [left, right]):
+            for index, (text, box) in enumerate(group):
+                y = 1 - (index / len(group))
+                xy = box[0] / np.array([image.shape[1], image.shape[0]])
+                xy[1] = 1 - xy[1]
+                ax.annotate(
+                    text=text,
+                    xy=xy,
+                    xytext=(-0.05 if side == "left" else 1.05, y),
+                    xycoords="axes fraction",
+                    arrowprops={"arrowstyle": "->", "color": "r"},
+                    color="r",
+                    fontsize=14,
+                    horizontalalignment="right" if side == "left" else "left",
+                )
+        return ax
+
+    def drawBoxes(self, image, boxes, color=(255, 0, 0), thickness=1, boxes_format="boxes"):
+        """Draw boxes onto an image.
+
+        Args:
+            image: The image on which to draw the boxes.
+            boxes: The boxes to draw.
+            color: The color for each box.
+            thickness: The thickness for each box.
+            boxes_format: The format used for providing the boxes. Options are
+                "boxes" which indicates an array with shape(N, 4, 2) where N is the
+                number of boxes and each box is a list of four points) as provided
+                by `keras_ocr.detection.Detector.detect`, "lines" (a list of
+                lines where each line itself is a list of (box, character) tuples) as
+                provided by `keras_ocr.data_generation.get_image_generator`,
+                or "predictions" where boxes is by itself a list of (word, box) tuples
+                as provided by `keras_ocr.pipeline.Pipeline.recognize` or
+                `keras_ocr.recognition.Recognizer.recognize_from_boxes`.
+        """
+        if len(boxes) == 0:
+            return image
+        canvas = image.copy()
+        if boxes_format == "lines":
+            revised_boxes = []
+            for line in boxes:
+                for box, _ in line:
+                    revised_boxes.append(box)
+            boxes = revised_boxes
+        if boxes_format == "predictions":
+            revised_boxes = []
+            for _, box in boxes:
+                revised_boxes.append(box)
+            boxes = revised_boxes
+        for box in boxes:
+            cv2.polylines(
+                img=canvas,
+                pts=box[np.newaxis].astype("int32"),
+                color=color,
+                thickness=thickness,
+                isClosed=True,
+            )
+        return canvas