OCR tutorial using Forte Ontologies to store data

docs/ch9.rst

@@ -6,3 +6,4 @@ Chapter 9. Tasks on Other modalities
    toc/audio_processing.md
 
    toc/image_processing.md
+   notebook_tutorial/ocr.ipynb

docs/spelling_wordlist.txt

@@ -156,3 +156,4 @@ GroupType
 PathLike
 ElementType
 customizable
+tokenizes

forte/data/ontology/top.py

@@ -878,15 +878,36 @@ def image(self):
                 "Cannot get image because image annotation is not "
                 "attached to any data pack."
             )
-        return self.pack.get_image_array(self._image_payload_idx)
+        return self.pack.get_payload_data_at(
+            Modality.Image, self._image_payload_idx
+        )
 
     @property
     def max_x(self):
-        return self.image.shape[1] - 1
+        return self._image_width - 1
 
     @property
     def max_y(self):
-        return self.image.shape[0] - 1
+        return self._image_height - 1
+
+    @property
+    def image_shape(self):
+        return (self._image_height, self._image_width)
+
+    def set_image_shape(self, width, height):
+        """
+        This function is used to set the shape of the image.
+
+        Args:
+            width: the width of the image. The unit is pixel.
+            height: the height of the image. The unit is pixel.
+        """
+        self._image_width = (  # pylint: disable=attribute-defined-outside-init
+            width
+        )
+        self._image_height = (  # pylint: disable=attribute-defined-outside-init
+            height
+        )
 
     def __eq__(self, other):
         if other is None:

forte/ontology_specs/base_ontology.json

@@ -1,6 +1,11 @@
 {
   "name": "base_ontology",
   "definitions": [
+    {
+      "entry_name": "ft.onto.base_ontology.Character",
+      "parent_entry": "forte.data.ontology.top.Annotation",
+      "description": "A span based annotation :class:`Character`, used to represent a character."
+    },
     {
       "entry_name": "ft.onto.base_ontology.Token",
       "parent_entry": "forte.data.ontology.top.Annotation",

ft/onto/base_ontology.py

@@ -26,6 +26,7 @@
 from typing import Optional
 
 __all__ = [
+    "Character",
     "Token",
     "Subword",
     "Classification",
@@ -60,6 +61,16 @@
 ]
 
 
+@dataclass
+class Character(Annotation):
+    """
+    A span based annotation :class:`Character`, used to represent a character.
+    """
+
+    def __init__(self, pack: DataPack, begin: int, end: int):
+        super().__init__(pack, begin, end)
+
+
 @dataclass
 class Token(Annotation):
     """