uncomment table detection

app.py

@@ -640,61 +640,60 @@ class TableExtractionPipeline():
 
         caption_ocr_res = await asyncio.gather(*sequential_caption_img_list)
         flag_caption_pos = 0 # 0=top, 1=bottom
-        for idx, caption_text in enumerate(caption_ocr_res):
-            if caption_text == "" or "table" not in caption_text.lower() or "表" not in caption_text.lower():
-                if idx%2==0:
-                    flag_caption_pos=1
-                break
+        if "table" in caption_ocr_res[0].lower() or "表" in caption_ocr_res[0]:
+            flag_caption_pos=0
+        else:
+            flag_caption_pos=1
 
         for idx, caption_text in enumerate(caption_ocr_res):
             if idx%2==flag_caption_pos:
                 c3.text(str(idx) + "_" + caption_text)
 
 
-        # for idx, unpadded_table in enumerate(cropped_img_list):
-
-        #     table = self.add_padding(unpadded_table, padd_top, padd_right,
-        #                              padd_bottom, padd_left)
-        #     # table = super_res(table)
-        #     # table = binarizeBlur_image(table)
-        #     # table = sharpen_image(table) # Test sharpen image next
-        #     # table = td_postprocess(table)
-
-        #     # table.save("result"+str(idx)+".png")
-
-        #     probas, bboxes_scaled = table_struct_recog(
-        #         table, THRESHOLD_PROBA=TSR_THRESHOLD)
-        #     rows, cols = self.generate_structure(c2, table_recognition_model,
-        #                                          table, probas, bboxes_scaled,
-        #                                          expand_rowcol_bbox_top,
-        #                                          expand_rowcol_bbox_bottom)
-        #     # st.write(len(rows), len(cols))
-        #     rows, cols = self.sort_table_featuresv2(rows, cols)
-        #     master_row, cols = self.individual_table_featuresv2(
-        #         table, rows, cols)
-
-        #     cells_img, max_cols, max_rows = self.object_to_cellsv2(
-        #         master_row, cols, expand_rowcol_bbox_top,
-        #         expand_rowcol_bbox_bottom, padd_left)
-
-        #     sequential_cell_img_list = []
-        #     for k, img_list in cells_img.items():
-        #         for img in img_list:
-        #             # img = super_res(img)
-        #             # img = sharpen_image(img) # Test sharpen image next
-        #             # img = binarizeBlur_image(img)
-        #             # img = self.add_padding(img, 10,10,10,10)
-        #             # plt.imshow(img)
-        #             # c3.pyplot()
-        #             sequential_cell_img_list.append(
-        #                 pytess(cell_pil_img=img, threshold=OCR_THRESHOLD))
-
-        #     cell_ocr_res = await asyncio.gather(*sequential_cell_img_list)
-
-        #     self.create_dataframe(c3, cell_ocr_res, max_cols, max_rows)
-        #     st.write(
-        #         'Errors in OCR is due to either quality of the image or performance of the OCR'
-        #     )
+        for idx, unpadded_table in enumerate(cropped_img_list):
+
+            table = self.add_padding(unpadded_table, padd_top, padd_right,
+                                     padd_bottom, padd_left)
+            # table = super_res(table)
+            # table = binarizeBlur_image(table)
+            # table = sharpen_image(table) # Test sharpen image next
+            # table = td_postprocess(table)
+
+            # table.save("result"+str(idx)+".png")
+
+            probas, bboxes_scaled = table_struct_recog(
+                table, THRESHOLD_PROBA=TSR_THRESHOLD)
+            rows, cols = self.generate_structure(c2, table_recognition_model,
+                                                 table, probas, bboxes_scaled,
+                                                 expand_rowcol_bbox_top,
+                                                 expand_rowcol_bbox_bottom)
+            # st.write(len(rows), len(cols))
+            rows, cols = self.sort_table_featuresv2(rows, cols)
+            master_row, cols = self.individual_table_featuresv2(
+                table, rows, cols)
+
+            cells_img, max_cols, max_rows = self.object_to_cellsv2(
+                master_row, cols, expand_rowcol_bbox_top,
+                expand_rowcol_bbox_bottom, padd_left)
+
+            sequential_cell_img_list = []
+            for k, img_list in cells_img.items():
+                for img in img_list:
+                    # img = super_res(img)
+                    # img = sharpen_image(img) # Test sharpen image next
+                    # img = binarizeBlur_image(img)
+                    # img = self.add_padding(img, 10,10,10,10)
+                    # plt.imshow(img)
+                    # c3.pyplot()
+                    sequential_cell_img_list.append(
+                        pytess(cell_pil_img=img, threshold=OCR_THRESHOLD))
+
+            cell_ocr_res = await asyncio.gather(*sequential_cell_img_list)
+
+            self.create_dataframe(c3, cell_ocr_res, max_cols, max_rows)
+            st.write(
+                'Errors in OCR is due to either quality of the image or performance of the OCR'
+            )
         # except:
         #     st.write('Either incorrectly identified table or no table, to debug remove try/except')
         # break