Add pick color

pages/About.py

@@ -1,5 +1,6 @@
 import streamlit as st
 
+st.set_page_config(page_title='OCR Comparator', layout ="wide")
 st.title("OCR solutions comparator")
 
 st.write("")

pages/App.py

@@ -6,6 +6,7 @@ import plotly.express as px
 import numpy as np
 import math
 import pandas as pd
+from time import sleep
 
 import cv2
 from PIL import Image, ImageColor
@@ -59,7 +60,6 @@ def initializations():
                           (['EasyOCR', 'PPOCR', 'MMOCR', 'Tesseract'])
         dict            : names and indices of the OCR solutions
                           ({'EasyOCR': 0, 'PPOCR': 1, 'MMOCR': 2, 'Tesseract': 3})
-        tuple           : color of the detected boxes
         list of dicts   : list of languages supported by each OCR solution
         list of int     : columns for recognition details results
         dict            : confidence color scale
@@ -72,9 +72,6 @@ def initializations():
     # Columns for recognition details results
     out_cols_size = [2] + [2,1]*(len(out_reader_type_list)-1) # Except Tesseract
 
-    # Color of the detected boxes
-    out_color = (0, 76, 153)
-
     # Dicts of laguages supported by each reader
     out_dict_lang_easyocr = {'Abaza': 'abq', 'Adyghe': 'ady', 'Afrikaans': 'af', 'Angika': 'ang', \
     'Arabic': 'ar', 'Assamese': 'as', 'Avar': 'ava', 'Azerbaijani': 'az', 'Belarusian': 'be', \
@@ -156,6 +153,8 @@ def initializations():
     if 'columns_color' not in st.session_state:
         st.session_state.columns_color = ["rgb(228,26,28)"] + \
                                          ["rgb(0,0,0)" for x in out_reader_type_list[1:]]
+    if 'list_coordinates' not in st.session_state:
+        st.session_state.list_coordinates = []
 
     # Confidence color scale
     out_list_confid = list(np.arange(0,101,1))
@@ -176,7 +175,7 @@ def initializations():
     out_fig.update_layout(paper_bgcolor="white", margin=dict(b=0,r=0,t=0,l=0), xaxis_side="top", \
                           showlegend=False)
 
-    return out_reader_type_list, out_reader_type_dict, out_color, out_list_dict_lang, \
+    return out_reader_type_list, out_reader_type_dict, out_list_dict_lang, \
            out_cols_size, out_dict_back_colors, out_fig
 
 ###
@@ -250,7 +249,6 @@ def init_readers(in_list_params):
     return out_list_readers
 
 ###
-@st.experimental_memo(show_spinner=False)
 def load_image(in_image_file):
     """Load input file and open it
 
@@ -262,10 +260,17 @@ def load_image(in_image_file):
         PIL.Image   : input file opened with Pillow
         matrix      : input file opened with Opencv
     """
+
+    #if isinstance(in_image_file, str):
+    #    out_image_path = "img."+in_image_file.split('.')[-1]
+    #else:
+    #    out_image_path = "img."+in_image_file.name.split('.')[-1]
+
     if isinstance(in_image_file, str):
-        out_image_path = "img."+in_image_file.split('.')[-1]
+        out_image_path = "wrk_"+in_image_file
     else:
-        out_image_path = "img."+in_image_file.name.split('.')[-1]
+        out_image_path = "wrk_"+in_image_file.name
+
     img = Image.open(in_image_file)
     img_saved = img.save(out_image_path)
 
@@ -393,12 +398,13 @@ def cropped_1box(in_box, in_img):
 
 ###
 @st.experimental_memo(show_spinner=False)
-def tesserocr_detect(_in_img, in_params):
+def tesserocr_detect(in_image_path, _in_img, in_params):
     """Detection with Tesseract
 
     Args:
-        _in_img (PIL.Image) : image to consider
-        in_params (list)    : list with the parameters for detection
+        in_image_path (string) : locally saved image path
+        _in_img (PIL.Image)    : image to consider
+        in_params (list)       : list with the parameters for detection
 
     Returns:
         list        : list of the boxes coordinates
@@ -407,6 +413,7 @@ def tesserocr_detect(_in_img, in_params):
     try:
         dict_param = in_params[1]
         df_res = pytesseract.image_to_data(_in_img, **dict_param, output_type=Output.DATAFRAME)
+
         df_res['box'] = df_res.apply(lambda d: [[d['left'], d['top']], \
                                                 [d['left'] + d['width'], d['top']], \
                                                 [d['left'] + d['width'], d['top'] + d['height']], \
@@ -454,7 +461,7 @@ def process_detect(in_image_path, _in_list_images, _in_list_readers, in_list_par
         # Visualization
         if ppocr_boxes_coordinates:
             ppocr_image_detect = draw_detected(_in_list_images[0], ppocr_boxes_coordinates, \
-                                               in_color, 'None', 7)
+                                               in_color, 'None', 3)
         else:
             ppocr_image_detect = ppocr_status
     ##
@@ -465,19 +472,20 @@ def process_detect(in_image_path, _in_list_images, _in_list_readers, in_list_par
         # Visualization
         if mmocr_boxes_coordinates:
             mmocr_image_detect = draw_detected(_in_list_images[0], mmocr_boxes_coordinates, \
-                                               in_color, 'None', 7)
+                                               in_color, 'None', 3)
         else:
             mmocr_image_detect = mmocr_status
     ##
 
     ## ------- Tesseract Text detection
     with st.spinner('Tesseract Text detection in progress ...'):
-        tesserocr_boxes_coordinates, tesserocr_status = tesserocr_detect(_in_list_images[0], \
+        tesserocr_boxes_coordinates, tesserocr_status = tesserocr_detect(in_image_path, \
+                                                                         _in_list_images[0], \
                                                                          in_list_params[3])
         # Visualization
-        if tesserocr_boxes_coordinates:
+        if tesserocr_status == 'OK':
             tesserocr_image_detect = draw_detected(_in_list_images[0],tesserocr_boxes_coordinates,\
-                                                   in_color, 'None', 7)
+                                                   in_color, 'None', 3)
         else:
             tesserocr_image_detect = tesserocr_status
     ##
@@ -508,19 +516,22 @@ def draw_detected(in_image, in_boxes_coordinates, in_color, posit='None', in_thi
         PIL.Image : original image with detected areas
     """
     work_img = in_image.copy()
-    font = cv2.FONT_HERSHEY_SIMPLEX
-    for ind_box, box in enumerate(in_boxes_coordinates):
-        box = np.reshape(np.array(box), [-1, 1, 2]).astype(np.int64)
-        work_img = cv2.polylines(np.array(work_img), [box], True, in_color, in_thickness)
-        if posit != 'None':
-            if posit == 'top_left':
-                pos = tuple(box[0][0])
-            elif posit == 'top_right':
-                pos = tuple(box[1][0])
-            work_img = cv2.putText(work_img, str(ind_box+1), pos, font, 5.5, color, \
-                                   in_thickness,cv2.LINE_AA)
-
-    out_image_drawn = Image.fromarray(work_img)
+    if in_boxes_coordinates:
+        font = cv2.FONT_HERSHEY_SIMPLEX
+        for ind_box, box in enumerate(in_boxes_coordinates):
+            box = np.reshape(np.array(box), [-1, 1, 2]).astype(np.int64)
+            work_img = cv2.polylines(np.array(work_img), [box], True, in_color, in_thickness)
+            if posit != 'None':
+                if posit == 'top_left':
+                    pos = tuple(box[0][0])
+                elif posit == 'top_right':
+                    pos = tuple(box[1][0])
+                work_img = cv2.putText(work_img, str(ind_box+1), pos, font, 5.5, color, \
+                                    in_thickness,cv2.LINE_AA)
+
+        out_image_drawn = Image.fromarray(work_img)
+    else:
+        out_image_drawn = work_img
 
     return out_image_drawn
 
@@ -820,11 +831,16 @@ def draw_reco_images(in_image, in_boxes_coordinates, in_list_texts, in_list_conf
             list_reco_images[ind_tessocr] = \
                 cv2.rectangle(list_reco_images[ind_tessocr], (box[0][0], box[0][1]), \
                               (box[2][0], box[2][1]), rgb_color, -1)
-            list_reco_images[ind_tessocr] = \
-                cv2.putText(list_reco_images[ind_tessocr], \
-                            in_df_results_tesseract.iloc[num]['text'], \
-                            (box[0][0],int(np.round((box[0][1]+box[2][1])/2,0))), \
-                            cv2.FONT_HERSHEY_DUPLEX, in_font_scale, text_color, 2)
+            try:
+                list_reco_images[ind_tessocr] = \
+                    cv2.putText(list_reco_images[ind_tessocr], \
+                                in_df_results_tesseract.iloc[num]['text'], \
+                                (box[0][0],int(np.round((box[0][1]+box[2][1])/2,0))), \
+                                cv2.FONT_HERSHEY_DUPLEX, in_font_scale, text_color, 2)
+
+            except:
+
+                pass
 
     with show_reco.container():
         # Draw the results, 2 images per line
@@ -852,7 +868,8 @@ def draw_reco_images(in_image, in_boxes_coordinates, in_list_texts, in_list_conf
                         cols[ind_col].write(list_reco_status[ind], \
                                             use_column_width=True)
 
-        st.markdown(' 💡 Wrong font size? you can adjust it below:')
+        st.markdown(' 💡 Bad font size? you can adjust it below and refresh:')
+
 ###
 def highlight():
     """Draw recognized text on original image, for each OCR solution used
@@ -868,7 +885,6 @@ def highlight():
     Returns:
         shows the results container
     """
-    show_detect.empty()
     with show_detect.container():
         columns_size = [1 for x in reader_type_list]
         column_width  = [400 for x in reader_type_list]
@@ -906,6 +922,10 @@ def get_demo():
 
     return out_img_demo_1, out_img_demo_2
 
+###
+def raz():
+    st.session_state.list_coordinates = []
+
 ###################################################################################################
 ##   MAIN
 ###################################################################################################
@@ -925,7 +945,7 @@ st.markdown("##### *EasyOCR, PPOCR, MMOCR, Tesseract*")
 
 # Initializations
 with st.spinner("Initializations in progress ..."):
-    reader_type_list, reader_type_dict, color, list_dict_lang, \
+    reader_type_list, reader_type_dict, list_dict_lang, \
     cols_size, dict_back_colors, fig_colorscale = initializations()
     img_demo_1, img_demo_2 = get_demo()
 
@@ -942,24 +962,27 @@ tesserocr_key_lang = lang_col[3].selectbox(reader_type_list[3]+" :", list_dict_l
 tesserocr_lang = list_dict_lang[3][tesserocr_key_lang]
 
 st.markdown("#### Choose picture:")
-cols_pict = st.columns([1, 1, 2, 2])
-img_typ = cols_pict[0].radio("", ['Upload file', 'Take a picture', 'Use a demo file'], index=0)
+cols_pict = st.columns([1, 2])
+img_typ = cols_pict[0].radio("", ['Upload file', 'Take a picture', 'Use a demo file'], \
+                             index=0, on_change=raz)
 
 if img_typ == 'Upload file':
-    image_file = cols_pict[2].file_uploader("Upload a file:", type=["png","jpg","jpeg"])
+    image_file = cols_pict[1].file_uploader("Upload a file:", type=["jpg","jpeg"], on_change=raz)
 if img_typ == 'Take a picture':
-    image_file = cols_pict[2].camera_input("Take a picture:")
+    image_file = cols_pict[1].camera_input("Take a picture:", on_change=raz)
 if img_typ == 'Use a demo file':
-    cols_pict[1].markdown('###### Choose a demo file:')
-    demo_used = cols_pict[1].radio('', ['File 1', 'File 2'], index=0)
-    cols_pict[2].markdown('###### File 1')
-    cols_pict[2].image(img_demo_1, use_column_width=True)
-    cols_pict[3].markdown('###### File 2')
-    cols_pict[3].image(img_demo_2, use_column_width=True)
-    if demo_used == 'File 1':
-        image_file = 'img_demo_1.jpg'
-    else:
-        image_file = 'img_demo_2.jpg'
+    with st.expander('Choose a demo file:', expanded=True):
+        demo_used = st.radio('', ['File 1', 'File 2'], index=0, \
+                             horizontal=True, on_change=raz)
+        cols_demo = st.columns([1, 2])
+        cols_demo[0].markdown('###### File 1')
+        cols_demo[0].image(img_demo_1, width=150)
+        cols_demo[1].markdown('###### File 2')
+        cols_demo[1].image(img_demo_2, width=300)
+        if demo_used == 'File 1':
+            image_file = 'img_demo_1.jpg'
+        else:
+            image_file = 'img_demo_2.jpg'
 
 ##----------- Process input image -----------------------------------------------------------------
 if image_file is not None:
@@ -1076,6 +1099,9 @@ Use rectlar box to calculate faster, and polygonal box more accurate for curved
                     placeholder='Limit tesseract to recognize only this characters', \
                     help='Example for numbers only : 0123456789')
 
+        color_hex = col2.color_picker('Pick a color for boxes outlines', '#004C99')
+        color_part = color_hex.lstrip('#')
+        color = tuple(int(color_part[i:i+2], 16) for i in (0, 2, 4))
 
         submit_detect = st.form_submit_button("Launch detection")
 
@@ -1127,14 +1153,13 @@ Use rectlar box to calculate faster, and polygonal box more accurate for curved
                                                        list_params_det, color)
         show_info1.empty()
 
-        if 'list_readers' not in st.session_state:
-            st.session_state.list_readers = list_readers
-        if 'list_coordinates' not in st.session_state:
-            st.session_state.list_coordinates = list_coordinates
-        if 'list_images' not in st.session_state:
-            st.session_state.list_images = list_images
-        if 'list_params_det' not in st.session_state:
-            st.session_state.list_params_det = list_params_det
+        # Clear previous recognition results
+        st.session_state.df_results = pd.DataFrame([])
+
+        st.session_state.list_readers = list_readers
+        st.session_state.list_coordinates = list_coordinates
+        st.session_state.list_images = list_images
+        st.session_state.list_params_det = list_params_det
 
         if 'columns_size' not in st.session_state:
             st.session_state.columns_size = [2] + [1 for x in reader_type_list[1:]]
@@ -1144,7 +1169,7 @@ Use rectlar box to calculate faster, and polygonal box more accurate for curved
             st.session_state.columns_color = ["rgb(228,26,28)"] + \
                                              ["rgb(0,0,0)" for x in reader_type_list[1:]]
 
-    if 'list_coordinates' in st.session_state:
+    if st.session_state.list_coordinates:
         list_coordinates = st.session_state.list_coordinates
         list_images = st.session_state.list_images
         list_readers = st.session_state.list_readers
@@ -1310,81 +1335,82 @@ Use rectlar box to calculate faster, and polygonal box more accurate for curved
             st.session_state.list_reco_status = list_reco_status
 
         if 'df_results' in st.session_state:
+            if not st.session_state.df_results.empty:
 ##----------- Show recognition results ------------------------------------------------------------
-            results_cols = st.session_state.df_results.columns
-            list_col_text = np.arange(1, len(cols_size), 2)
-            list_col_confid = np.arange(2, len(cols_size), 2)
-
-            dict_draw_reco = {'in_image': st.session_state.list_images[1], \
-                              'in_boxes_coordinates': st.session_state.list_boxes, \
-                              'in_list_texts': [st.session_state.df_results[x].to_list() \
-                                                for x in results_cols[list_col_text]], \
-                              'in_list_confid': [st.session_state.df_results[x].to_list() \
-                                                for x in results_cols[list_col_confid]], \
-                              'in_dict_back_colors': dict_back_colors, \
-                              'in_df_results_tesseract' : st.session_state.df_results_tesseract, \
-                              'in_reader_type_list': reader_type_list
-                              }
-            show_reco = st.empty()
-
-            with st.form("form3"):
-                st.plotly_chart(fig_colorscale, use_container_width=True)
-
-                col_font, col_threshold = st.columns(2)
-
-                col_font.slider('Font scale', 1, 7, 4, step=1, key="font_scale_sld")
-                col_threshold.slider('% confidence threshold for text color change', 40, 100, 64, \
-                                    step=1, key="conf_threshold_sld")
-                col_threshold.write("(text color is black below this % confidence threshold, \
-                                     and white above)")
-
-                draw_reco_images(**dict_draw_reco)
-
-                submit_resize = st.form_submit_button("Refresh")
-
-            if submit_resize:
-                draw_reco_images(**dict_draw_reco, \
-                                        in_font_scale=st.session_state.font_scale_sld, \
-                                        in_conf_threshold=st.session_state.conf_threshold_sld)
-
-            st.subheader("Recognition details")
-            with st.expander("Detailed areas for EasyOCR, PPOCR, MMOCR", expanded=True):
-                cols = st.columns(cols_size)
-                cols[0].markdown('#### Detected area')
-                for i in range(1, (len(reader_type_list)-1)*2, 2):
-                    cols[i].markdown('#### with ' + reader_type_list[i//2])
-
-                for row in st.session_state.df_results.itertuples():
-                    #cols = st.columns(1 + len(reader_type_list)*2)
+                results_cols = st.session_state.df_results.columns
+                list_col_text = np.arange(1, len(cols_size), 2)
+                list_col_confid = np.arange(2, len(cols_size), 2)
+
+                dict_draw_reco = {'in_image': st.session_state.list_images[1], \
+                                'in_boxes_coordinates': st.session_state.list_boxes, \
+                                'in_list_texts': [st.session_state.df_results[x].to_list() \
+                                                    for x in results_cols[list_col_text]], \
+                                'in_list_confid': [st.session_state.df_results[x].to_list() \
+                                                    for x in results_cols[list_col_confid]], \
+                                'in_dict_back_colors': dict_back_colors, \
+                                'in_df_results_tesseract' : st.session_state.df_results_tesseract, \
+                                'in_reader_type_list': reader_type_list
+                                }
+                show_reco = st.empty()
+
+                with st.form("form3"):
+                    st.plotly_chart(fig_colorscale, use_container_width=True)
+
+                    col_font, col_threshold = st.columns(2)
+
+                    col_font.slider('Font scale', 1, 7, 4, step=1, key="font_scale_sld")
+                    col_threshold.slider('% confidence threshold for text color change', 40, 100, 64, \
+                                        step=1, key="conf_threshold_sld")
+                    col_threshold.write("(text color is black below this % confidence threshold, \
+                                        and white above)")
+
+                    draw_reco_images(**dict_draw_reco)
+
+                    submit_resize = st.form_submit_button("Refresh")
+
+                if submit_resize:
+                    draw_reco_images(**dict_draw_reco, \
+                                    in_font_scale=st.session_state.font_scale_sld, \
+                                    in_conf_threshold=st.session_state.conf_threshold_sld)
+
+                st.subheader("Recognition details")
+                with st.expander("Detailed areas for EasyOCR, PPOCR, MMOCR", expanded=True):
                     cols = st.columns(cols_size)
-                    cols[0].image(row.cropped_image, width=150)
-                    for ind_col in range(1, len(cols), 2):
-                        cols[ind_col].write(getattr(row, results_cols[ind_col]))
-                        cols[ind_col+1].write("("+str( \
-                            getattr(row, results_cols[ind_col+1]))+"%)")
-
-                st.download_button(
-                    label="Download results as CSV file",
-                    data=convert_df(st.session_state.df_results),
-                    file_name='OCR_comparator_results.csv',
-                    mime='text/csv',
-                )
-
-            if not st.session_state.df_results_tesseract.empty:
-                with st.expander("Detailed areas for Tesseract", expanded=False):
-                    cols = st.columns([2,2,1])
                     cols[0].markdown('#### Detected area')
-                    cols[1].markdown('#### with Tesseract')
-
-                    for row in st.session_state.df_results_tesseract.itertuples():
-                        cols = st.columns([2,2,1])
-                        cols[0].image(row.cropped, width=150)
-                        cols[1].write(getattr(row, 'text'))
-                        cols[2].write("("+str(getattr(row, 'conf'))+"%)")
+                    for i in range(1, (len(reader_type_list)-1)*2, 2):
+                        cols[i].markdown('#### with ' + reader_type_list[i//2])
+
+                    for row in st.session_state.df_results.itertuples():
+                        #cols = st.columns(1 + len(reader_type_list)*2)
+                        cols = st.columns(cols_size)
+                        cols[0].image(row.cropped_image, width=150)
+                        for ind_col in range(1, len(cols), 2):
+                            cols[ind_col].write(getattr(row, results_cols[ind_col]))
+                            cols[ind_col+1].write("("+str( \
+                                getattr(row, results_cols[ind_col+1]))+"%)")
 
                     st.download_button(
-                        label="Download Tesseract results as CSV file",
+                        label="Download results as CSV file",
                         data=convert_df(st.session_state.df_results),
-                        file_name='OCR_comparator_Tesseract_results.csv',
+                        file_name='OCR_comparator_results.csv',
                         mime='text/csv',
                     )
+
+                if not st.session_state.df_results_tesseract.empty:
+                    with st.expander("Detailed areas for Tesseract", expanded=False):
+                        cols = st.columns([2,2,1])
+                        cols[0].markdown('#### Detected area')
+                        cols[1].markdown('#### with Tesseract')
+
+                        for row in st.session_state.df_results_tesseract.itertuples():
+                            cols = st.columns([2,2,1])
+                            cols[0].image(row.cropped, width=150)
+                            cols[1].write(getattr(row, 'text'))
+                            cols[2].write("("+str(getattr(row, 'conf'))+"%)")
+
+                        st.download_button(
+                            label="Download Tesseract results as CSV file",
+                            data=convert_df(st.session_state.df_results),
+                            file_name='OCR_comparator_Tesseract_results.csv',
+                            mime='text/csv',
+                        )