File size: 6,169 Bytes
aa13b63 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 |
import streamlit as st
import os
import pandas as pd
from dif import *
from PIL import Image
import shutil
st.set_page_config(
page_title="Duplicate Image Finder",
page_icon="🖼",
layout="wide",
initial_sidebar_state="auto",
)
@st.cache(persist=True,allow_output_mutation=False,show_spinner=True,suppress_st_warning=True)
def clean_directory(dir):
shutil.rmtree(dir)
os.makedirs(dir)
single_folder_upload_path = "single_uploads/"
multi_folder1_upload_path = "multi_uploads/folder_1/"
multi_folder2_upload_path = "multi_uploads/folder_2/"
clean_directory(single_folder_upload_path)
clean_directory(multi_folder1_upload_path)
clean_directory(multi_folder2_upload_path)
top_image = Image.open('static/banner_top__.jpg')
bottom_image = Image.open('static/banner_bottom.png')
st.sidebar.image(top_image,use_column_width='auto')
selection_choice = st.sidebar.selectbox('Search for duplicate Images under? 🎯',["Two Directories","Single Directory"])
st.sidebar.image(bottom_image,use_column_width='auto')
st.title("👨💻 Duplicate Image Finder 📷")
st.info('✨ Supports all popular image formats 📷 - PNG, JPG, BMP 😉')
if selection_choice == "Single Directory":
uploaded_files = st.file_uploader("Upload Images 🚀", type=["png","jpg","bmp","jpeg"], accept_multiple_files=True)
with st.spinner(f"Working... 💫"):
if uploaded_files:
for uploaded_file in uploaded_files:
with open(os.path.join(single_folder_upload_path,uploaded_file.name),"wb") as f:
f.write((uploaded_file).getbuffer())
search = dif("single_uploads/")
dup_imgs = [key for key in search.result.keys()]
low_res_imgs = [str(img.split("/")[-1]) for img in search.lower_quality]
stats_metrics = [search.stats[key] for key in search.stats.keys()]
time_metrics = [stats_metrics[2][key] for key in stats_metrics[2].keys()]
similarity_grade = str(stats_metrics[3])
similarity_mse = str(stats_metrics[4])
total_imgs_searched = str(stats_metrics[5])
total_imgs_found = str(stats_metrics[6])
strt_datetime = str(time_metrics[0])+ " " + str(time_metrics[1])
end_datetime = str(time_metrics[2])+ " " + str(time_metrics[3])
secs_elapsed = str(time_metrics[-1])
df = pd.DataFrame(columns = ['names of duplicate images'])
df['names of duplicate images'] = dup_imgs
df['names of lowest quality images'] = low_res_imgs
if len(total_imgs_searched) != 0:
col1, col2, col3 = st.columns(3)
col1.metric("Total Images Searched", total_imgs_searched)
col2.metric("Duplicate Images Found", total_imgs_found)
col3.metric("Lowest Quality Images Found", len(low_res_imgs))
col1.metric("Similarity Grade", similarity_grade.title())
col2.metric("Similarity MSE", similarity_mse)
col3.metric("Seconds Elapsed", secs_elapsed)
with col2:
st.markdown("<br>", unsafe_allow_html=True)
st.dataframe(df)
else:
st.warning('⚠ Please upload your images! 😯')
if selection_choice == "Two Directories":
main_col1, main_col2 = st.columns(2)
with main_col1:
multi_folder1_uploaded_files = st.file_uploader("Upload Images (folder 1)🖼", type=["png","jpg","bmp","jpeg"], accept_multiple_files=True)
with main_col2:
multi_folder2_uploaded_files = st.file_uploader("Upload Images (folder 2)🖼", type=["png","jpg","bmp","jpeg"], accept_multiple_files=True)
with st.spinner(f"Working... 💫"):
if multi_folder1_uploaded_files and multi_folder2_uploaded_files:
for uploaded_file in multi_folder1_uploaded_files:
with open(os.path.join(multi_folder1_upload_path,uploaded_file.name),"wb") as f:
f.write((uploaded_file).getbuffer())
for uploaded_file in multi_folder2_uploaded_files:
with open(os.path.join(multi_folder2_upload_path,uploaded_file.name),"wb") as f:
f.write((uploaded_file).getbuffer())
search = dif("multi_uploads/folder_1/", "multi_uploads/folder_2/")
dup_imgs = [key for key in search.result.keys()]
low_res_imgs = [str(img.split("/")[-1]) for img in search.lower_quality]
stats_metrics = [search.stats[key] for key in search.stats.keys()]
time_metrics = [stats_metrics[2][key] for key in stats_metrics[2].keys()]
similarity_grade = str(stats_metrics[3])
similarity_mse = str(stats_metrics[4])
total_imgs_searched = str(stats_metrics[5])
total_imgs_found = str(stats_metrics[6])
strt_datetime = str(time_metrics[0])+ " " + str(time_metrics[1])
end_datetime = str(time_metrics[2])+ " " + str(time_metrics[3])
secs_elapsed = str(time_metrics[-1])
df = pd.DataFrame(columns = ['names of duplicate images'])
df['names of duplicate images'] = dup_imgs
df['names of lowest quality images'] = low_res_imgs
if len(total_imgs_searched) != 0:
col1, col2, col3 = st.columns(3)
col1.metric("Total Images Searched", total_imgs_searched)
col2.metric("Duplicate Images Found", total_imgs_found)
col3.metric("Lowest Quality Images Found", len(low_res_imgs))
col1.metric("Similarity Grade", similarity_grade.title())
col2.metric("Similarity MSE", similarity_mse)
col3.metric("Seconds Elapsed", secs_elapsed)
with col2:
st.markdown("<br>", unsafe_allow_html=True)
st.dataframe(df)
else:
st.warning('⚠ Please upload your images! 😯')
st.markdown("<br><hr><center>Made with ❤️ by PROXIMA.PK ✨</center><hr>", unsafe_allow_html=True)
|