anilsathyan anilsathyan7

## README.md

      
              2 files
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                anilsathyan7
                / README.md
            
            
              Last active
              October 24, 2019 08:23
            
              
                Cluster similar patches in an image using ssim, with the help of opencv and scikit-learn
              
          
    Sample Output

Similar patches or objects in the input image(left) are grouped into same clusters, using Structural Similarity Index(SSIM).
Members of the same cluster are shown with same coloured  bounding  boxes in the output image(right).


## README.md

      
              2 files
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                anilsathyan7
                / README.md
            
            
              Last active
              October 24, 2019 08:27
            
              
                Cluster similar shapes in an image using hu moments, with the help of opencv and scikit-learn 
              
          
    Sample Output

Similar shapes in the input image(left) are grouped into same clusters, using hu moments. Members of the same cluster are shown with same coloured  bounding  boxes in the output image(right).


## image_scramble.py
import numpy as np
from PIL import Image
from imageio import imsave
from skimage.util.shape import view_as_blocks

# Global shuffle key
map={}

'''
Args:-

## convert_to_numpy.py
from PIL import Image
import os, sys
import cv2
import numpy as np

'''
Converts all images in a directory to '.npy' format.
Use np.save and np.load to save and load the images.
Use it for training your neural networks in ML/DL projects.
'''

## synthetic.py
from PIL import Image
import os, sys
from scipy.misc import imsave
import cv2
import numpy as np
import random
import argparse

'''
Creates synthetic images with custom backgrounds, using the default images and masks in the dataset.

## image_capture.py
import numpy as np
import cv2

cap = cv2.VideoCapture(0)
i=1
while(True):
	# Capture frame-by-frame
	ret, frame = cap.read()

	# Operations on the frame

## colour_cv.py
import caffe
import numpy as np
import cv2
import Image
import os

#nvcamerasrc
#gst = "/dev/video1 ! video/x-raw(memory:NVMM), width=(int)640, height=(int)480, format=(string)I420, framerate=(fraction)30/1 ! nvvidconv flip-method=0 ! video/x-raw, format=(string)I420 ! videoconvert ! video/x-raw, format=(string)BGR ! appsink"

#gst-launch-1.0 v4l2src device="/dev/video1" ! 'video/x-raw(memory:NVMM), width=(int)640, height=(int)480, format=(string)I420, framerate=(fraction)30/1' ! nvvidconv flip-method=0 ! 'video/x-raw, format=(string)I420' ! videoconvert ! 'video/x-raw, format=(string)BGR' ! fakesink

## shellscript.sh
clear
echo -e "\e[1;4mI LOVE SHELL SCRIPTING!!\n"
echo -e "WELCOME \033[31m$USER to $HOSTNAME"
$ echo -e "\033[7m Linux OS! Best OS!! \033[0m"
echo "Today is `date`"
val=`expr 6 + 3`
echo "six plus three is $val"
echo "What is your full name?"
read fname
echo "Hello $fname, my buddy!"

## index.html
<!DOCTYPE html>
<html>
  <head>
    <title>Google Realtime Quickstart</title>

    <!-- Load Styles -->
    <link href="https://www.gstatic.com/realtime/quickstart-styles.css" rel="stylesheet" type="text/css"/>

    <!-- Load the Realtime JavaScript library -->
    <script src="https://apis.google.com/js/api.js"></script>

## first.tcl
# The preamble

set ns [new Simulator]                                                               ;#initialise the simulation

# Predefine tracing
set f [open out.tr w]
$ns trace-all $f
set nf [open out.nam w]
$ns namtrace-all $nf
	import numpy as np
	from PIL import Image
	from imageio import imsave
	from skimage.util.shape import view_as_blocks

	# Global shuffle key
	map={}

	'''
	Args:-
	from PIL import Image
	import os, sys
	import cv2
	import numpy as np

	'''
	Converts all images in a directory to '.npy' format.
	Use np.save and np.load to save and load the images.
	Use it for training your neural networks in ML/DL projects.
	'''
	from PIL import Image
	import os, sys
	from scipy.misc import imsave
	import cv2
	import numpy as np
	import random
	import argparse

	'''
	Creates synthetic images with custom backgrounds, using the default images and masks in the dataset.
	import numpy as np
	import cv2

	cap = cv2.VideoCapture(0)
	i=1
	while(True):
	# Capture frame-by-frame
	ret, frame = cap.read()

	# Operations on the frame
	import caffe
	import numpy as np
	import cv2
	import Image
	import os

	#nvcamerasrc
	#gst = "/dev/video1 ! video/x-raw(memory:NVMM), width=(int)640, height=(int)480, format=(string)I420, framerate=(fraction)30/1 ! nvvidconv flip-method=0 ! video/x-raw, format=(string)I420 ! videoconvert ! video/x-raw, format=(string)BGR ! appsink"

	#gst-launch-1.0 v4l2src device="/dev/video1" ! 'video/x-raw(memory:NVMM), width=(int)640, height=(int)480, format=(string)I420, framerate=(fraction)30/1' ! nvvidconv flip-method=0 ! 'video/x-raw, format=(string)I420' ! videoconvert ! 'video/x-raw, format=(string)BGR' ! fakesink
	clear
	echo -e "\e[1;4mI LOVE SHELL SCRIPTING!!\n"
	echo -e "WELCOME \033[31m$USER to $HOSTNAME"
	$ echo -e "\033[7m Linux OS! Best OS!! \033[0m"
	echo "Today is `date`"
	val=`expr 6 + 3`
	echo "six plus three is $val"
	echo "What is your full name?"
	read fname
	echo "Hello $fname, my buddy!"
	<!DOCTYPE html>
	<html>
	<head>
	<title>Google Realtime Quickstart</title>

	<!-- Load Styles -->
	<link href="https://www.gstatic.com/realtime/quickstart-styles.css" rel="stylesheet" type="text/css"/>

	<!-- Load the Realtime JavaScript library -->
	<script src="https://apis.google.com/js/api.js"></script>
	# The preamble

	set ns [new Simulator] ;#initialise the simulation

	# Predefine tracing
	set f [open out.tr w]
	$ns trace-all $f
	set nf [open out.nam w]
	$ns namtrace-all $nf