How to use Order Statistic Filters with OpenCV

[caption id="attachment_789" align="alignnone" width="471"] Order Statistic Filters[/caption]

Order Statistic filters are filters whose response is based on ordering/ranking the pixels
containing in the 3x3 window.
1. Median filter

The value of the centre pixel is replaced by the median value of its neighbourhood pixels. The median is taken after arranging the pixel values in ascending order and then taking the middle value. Use the following function,

void cvSmooth( const CvArr* src,
CvArr* dst,
int smoothtype=CV_MEDIAN,
int param1=3, int param2=3);

CV_MEDIAN (median blur) - finding median of param1×param1 neighborhood (the neighborhood is square).
2. Max filter
The max filter uses the maximum value of its neighbourhood pixels to replace the centre pixel value.

void cvDilate(const CvArr* src,
CvArr* dst,
IplConvKernel* element=NULL,
int iterations=1)

The function dilates the source image using the specified structuring element that determines the shape of a pixel neighborhood over which the maximum is taken. Image Understanding and Processing (OpenCV)

3. Minimum filter
The minimum filter uses the minimum value of its neighbourhood pixels to replace the centre pixel value.

void cvErode(const CvArr* src,
CvArr* dst,
IplConvKernel* element=NULL,
int iterations=1)

The function erodes the source image using the specified structuring element that determines the shape of a pixel neighborhood over which the minimum is taken.

Sample Code

[sourcecode language="cpp"]
#include "stdafx.h"
#include <cv.h>
#include <cxcore.h>
#include <highgui.h>

int _tmain(int argc, _TCHAR* argv[])
{

IplImage *img = cvLoadImage("apple noise.jpg");
IplImage *dst1=cvCreateImage(cvSize(img->width,img->height),8,3);

//cvSmooth(img,dst,CV_MEDIAN,3,3); Median Filter
//cvDilate(img,dst,NULL,1); Max Filter
//cvErode(img,dst,NULL,1); //Max FiltercvNamedWindow

cvNamedWindow("Image:");
cvShowImage("Image:", img);

cvNamedWindow("DST:");
cvShowImage("DST:", dst1);

cvWaitKey(0);

cvDestroyWindow("Image:");
cvReleaseImage(&img);

cvDestroyWindow("DST:");
cvReleaseImage(&dst1);

return 0;
}

[/sourcecode]

How to get TimeZone Offset in PHP

[caption id="attachment_768" align="alignnone" width="502"] timezone[/caption]

[sourcecode language="php"]
function getOffsetByTimeZone($localTimeZone)
{
$time = new DateTime(date('Y-m-d H:i:s'), new DateTimeZone($localTimeZone));
$timezoneOffset = $time->format('P');
return $timezoneOffset;
}

[/sourcecode]

Call this function passing a local time zone as a string.
eg.

getOffsetByTimeZone('America/New_York');

How to switch between Timezones in PHP

[caption id="attachment_768" align="alignnone" width="502"] timezone[/caption]

[Extracted from : http://www.mindfiresolutions.com/PHP-function-for-Time-Zone-conversion-56.php]

Convert from GMT to a local timezone

[sourcecode language="php"]
function ConvertGMTToLocalTimezone($gmttime,$timezoneRequired)
{
$system_timezone = date_default_timezone_get();

date_default_timezone_set("GMT");
$gmt = date("Y-m-d h:i:s A");

$local_timezone = $timezoneRequired;
date_default_timezone_set($local_timezone);
$local = date("Y-m-d h:i:s A");

date_default_timezone_set($system_timezone);
$diff = (strtotime($local) - strtotime($gmt));

$date = new DateTime($gmttime);
$date->modify("+$diff seconds");
$timestamp = $date->format("Y-m-d h:i:s A");
return $timestamp;

}
[/sourcecode]

Convert from local timezone to GMT

[sourcecode language="php"]
function ConvertLocalTimezoneToGMT($gmttime,$timezoneRequired)
{
$system_timezone = date_default_timezone_get();

$local_timezone = $timezoneRequired;
date_default_timezone_set($local_timezone);
$local = date("Y-m-d h:i:s A");

date_default_timezone_set("GMT");
$gmt = date("Y-m-d h:i:s A");

date_default_timezone_set($system_timezone);
$diff = (strtotime($gmt) - strtotime($local));

$date = new DateTime($gmttime);
$date->modify("+$diff seconds");
$timestamp = $date->format("Y-m-d h:i:s A");
return $timestamp;
}

[/sourcecode]

Convert from one local timezone to another local timezone


[sourcecode language="php"]
function ConvertOneTimezoneToAnotherTimezone($time,$currentTimezone,$timezoneRequired)
{
$system_timezone = date_default_timezone_get();
$local_timezone = $currentTimezone;
date_default_timezone_set($local_timezone);
$local = date("Y-m-d h:i:s A");

date_default_timezone_set("GMT");
$gmt = date("Y-m-d h:i:s A");

$require_timezone = $timezoneRequired;
date_default_timezone_set($require_timezone);
$required = date("Y-m-d h:i:s A");

date_default_timezone_set($system_timezone);

$diff1 = (strtotime($gmt) - strtotime($local));
$diff2 = (strtotime($required) - strtotime($gmt));

$date = new DateTime($time);
$date->modify("+$diff1 seconds");
$date->modify("+$diff2 seconds");
$timestamp = $date->format("Y-m-d h:i:s A");
return $timestamp;
}
[/sourcecode]
[sourcecode language="php"]
echo ConvertGMTToLocalTimezone("2013-03-16 14:28:00","Asia/Seoul")."
";
echo ConvertLocalTimezoneToGMT("2013-03-16 14:28:00","Asia/Seoul")."
";
echo ConvertOneTimezoneToAnotherTimezone("2013-03-16 14:28:00","Asia/Seoul","Australia/South");
[/sourcecode]

Python Email Crawler Class

[caption id="attachment_775" align="alignnone" width="202"] Email Crawler[/caption]

[sourcecode language="python"]
import os
import re

class EmailCrawler:
email_list = []
emailregex = re.compile('\w+[@][a-zA-Z_\.]+\.[a-zA-Z]{2,6}')
output_path = os.getcwd()

def setBaseURL(self,url):
self.tocrawl = set([url])

def run(self):
dir = raw_input('Enter the directory path for crawled files\n')
self.verifyDir(dir)
self.crawl(dir)

def output(self):
with open("emails.txt", "w") as a:
for email in self.email_list:
a.write(str(email) + os.linesep)
print email

def verifyDir(self,path):
if not os.path.exists(path):
print "This directory does not exist"
exit

def crawl(self,dir_path):
print "Crawling Email links in " + dir_path + "....\n\n"
for path, subdirs, files in os.walk(self.get_raw_string(dir_path)):
for filename in files:
filePath = os.path.join(path, filename)
f=open(filePath, 'r')
html=f.read()
f.close()
results = self.emailregex.findall(html)
if results:
for email in results:
if email not in self.email_list:
self.email_list.append(email)
self.output()

def get_raw_string(self,text):
"""Returns a raw string representation of text"""
escape_dict={'\a':r'\a',
'\b':r'\b',
'\c':r'\c',
'\f':r'\f',
'\n':r'\n',
'\r':r'\r',
'\t':r'\t',
'\v':r'\v',
'\'':r'\'',
'\"':r'\"'}

new_string=''
for char in text:
try:
new_string += escape_dict[char]
except KeyError:
new_string += char
return new_string

[/sourcecode]

How to run this email crawler?
Load and run this program in Python Shell. (In Python shell, Run >> Run Module)

import email_crawler
e = email_crawler.EmailCrawler()
e.run()

Python Web Crawler Class

[caption id="attachment_775" align="alignnone" width="202"] web crawler[/caption]

[sourcecode language="python"]
import sys
import re
import urllib2
import urlparse
import datetime
import os

class WebCrawler:
tocrawl = set([])
crawled = set([])
linkregex = re.compile('<a\s*href=[\'|"](.*?)[\'"].*?>')

def setBaseURL(self,url):
self.tocrawl = set([url])

def run(self):
url = raw_input('Enter an URL to crawl\n')
self.setBaseURL(url)
dir = raw_input('Where should I put crawled HTML source files?\n')
self.crawl(dir)

def getTitle(self,html):
startPos = html.find('<title>')
if startPos != -1:
endPos = html.find('</title>', startPos+7)
if endPos != -1:
title = html[startPos+7:endPos]
return title

def writeToFile(self,url):
with open('hyperlinks.txt', 'a') as file:
file.write(url + '\n')

def writeHTML(self,fileName,html,dirPath):
self.verifyDir(dirPath)
fileName = re.sub('[\\/:"*?<>|]',"",fileName)
with open(dirPath+'\\'+ fileName + '.txt', 'w+') as file:
file.write(html)

def verifyDir(self,path):
if not os.path.exists(path):
os.makedirs(path)

def crawl(self,dir_path):
while 1:
try:
if self.tocrawl:
crawling = self.tocrawl.pop()
print '\n\nStart Crawling - ' + crawling + '\n'
except KeyError:
raise StopIteration
url = urlparse.urlparse(crawling)
try:
response = urllib2.urlopen(crawling)
except:
continue
msg = response.read()
self.writeHTML(crawling,msg,dir_path)

#Display page title
print self.getTitle(msg)

links = self.linkregex.findall(msg)
self.crawled.add(crawling)
self.writeToFile(crawling)
for link in links:
if link.startswith('mailto'):
continue
if link.startswith('/'):
link = 'http://' + url[1] + link
elif link.startswith('#'):
link = 'http://' + url[1] + url[2] + link
elif not link.startswith('http'):
link = 'http://' + url[1] + '/' + link
if link not in self.crawled:
print '----' + link
self.tocrawl.add(link)

[/sourcecode]

How to run this crawler?

Run following command in Python shell.

import web_crawler
w = web_crawler.WebCrawler()
w.run()