Character Recognition Paper, DSP Code

Character Recognition by Feature Point Extraction
http://www.ccs.neu.edu/home/feneric/charrec.html
 
 
FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensionshttp://www.fftw.org
 
FAQs (Frequently asked questions with answers) on Digital Signal Processinghttp://www.bdti.com/faq/dsp_faq.htm
http://www.bdti.com/faq/1.htm
 

Comments

Post a Comment

Popular posts from this blog

Imote2 with Camera setup IMB400 over Ubuntu 9.10/10.04

Imote2 Camera driver for TinyOS is available in contribution directory of  TinyOS 2.x . It goes by the name of  tinyos-2.x-contrib . Its location within is  tinyos-2.x-contrib/intelmote2/apps I am assuming that you have tinyos-2.1.1 installed, this is required to have Camera Driver build. If you dont have it installed... than better have it done by invoking: apt-get install tinyos-2.1.1 From here on to get the driver working,  the procedure is as follows: Browse to opt directory. cd /opt The recommended way to get the source of tinyos-2.x and tinyos-2.x-contribis is through CVS. echo "Getting TinyOS 2.x and TinyOS 2.x-contrib from CVS" echo "Press enter when asked for password." cvs -d:pserver:anonymous@tinyos.cvs.sourceforge.net:/cvsroot/tinyos login cvs -z3 -d:pserver:anonymous@tinyos.cvs.sourceforge.net:/cvsroot/tinyos co -P tinyos-2.x cvs -z3 -d:pserver:anonymous@tinyos.cvs.sourceforge.net:/cvsroot/tinyos co -P tinyos-2.x-contrib --OR--  echo "
Read more

Branch and bound algorithm in C#- Article by AsiF Munir

A very authoritative Article along with Implementation by Asif Munir ( http://www.navicosoft.com ) on  Branch and bound algorithm in C#  h ttp://www.codersource.net/microsoft-net/c-image-processing/branch-and-bound-algorithm-in-c.aspx It was also selected as a   Top Pick of the month at  http://www.codersource.net/default.aspx A very encouraging contribution indeed.
Read more

Tensorflow - Simplest Gradient Descent using GradientDescentOptimizer

Below is the code to find the minimum possible value of weight (w) such that the outcome of equation is closest to 0, using Gradient Descent method. These weights are multiplied with input (x) to compute cost, thus minimizing it. The equation is below... w 2 - 10 w + 25 ---------------------- (i) i.e. ( w - 5 ) 2 Thus, the coefficients from (i) would be 1, -10 and 25 import numpy as np import tensorflow as tf coefficients = np.array([[ 1 ], [ - 10 ], [ 25 ]]) # try 1, -20, 100 -- line 4 w = tf.Variable([ 0 ], dtype = tf.float32) x = tf.placeholder(tf.float32, [ 3 , 1 ]) cost = (x[ 0 ][ 0 ] * w ** 2 ) + (x[ 1 ][ 0 ] * w) + x[ 2 ][ 0 ] # (w-5)^2 train = tf.train.GradientDescentOptimizer( 0.01 ).minimize(cost) init = tf.global_variables_initializer() with tf.Session() as session: session.run(init) print (session.run(w)) for i in range ( 1000 ): session.run(train, feed_dict = {x:coefficients}) print (session.run(w)) T
Read more