unknown mode: new
.login: No such file or directory
% ocrchie
ocrchie

Done initializing new tcl commands
Done initializing link variables
Learning from train.tif and train.txt sych 0
open succeeded on file train.tif.  length = 300. width = 2400
Extracting Components
  
@��@	�� 
@      
Learning from 4.header.tif and 4.header.txt sych 1
open succeeded on file 4.header.tif.  length = 129. width = 1825
Extracting Components
       
Opening train.tif
open succeeded on file train.tif.  length = 300. width = 2400
SCALE_FACTOR = 1.000000  Skip = 1.000000
Starting deskew process: time = 0.000000
Determining Line boundaries
Calling recognize from Tcl
Extracting Components
Recognizing document
abcdefghijklmnopqrstuvwxyz: ;\ 
ABCDEFGHIJKLMNOPQRSTUVWXYZ 
0 1 234567890~ ! @#$%%^&* ()+=-,.<<>>/?' 
Error: Huh?Opening 4.col0.tif
open succeeded on file 4.col0.tif.  length = 2461. width = 877
SCALE_FACTOR = 1.000000  Skip = 1.000000
Starting deskew process: time = 0.000000
Determining Line boundaries
Calling recognize from Tcl
Extracting Components
Recognizing document
dispersion and models of temporal price dis- 
persion. Most models of spatial price disper- 
sion, such as the Salop-Stiglitz model or the 
Wilde-Schwartz model, have equilibria with 
specific prices being charged with positive 
probability mass. The above argument shows 
that such strategies cannot be profit-max- 
iMzing Nash behavior in a temporal ran- 
domizing model. 
Since there are no point masses in the 
equilibrium density, the cumulative distribuM 
tion function will be a continuous function 
On (P*, T ). Let E(P ) be the cumuIative dis- 
tribution function for y( P ); thus y(P) = 
E^(P ) almost eveWhere. 
We can now construct the expected profit 
function for a representative store. When a 
store charges price P, exactIy two events are 
relevant. lt may be that P is the smallest 
price heing charged, in which case, the given 
store gets all of the informed customers. 
nis event happens only if all the other 
8tores charge prices higher than P, an event 
which has probability (l - F( P ))*- ' . On the 
other hand, there may be some store with a 
lower price, in which case the store in ques- 
tion only gets its share of the uninformed 
customers. This event happens with proba- 
bility l - (l - F( P))^ - '. (By Proposition 3 
we can neglect the prohahiIity of any ties.) 
Hence the expected profit of a representa- 
. 
tIve store Is 
/: ( N( P )( l - E( P ))^- ' 

+ @( P ) ( l - ( l - F( P ))^- ' ) 1/( P ) @ 
where N( P ) =P( C+ I ) - C( C+ I ) 
HI( P ) -P C- %( C ) 
The maximization problem of the firm is 
to choose the density function y( P) so as to 
maximize expected profits su%ect to the 
constraInts: 
/V 
1( P ) ? 0 ; .y( P ) @ - l 
It is clear that all prices that are charged 
with positive density must yield the same 
Error: Huh?Opening hal4eqn.tif
open succeeded on file hal4eqn.tif.  length = 1349. width = 1753
SCALE_FACTOR = 1.000000  Skip = 1.000000
Starting deskew process: time = 0.000000
Determining Line boundaries
109.0 449.0 3 354 538
109.0 449.0 0 61 89
1622.0 719.0 4 641 780
1622.0 719.0 3 354 538
390.0 913.0 5 878 961
390.0 913.0 4 641 780
1450.0 919.0 5 878 961
1450.0 919.0 5 878 961
401.0 1108.0 6 1059 1154
401.0 1108.0 5 878 961
1095.0 1104.0 6 1059 1154
1095.0 1104.0 6 1059 1154
Calling recognize from Tcl
Extracting Components
Recognizing document
we can neglect the probability ot any ties.) 
Hence the expected profit of a representa- 
tive store is 
/ P ^. ' ^ * ' ^ * ' ' - ^ ' ^ * * ^ - ' 
+ w 1 ( P ) ( l - ( l - E ( P ) ) ^ - ' ) ) y ( P ) d T 
where w S ( P ) - - P ( C + I ) - C ( C + I ) 
E 1 ( P ) - - P G - C ( C ) 
The maximization problem of the firm is 
Calling recognize from Tcl
Extracting Components
Recognizing document
we can neglect the probability ot any ties.) 
Hence the expected profit of a representa- 
tive store is 
/ P ^. ' ^ * ' ^ * ' ' - ^ ' ^ * * ^ - ' 
+ w 1 ( P ) ( l - ( l - E ( P ) ) ^ - ' ) ) y ( P ) d T 
where w S ( P ) - - P ( C + I ) - C ( C + I ) 
E 1 ( P ) - - P G - C ( C ) 
The maximization problem of the firm is 
Calling interactive learn from Tcl
Learning from recog.tmp and 1 sych 0
Calling recognize from Tcl
Extracting Components
Recognizing document
we can neglect the probability of any ties.) 
Hence the expected profit of a representa- 
tive store is 
<Int> P r* { <pi> s ( p ) ( 1 - F ( p ) ) n - 1 
+ <pi> f ( p ) [ l - ( l - F ( P ) ) n - 1 ] } f ( p ) d p 
where <pi> s ( P ) = - P ( + + I ) - C ( + + I ) 
<pi> f ( p ) = - U - c C ( ) ) 
The maximization problem of the firm is 
Calling recognize from Tcl
Extracting Components
Recognizing document
we can neglect the probability of any ties.) 
Hence the expected profit of a representa- 
tive store is 
<Int> P r* { <pi> s ( p ) ( 1 - F ( p ) ) n - 1 
+ <pi> f ( p ) [ l - ( l - F ( P ) ) n - 1 ] } f ( p ) d p 
where <pi> s ( P ) = - P ( + + I ) - C ( + + I ) 
<pi> f ( p ) = - U - c C ( ) ) 
The maximization problem of the firm is 
436.9u 302.5s 14:08 87%
% ocrchie
ocrchie

Done initializing new tcl commands
Done initializing link variables
Learning from train.tif and train.txt sych 0
open succeeded on file train.tif.  length = 300. width = 2400
Extracting Components
  
@��@	�� 
@      
Learning from 4.header.tif and 4.header.txt sych 1
open succeeded on file 4.header.tif.  length = 129. width = 1825
Extracting Components
@� @� ��  
�
� ��  
Opening train.tif
open succeeded on file train.tif.  length = 300. width = 2400
SCALE_FACTOR = 1.000000  Skip = 1.000000
Starting deskew process: time = 0.000000
Determining Line boundaries
Calling recognize from Tcl
Extracting Components
Recognizing document
Segmentation fault (core dumped)
11.5u 4.7s 0:33 48%
% Segmentation fault (core dumped)
Segmentation fault (core dumped)

Badly placed ()'s.
% rm core
rm core

% run
run

run: Command not found.
% ocrchie
ocrchie

Done initializing new tcl commands
Done initializing link variables
Learning from train.tif and train.txt sych 0
open succeeded on file train.tif.  length = 300. width = 2400
Extracting Components
  
@��@	�� 
@      
Learning from 4.header.tif and 4.header.txt sych 1
open succeeded on file 4.header.tif.  length = 129. width = 1825
Extracting Components
       
Opening int.tif
open succeeded on file int.tif.  length = 227. width = 277
SCALE_FACTOR = 1.000000  Skip = 1.000000
Starting deskew process: time = 0.000000
Determining Line boundaries
Calling recognize from Tcl
Extracting Components
Recognizing document
/: ' ^ 
Thank you for using OCRchie.
16.0u 12.4s 0:35 81%
% grep Extracting Components {*.cc *.tcl}
grep Extracting Components {*.cc *.tcl}

Missing }.
% grep Extracting Components *.cc
grep Extracting Components *.cc

grep: can't open Components
Page.cc:    printf("Extracting Components\n");
status_message.cc:  set_string_status("Extracting Words", p, f);
status_message.cc:  set_string_status("Extracting Characters", p, f);
%