/[gzz]/manuscripts/Paper/paper.tex
ViewVC logotype

Diff of /manuscripts/Paper/paper.tex

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.128 by jvk, Tue Apr 22 15:07:28 2003 UTC revision 1.129 by jvk, Thu Apr 24 12:11:09 2003 UTC
# Line 53  Janne V. Kujala and Tuomas J. Lukka\\ Line 53  Janne V. Kujala and Tuomas J. Lukka\\
53    
54  \begin{abstract}  \begin{abstract}
55    
56    %FIXME: more references of texture generation
57    
58    %FIXME: Justify why adding unique background will help recognise a document
59    %from a fragment and enhance text readability. (Optional)
60    
61    %FIXME: Add a concise description of how fig. 3 works in the paper.
62    
63    %FIXME: The order and the index of the figures are not coincident.
64    
65    %FIXME: Make the titles of figures shorter, and explain the details in the
66    %context.(Optional)
67    
68    %FIXME: Fig 1, a): Mark the link clearer. Try to avoid line crossing.
69    
70    %FIXME: The citation might be better if only a unified format is used.  
71    %E.g., "point (see, e.g., Heeger[16])" -> "point[16]" . (Optional)
72    %XXX: is there a reason for inserting "], [" between citations?
73    
74    %FIXME: The fonts should be uniform in the topics of figure 1 and table 1.
75    
76    %FIXME: Revise the spelling and grammar errors, esp. grammar of long sentences.
77    
78    
79    %FIXME: more concise and exact explanations in some sections
80    %FIXME: what are this paper's spefific contributions? (e.g., in Sec. 4)
81    
82  %NO NEED FOR PERFECT RECALL - JUST A CUE  %NO NEED FOR PERFECT RECALL - JUST A CUE
83    
# Line 250  olano98pixelflow,mccool99textureshaders} Line 275  olano98pixelflow,mccool99textureshaders}
275  %In addition to being drawn by hand or scanned,  %In addition to being drawn by hand or scanned,
276  Textures have been synthesized in several ways: procedurally\cite{perlin-noise-intro},  Textures have been synthesized in several ways: procedurally\cite{perlin-noise-intro},
277  using  using
278  other textures as a starting point  other textures as a starting point\cite{heeger95pyramid},
 (see, e.g., Heeger\cite{heeger95pyramid}),  
279  perceptually, for visualizing surface orientation\cite{schweitzer83texturing,interrante97illustrating} and scalar or vector fields\cite{ware95texture},  perceptually, for visualizing surface orientation\cite{schweitzer83texturing,interrante97illustrating} and scalar or vector fields\cite{ware95texture},
280  and statistically, as samples from a probability distribution on a random field  and statistically, as samples from a probability distribution on a random field
281  \cite{cross83markov,geman84stochastic}.  \cite{cross83markov,geman84stochastic}.
282    % FIXME: grammar
283  % XXX: there's overlap between the enumerated cases  % XXX: there's overlap between the enumerated cases
284    
285  %Textures have also been modeled statistically,  %Textures have also been modeled statistically,
# Line 283  equally well \cite{bergen88earlyvision}. Line 308  equally well \cite{bergen88earlyvision}.
308  In these models, a bank of linear filters is applied to the texture followed  In these models, a bank of linear filters is applied to the texture followed
309  by a nonlinearity and then another set of filters to extract features  by a nonlinearity and then another set of filters to extract features
310  (see, e.g., Heeger\cite{heeger95pyramid}).  (see, e.g., Heeger\cite{heeger95pyramid}).
311    %FIXME: grammar and citation
312  There is also physiological evidence of the filtering processes:  There is also physiological evidence of the filtering processes:
313  %The first stages  %The first stages
314  %of visual perception  %of visual perception
315  %are fairly well known  %are fairly well known
316  in the visual cortex, there are cells sensitive to different  in the visual cortex, there are cells sensitive to different
317  frequencies, orientations, and locations in the visual field  frequencies, orientations, and locations in the visual field
318  (see, e.g.,~Bruce et al\cite{bruce96visualperception}).  %(see, e.g.,~Bruce et al
319    \cite{bruce96visualperception}.
320    
321  On a higher level, the correlations between local features are combined  On a higher level, the correlations between local features are combined
322  by forming contours and possibly  by forming contours and possibly
323  other higher-level constructions (see, e.g., \cite{saarinen97integration}).  other higher-level constructions %(see, e.g.,
324    \cite{saarinen97integration}.
325  These higher levels are not yet thoroughly understood;  These higher levels are not yet thoroughly understood;
326  some theories  some theories
327  (see, e.g., Biederman\cite{biederman87})  %(see, e.g., Biederman%
328    \cite{biederman87}
329  assume certain primitive shapes whose  assume certain primitive shapes whose
330  structure facilitates recognition.  structure facilitates recognition.
331    
# Line 1050  any mapping of the texture is fine, as l Line 1079  any mapping of the texture is fine, as l
1079  with the selected repeating unit. For example, a texture can  with the selected repeating unit. For example, a texture can
1080  repeat multiple times inside the repeating unit, or can be skewed  repeat multiple times inside the repeating unit, or can be skewed
1081  w.r.t.~the repeating unit.  w.r.t.~the repeating unit.
1082    %FIXME: spell out w.r.t?(Optional)
1083  Again, a heuristic distribution is used which does not skew or scale  Again, a heuristic distribution is used which does not skew or scale
1084  the basis texture too much too often.  the basis texture too much too often.
1085    

Legend:
Removed from v.1.128  
changed lines
  Added in v.1.129

savannah-hackers-public@gnu.org
ViewVC Help
Powered by ViewVC 1.1.26