1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61
|
#!/bin/bash
# File: counttestset.sh
# Description: Script to count the errors on a single UNLV set.
# Author: Ray Smith
# Created: Wed Jun 13 11:58:01 PDT 2007
#
# (C) Copyright 2007, Google Inc.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
# http://www.apache.org/licenses/LICENSE-2.0
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
if [ $# -ne 1 ]
then
echo "Usage:$0 pagesfile"
exit 1
fi
if [ ! -d ccmain ]
then
echo "Run $0 from the tesseract-ocr root directory!"
exit 1
fi
if [ ! -r testing/unlv/accuracy ]
then
echo "Please download the UNLV accuracy tools (and build) to testing/unlv"
exit 1
fi
pages=$1
imdir=${pages%/pages}
setname=${imdir##*/}
resdir=testing/results/$setname
mkdir -p testing/reports
echo "Counting on set $setname in directory $imdir to $resdir"
accfiles=""
wafiles=""
while read page dir
do
if [ "$dir" ]
then
srcdir="$imdir/$dir"
else
srcdir="$imdir"
fi
# echo "$srcdir/$page.tif"
# Count character errors.
testing/unlv/accuracy $srcdir/$page.txt $resdir/$page.txt $resdir/$page.acc
accfiles="$accfiles $resdir/$page.acc"
# Count word errors.
testing/unlv/wordacc $srcdir/$page.txt $resdir/$page.txt $resdir/$page.wa
wafiles="$wafiles $resdir/$page.wa"
done <$pages
testing/unlv/accsum $accfiles >testing/reports/$setname.characc
testing/unlv/wordaccsum $wafiles >testing/reports/$setname.wordacc
|