Merged test scripts into a single test file: find_svm_parameter.py.

src/load_characters.py

@@ -1,24 +1,29 @@
 #!/usr/bin/python
 from os import listdir
 from cPickle import dump
-from pylab import imshow, show
+from sys import argv, exit
 
 from GrayscaleImage import GrayscaleImage
 from NormalizedCharacterImage import NormalizedCharacterImage
 from Character import Character
 
+if len(argv) < 4:
+    print 'Usage: python %s FILE_SUFFIX BLUR_SCALE NEIGHBOURS' % argv[0]
+    exit(1)
+
 c = []
 
 for char in sorted(listdir('../images/LearningSet')):
     for image in sorted(listdir('../images/LearningSet/' + char)):
         f = '../images/LearningSet/' + char + '/' + image
         image = GrayscaleImage(f)
-        norm = NormalizedCharacterImage(image, blur=1, size=(48, 36))
-        #imshow(norm.data, cmap='gray')
-        #show()
+        norm = NormalizedCharacterImage(image, blur=float(argv[2]), height=42)
+        #from pylab import imshow, show
+        #imshow(norm.data, cmap='gray'); show()
         character = Character(char, [], norm)
-        character.get_single_cell_feature_vector()
+        character.get_single_cell_feature_vector(int(argv[3]))
         c.append(character)
         print char
 
-dump(c, open('characters.dat', 'w+'))
+print 'Saving characters...'
+dump(c, open('characters%s.dat' % argv[1], 'w+'))

src/load_learning_set.py

@@ -0,0 +1,40 @@
+#!/usr/bin/python
+from cPickle import dump, load
+from sys import argv, exit
+
+if len(argv) < 2:
+    print 'Usage: python %s FILE_SUFFIX' % argv[0]
+    exit(1)
+
+print 'Loading characters...'
+chars = load(file('characters%s.dat' % argv[1], 'r'))
+learning_set = []
+test_set = []
+
+#s = {}
+#
+#for char in chars:
+#    if char.value not in s:
+#        s[char.value] = [char]
+#    else:
+#        s[char.value].append(char)
+#
+#for value, chars in s.iteritems():
+#    learning_set += chars[::2]
+#    test_set += chars[1::2]
+
+learned = []
+
+for char in chars:
+    if learned.count(char.value) == 70:
+        test_set.append(char)
+    else:
+        learning_set.append(char)
+        learned.append(char.value)
+
+print 'Learning set:', [c.value for c in learning_set]
+print '\nTest set:', [c.value for c in test_set]
+print '\nSaving learning set...'
+dump(learning_set, file('learning_set%s.dat' % argv[1], 'w+'))
+print 'Saving test set...'
+dump(test_set, file('test_set%s.dat' % argv[1], 'w+'))

src/test_classifier.py

@@ -1,53 +1,23 @@
 #!/usr/bin/python
-from xml_helper_functions import xml_to_LicensePlate
-from Classifier import Classifier
 from cPickle import dump, load
 
-chars = load(file('characters.dat', 'r'))
-learning_set = []
-test_set = []
-
-#s = {}
-#
-#for char in chars:
-#    if char.value not in s:
-#        s[char.value] = [char]
-#    else:
-#        s[char.value].append(char)
-#
-#for value, chars in s.iteritems():
-#    learning_set += chars[::2]
-#    test_set += chars[1::2]
-
-learned = []
+from Classifier import Classifier
 
-for char in chars:
-    if learned.count(char.value) == 70:
-        test_set.append(char)
-    else:
-        learning_set.append(char)
-        learned.append(char.value)
+if len(argv) < 5:
+    print 'Usage: python %s FILE_SUFFIX C GAMMA NEIGHBOURS' % argv[0]
+    exit(1)
 
-print 'Learning set:', [c.value for c in learning_set]
-print 'Test set:', [c.value for c in test_set]
-print 'Saving learning set...'
-dump(learning_set, file('learning_set.dat', 'w+'))
-print 'Saving test set...'
-dump(test_set, file('test_set.dat', 'w+'))
-#----------------------------------------------------------------
 print 'Loading learning set'
-learning_set = load(file('learning_set.dat', 'r'))
+learning_set = load(file('learning_set%s.dat' % argv[1], 'r'))
 
 # Train the classifier with the learning set
-classifier = Classifier(c=512, gamma=.125, cell_size=12)
+classifier = Classifier(c=float(argv[1]), \
+                        gamma=float(argv[2]), \
+                        neighbours=int(argv[3]))
 classifier.train(learning_set)
-classifier.save('classifier.dat')
-print 'Saved classifier'
-#----------------------------------------------------------------
-print 'Loading classifier'
-classifier = Classifier(filename='classifier.dat')
+
 print 'Loading test set'
-test_set = load(file('test_set.dat', 'r'))
+test_set = load(file('test_set%s.dat' % argv[1], 'r'))
 l = len(test_set)
 matches = 0