Merge branch 'master' of github.com:taddeus/licenseplates

docs/report.tex

@@ -172,11 +172,7 @@ order. Starting with dividing the pattern in to cells of size 16.
 result is a feature vector of the image.
 
 \item Feed these vectors to a support vector machine. This will ''learn'' which
-<<<<<<< HEAD
 vector indicates what vector is which character. 
-=======
-vectors indicate what letter. 
->>>>>>> 2e1b2e8c8db4f802d203791a6f03eeca7d0aff70
 
 \end{itemize}
 

src/.gitignore

 *.dat
-results.txt
+results*.txt

src/Character.py

@@ -7,11 +7,12 @@ class Character:
         self.image   = image
         self.filename = filename
 
-    def get_single_cell_feature_vector(self):
+    def get_single_cell_feature_vector(self, neighbours=5):
         if hasattr(self, 'feature'):
             return
 
-        self.feature = LBP(self.image).single_cell_features_vector()
+        pattern = LBP(self.image, neighbours=neighbours)
+        self.feature = pattern.single_cell_features_vector()
 
     def get_feature_vector(self, cell_size=None):
         pattern = LBP(self.image) if cell_size == None \

src/Classifier.py

@@ -3,8 +3,8 @@ from svmutil import svm_train, svm_problem, svm_parameter, svm_predict, \
 
 
 class Classifier:
-    def __init__(self, c=None, gamma=None, filename=None, cell_size=12):
-        self.cell_size = cell_size
+    def __init__(self, c=None, gamma=None, filename=None, neighbours=3):
+        self.neighbours = neighbours
 
         if filename:
             # If a filename is given, load a model from the given filename
@@ -34,7 +34,7 @@ class Classifier:
                   % (char.value, i + 1, l, int(100 * (i + 1) / l))
             classes.append(float(ord(char.value)))
             #features.append(char.get_feature_vector())
-            char.get_single_cell_feature_vector()
+            char.get_single_cell_feature_vector(self.neighbours)
             features.append(char.feature)
 
         problem = svm_problem(classes, features)
@@ -56,7 +56,7 @@ class Classifier:
         """Classify a character object, return its value."""
         true_value = 0 if true_value == None else ord(true_value)
         #x = character.get_feature_vector(self.cell_size)
-        character.get_single_cell_feature_vector()
+        character.get_single_cell_feature_vector(self.neighbours)
         p = svm_predict([true_value], [character.feature], self.model)
         prediction_class = int(p[0][0])
 

src/LocalBinaryPatternizer.py

@@ -3,9 +3,13 @@ from math import ceil
 
 class LocalBinaryPatternizer:
 
-    def __init__(self, image, cell_size=16):
+    def __init__(self, image, cell_size=16, neighbours=3):
         self.cell_size = cell_size
         self.image = image
+        self.pattern_callback, self.bins = {
+                    3: (self.pattern_3x3, 256),
+                    5: (self.pattern_5x5, 4096)
+                }[neighbours]
 
     def setup_histograms(self):
         cells_in_width = int(ceil(self.image.width / float(self.cell_size)))
@@ -16,9 +20,9 @@ class LocalBinaryPatternizer:
             self.histograms.append([])
 
             for j in xrange(cells_in_width):
-                self.histograms[i].append(Histogram(256, 0, 256))
+                self.histograms[i].append(Histogram(self.bins, 0, self.bins))
 
-    def local_binary_pattern(self, y, x, value):
+    def pattern_3x3(self, y, x, value):
         return (self.is_pixel_darker(y - 1, x - 1, value) << 7) \
              | (self.is_pixel_darker(y - 1, x    , value) << 6) \
              | (self.is_pixel_darker(y - 1, x + 1, value) << 5) \
@@ -26,7 +30,21 @@ class LocalBinaryPatternizer:
              | (self.is_pixel_darker(y + 1, x + 1, value) << 3) \
              | (self.is_pixel_darker(y + 1, x    , value) << 2) \
              | (self.is_pixel_darker(y + 1, x - 1, value) << 1) \
-             | (self.is_pixel_darker(y    , x - 1, value) << 0)
+             | (self.is_pixel_darker(y    , x - 1, value))
+
+    def pattern_5x5(self, y, x, value):
+        return (self.is_pixel_darker(y - 1, x - 2, value) << 11) \
+             | (self.is_pixel_darker(y    , x - 2, value) << 10) \
+             | (self.is_pixel_darker(y + 1, x - 2, value) << 9) \
+             | (self.is_pixel_darker(y + 2, x - 1, value) << 8) \
+             | (self.is_pixel_darker(y + 2, x    , value) << 7) \
+             | (self.is_pixel_darker(y + 2, x + 1, value) << 6) \
+             | (self.is_pixel_darker(y + 1, x + 2, value) << 5) \
+             | (self.is_pixel_darker(y    , x + 2, value) << 4) \
+             | (self.is_pixel_darker(y - 1, x + 2, value) << 3) \
+             | (self.is_pixel_darker(y - 2, x + 1, value) << 2) \
+             | (self.is_pixel_darker(y - 2, x    , value) << 1) \
+             | (self.is_pixel_darker(y - 2, x - 1, value))
 
     def create_features_vector(self):
         '''Walk around the pixels in clokwise order, shifting 1 bit less at
@@ -36,7 +54,7 @@ class LocalBinaryPatternizer:
 
         for y, x, value in self.image:
             cy, cx = self.get_cell_index(y, x)
-            self.histograms[cy][cx].add(self.local_binary_pattern(y, x, value))
+            self.histograms[cy][cx].add(self.pattern_callback(y, x, value))
 
         return self.get_features_as_array()
 
@@ -55,15 +73,14 @@ class LocalBinaryPatternizer:
                 f.extend(hist.bins)
 
         return f
-        #return [h.bins for h in [h for sub in self.histograms for h in sub]][0]
 
     def get_single_histogram(self):
         """Create a single histogram of the local binary patterns in the
         image."""
-        h = Histogram(256, 0, 256)
+        h = Histogram(self.bins, 0, self.bins)
 
         for y, x, value in self.image:
-            h.add(self.local_binary_pattern(y, x, value))
+            h.add(self.pattern_callback(y, x, value))
 
         h.normalize()
 

src/NormalizedCharacterImage.py

@@ -5,19 +5,22 @@ from GaussianFilter import GaussianFilter
 
 class NormalizedCharacterImage(GrayscaleImage):
 
-    def __init__(self, image=None, data=None, size=(60, 40), blur=1.1, \
-            crop_threshold=0.9):
+    def __init__(self, image=None, data=None, height=None, blur=1.1):
         if image != None:
             GrayscaleImage.__init__(self, data=deepcopy(image.data))
         elif data != None:
             GrayscaleImage.__init__(self, data=deepcopy(data))
+
         self.blur = blur
-        self.crop_threshold = crop_threshold
-        self.size = size
         self.gaussian_filter()
+
         self.increase_contrast()
+
+        #self.crop_threshold = crop_threshold
         #self.crop_to_letter()
-        #self.resize()
+
+        self.height = height
+        self.resize()
 
     def increase_contrast(self):
         self.data -= self.data.min()
@@ -31,4 +34,9 @@ class NormalizedCharacterImage(GrayscaleImage):
         cropper.crop_to_letter(self)
 
     def resize(self):
-        GrayscaleImage.resize(self, self.size)
+        """Resize the image to a fixed height."""
+        if self.height == None:
+            return
+
+        h, w = self.data.shape
+        GrayscaleImage.resize(self, (self.height, self.height * w / h))

src/find_svm_params.py

 #!/usr/bin/python
-from cPickle import load
+from os import listdir
+from os.path import exists
+from cPickle import load, dump
+from sys import argv, exit
+
+from GrayscaleImage import GrayscaleImage
+from NormalizedCharacterImage import NormalizedCharacterImage
+from Character import Character
 from Classifier import Classifier
 
+if len(argv) < 3:
+    print 'Usage: python %s NEIGHBOURS BLUR_SCALE' % argv[0]
+    exit(1)
+
+neighbours = int(argv[1])
+blur_scale = float(argv[2])
+suffix = '_%s_%s' % (blur_scale, neighbours)
+
+chars_file = 'characters%s.dat' % suffix
+learning_set_file = 'learning_set%s.dat' % suffix
+test_set_file = 'test_set%s.dat' % suffix
+classifier_file = 'classifier%s.dat' % suffix
+results_file = 'results%s.txt' % suffix
+
+
+# Load characters
+if exists(chars_file):
+    print 'Loading characters...'
+    chars = load(open(chars_file, 'r'))
+else:
+    print 'Going to generate character objects...'
+    chars = []
+
+    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=blur_scale, height=42)
+            #imshow(norm.data, cmap='gray'); show()
+            character = Character(char, [], norm)
+            character.get_single_cell_feature_vector(neighbours)
+            chars.append(character)
+            print char
+
+    print 'Saving characters...'
+    dump(chars, open(chars_file, 'w+'))
+
+
+# Load learning set and test set
+if exists(learning_set_file):
+    print 'Loading learning set...'
+    learning_set = load(open(learning_set_file, 'r'))
+    print 'Learning set:', [c.value for c in learning_set]
+    print 'Loading test set...'
+    test_set = load(open(test_set_file, 'r'))
+    print 'Test set:', [c.value for c in test_set]
+else:
+    print 'Going to generate learning set and test set...'
+    learning_set = []
+    test_set = []
+    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_file, 'w+'))
+    print 'Saving test set...'
+    dump(test_set, file(test_set_file, 'w+'))
+
+
+# Perform a grid-search to find the optimal values for C and gamma
 C = [float(2 ** p) for p in xrange(-5, 16, 2)]
 Y = [float(2 ** p) for p in xrange(-15, 4, 2)]
-best_classifier = None
-
-print 'Loading learning set...'
-learning_set = load(file('learning_set.dat', 'r'))
-print 'Learning set:', [c.value for c in learning_set]
-print 'Loading test set...'
-test_set = load(file('test_set.dat', 'r'))
-print 'Test set:', [c.value for c in test_set]
 
-# Perform a grid-search on different combinations of soft margin and gamma
 results = []
 best = (0,)
 i = 0
 
 for c in C:
     for y in Y:
-        classifier = Classifier(c=c, gamma=y)
+        classifier = Classifier(c=c, gamma=y, neighbours=neighbours)
         classifier.train(learning_set)
         result = classifier.test(test_set)
 
@@ -33,22 +99,30 @@ for c in C:
               % (i, len(C) * len(Y), c, y, int(round(result * 100)))
 
 i = 0
+s = '     c\y'
 
-print '\n     c\y',
 for y in Y:
-    print '| %f' % y,
+    s += '| %f' % y
 
-print
+s += '\n'
 
 for c in C:
-    print ' %7s' % c,
+    s += ' %7s' % c
 
     for y in Y:
-        print '| %8d' % int(round(results[i] * 100)),
+        s +=  '| %8d' % int(round(results[i] * 100))
         i += 1
 
-    print
+    s += '\n'
+
+s += '\nBest result: %.3f%% for C = %f and gamma = %f' % best[:3]
+
+print 'Saving results...'
+f = open(results_file, 'w+')
+f.write(s + '\n')
+f.close()
 
-print '\nBest result: %.3f%% for C = %f and gamma = %f' % best[:3]
+print 'Saving best classifier...'
+best[3].save(classifier_file)
 
-best[3].save('classifier.dat')
+print '\n' + s

src/load_characters.py

 #!/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

+#!/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

 #!/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