import cv2
import numpy as np

class DenseDetector(object):
    def __init__(self, step_size=20, feature_scale=40, img_bound=20):
        # Create a dense feature detector
        self.detector = cv2.FeatureDetector_create("Dense")

        # Initialize it with all the required parameters
        self.detector.setInt("initXyStep", step_size)
        self.detector.setInt("initFeatureScale", feature_scale)
        self.detector.setInt("initImgBound", img_bound)

    def detect(self, img):
        # Run feature detector on the input image
        return self.detector.detect(img)

if __name__=='__main__':
    input_image = cv2.imread(sys.argv[1])
    input_image_sift = np.copy(input_image)

    # Convert to grayscale
    gray_image = cv2.cvtColor(input_image, cv2.COLOR_BGR2GRAY)

    keypoints = DenseDetector(20,20,5).detect(input_image)

    # Draw keypoints on top of the input image
    input_image = cv2.drawKeypoints(input_image, keypoints,
            flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)

    # Display the output image
    cv2.imshow('Dense feature detector', input_image)

    # Initialize SIFT object
    sift = cv2.SIFT()

    # Detect keypoints using SIFT
    keypoints = sift.detect(gray_image, None)

    # Draw SIFT keypoints on the input image
    input_image_sift = cv2.drawKeypoints(input_image_sift,
            keypoints, flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)

    # Display the output image
    cv2.imshow('SIFT detector', input_image_sift)

    # Wait until user presses a key
    cv2.waitKey()

import os
import sys
import argparse
import cPickle as pickle
import json

import cv2
import numpy as np
from sklearn.cluster import KMeans

def build_arg_parser():
    parser = argparse.ArgumentParser(description='Creates features for given images')
    parser.add_argument("--samples", dest="cls", nargs="+", action="append",
            required=True, help="Folders containing the training images. \
            The first element needs to be the class label.")
    parser.add_argument("--codebook-file", dest='codebook_file', required=True,
            help="Base file name to store the codebook")
    parser.add_argument("--feature-map-file", dest='feature_map_file', required=True,
            help="Base file name to store the feature map")

    return parser

# Loading the images from the input folder
def load_input_map(label, input_folder):
    combined_data = []

    if not os.path.isdir(input_folder):
        raise IOError("The folder " + input_folder + " doesn't exist")

    # Parse the input folder and assign the  labels
    for root, dirs, files in os.walk(input_folder):
        for filename in (x for x in files if x.endswith('.jpg')):
            combined_data.append({'label': label, 'image': os.path.join(root, filename)})

    return combined_data

class FeatureExtractor(object):
    def extract_image_features(self, img):
        # Dense feature detector
        kps = DenseDetector().detect(img)

        # SIFT feature extractor
        kps, fvs = SIFTExtractor().compute(img, kps)

        return fvs

    # Extract the centroids from the feature points
    def get_centroids(self, input_map, num_samples_to_fit=10):
        kps_all = []

        count = 0
        cur_label = ''
        for item in input_map:
            if count >= num_samples_to_fit:
                if cur_label != item['label']:
                    count = 0
                else:
                    continue

            count += 1

            if count == num_samples_to_fit:
                print "Built centroids for", item['label']

            cur_label = item['label']
            img = cv2.imread(item['image'])
            img = resize_to_size(img, 150)

            num_dims = 128
            fvs = self.extract_image_features(img)
            kps_all.extend(fvs)

        kmeans, centroids = Quantizer().quantize(kps_all)
        return kmeans, centroids

    def get_feature_vector(self, img, kmeans, centroids):
        return Quantizer().get_feature_vector(img, kmeans, centroids)

def extract_feature_map(input_map, kmeans, centroids):
    feature_map = []

    for item in input_map:
        temp_dict = {}
        temp_dict['label'] = item['label']

        print "Extracting features for", item['image']
        img = cv2.imread(item['image'])
        img = resize_to_size(img, 150)

        temp_dict['feature_vector'] = FeatureExtractor().get_feature_vector(
                    img, kmeans, centroids)

        if temp_dict['feature_vector'] is not None:
            feature_map.append(temp_dict)

    return feature_map

# Vector quantization
class Quantizer(object):
    def __init__(self, num_clusters=32):
        self.num_dims = 128
        self.extractor = SIFTExtractor()
        self.num_clusters = num_clusters
        self.num_retries = 10

    def quantize(self, datapoints):
        # Create KMeans object
        kmeans = KMeans(self.num_clusters,
                        n_init=max(self.num_retries, 1),
                        max_iter=10, tol=1.0)

        # Run KMeans on the datapoints
        res = kmeans.fit(datapoints)

        # Extract the centroids of those clusters
        centroids = res.cluster_centers_

        return kmeans, centroids

    def normalize(self, input_data):
        sum_input = np.sum(input_data)
        if sum_input > 0:
            return input_data / sum_input
        else:
            return input_data

    # Extract feature vector from the image
    def get_feature_vector(self, img, kmeans, centroids):
        kps = DenseDetector().detect(img)
        kps, fvs = self.extractor.compute(img, kps)
        labels = kmeans.predict(fvs)
        fv = np.zeros(self.num_clusters)

        for i, item in enumerate(fvs):
            fv[labels[i]] += 1

        fv_image = np.reshape(fv, ((1, fv.shape[0])))
        return self.normalize(fv_image)

class DenseDetector(object):
    def __init__(self, step_size=20, feature_scale=40, img_bound=20):
        self.detector = cv2.FeatureDetector_create("Dense")
        self.detector.setInt("initXyStep", step_size)
        self.detector.setInt("initFeatureScale", feature_scale)
        self.detector.setInt("initImgBound", img_bound)

    def detect(self, img):
        return self.detector.detect(img)

class SIFTExtractor(object):
    def compute(self, image, kps):
        if image is None:
            print "Not a valid image"
            raise TypeError

        gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
        kps, des = cv2.SIFT().compute(gray_image, kps)
        return kps, des

# Resize the shorter dimension to 'new_size'
# while maintaining the aspect ratio
def resize_to_size(input_image, new_size=150):
    h, w = input_image.shape[0], input_image.shape[1]
    ds_factor = new_size / float(h)

    if w < h:
        ds_factor = new_size / float(w)

    new_size = (int(w * ds_factor), int(h * ds_factor))
    return cv2.resize(input_image, new_size)

if __name__=='__main__':
    args = build_arg_parser().parse_args()

    input_map = []
    for cls in args.cls:

        assert len(cls) >= 2, "Format for classes is `<label> file`"
        label = cls[0]
        input_map += load_input_map(label, cls[1])

    # Building the codebook
    print "===== Building codebook ====="
    kmeans, centroids = FeatureExtractor().get_centroids(input_map)
    if args.codebook_file:
        with open(args.codebook_file, 'w') as f:
            pickle.dump((kmeans, centroids), f)

    # Input data and labels
    print "===== Building feature map ====="
    feature_map = extract_feature_map(input_map, kmeans, centroids)
    if args.feature_map_file:
        with open(args.feature_map_file, 'w') as f:
            pickle.dump(feature_map, f)

import os
import sys
import argparse

import cPickle as pickle
import numpy as np
from sklearn.multiclass import OneVsOneClassifier
from sklearn.svm import LinearSVC
from sklearn import preprocessing

def build_arg_parser():
    parser = argparse.ArgumentParser(description='Trains the classifier models')
    parser.add_argument("--feature-map-file", dest="feature_map_file", required=True,
            help="Input pickle file containing the feature map")
    parser.add_argument("--svm-file", dest="svm_file", required=False,
            help="Output file where the pickled SVM model will be stored")
    return parser

# To train the classifier
class ClassifierTrainer(object):
    def __init__(self, X, label_words):
        # Encoding the labels (words to numbers)
        self.le = preprocessing.LabelEncoder()

        # Initialize One vs One Classifier using a linear kernel
        self.clf = OneVsOneClassifier(LinearSVC(random_state=0))

        y = self._encodeLabels(label_words)
        X = np.asarray(X)
        self.clf.fit(X, y)

    # Predict the output class for the input datapoint
    def _fit(self, X):
        X = np.asarray(X)
        return self.clf.predict(X)

    # Encode the labels (convert words to numbers)
    def _encodeLabels(self, labels_words):
        self.le.fit(labels_words)
        return np.array(self.le.transform(labels_words), dtype=np.float32)

    # Classify the input datapoint
    def classify(self, X):
        labels_nums = self._fit(X)
        labels_words = self.le.inverse_transform([int(x) for x in labels_nums])
        return labels_words

if __name__=='__main__':
    args = build_arg_parser().parse_args()
    feature_map_file = args.feature_map_file
    svm_file = args.svm_file

    # Load the feature map
    with open(feature_map_file, 'r') as f:
        feature_map = pickle.load(f)

    # Extract feature vectors and the labels
    labels_words = [x['label'] for x in feature_map]

    # Here, 0 refers to the first element in the
    # feature_map, and 1 refers to the second
    # element in the shape vector of that element
    # (which gives us the size)
    dim_size = feature_map[0]['feature_vector'].shape[1]

    X = [np.reshape(x['feature_vector'], (dim_size,)) for x in feature_map]

    # Train the SVM
    svm = ClassifierTrainer(X, labels_words)
    if args.svm_file:
        with open(args.svm_file, 'w') as f:
            pickle.dump(svm, f)

$ pip install scikit-learn

$ python create_features.py --samples bag img/bag/ --samples dress img/dress/ --samples footwear img/footwear/ --codebook-file models/codebook.pkl --feature-map-file models/feature_map.pkl
$ python training.py --feature-map-file models/feature_map.pkl --svm-file models/svm.pkl

import os
import sys
import argparse
import cPickle as pickle

import cv2
import numpy as np

import create_features as cf
from training import ClassifierTrainer

def build_arg_parser():
    parser = argparse.ArgumentParser(description='Extracts features \
            from each line and classifies the data')
    parser.add_argument("--input-image", dest="input_image", required=True,
            help="Input image to be classified")
    parser.add_argument("--svm-file", dest="svm_file", required=True,
            help="File containing the trained SVM model")
    parser.add_argument("--codebook-file", dest="codebook_file",
            required=True, help="File containing the codebook")
    return parser

# Classifying an image
class ImageClassifier(object):
    def __init__(self, svm_file, codebook_file):
        # Load the SVM classifier
        with open(svm_file, 'r') as f:
            self.svm = pickle.load(f)

        # Load the codebook
        with open(codebook_file, 'r') as f:
            self.kmeans, self.centroids = pickle.load(f)

    # Method to get the output image tag
    def getImageTag(self, img):
        # Resize the input image
        img = cf.resize_to_size(img)

        # Extract the feature vector
        feature_vector = cf.FeatureExtractor().get_feature_vector(img, self.kmeans, self.centroids)

        # Classify the feature vector and get the output tag
        image_tag = self.svm.classify(feature_vector)

        return image_tag

if __name__=='__main__':
    args = build_arg_parser().parse_args()
    svm_file = args.svm_file
    codebook_file = args.codebook_file
    input_image = cv2.imread(args.input_image)

    print "Output class:", ImageClassifier(svm_file, codebook_file).getImageTag(input_image)

$ python classify_data.py --input-image new_image.jpg --svm-file models/svm.pkl --codebook-file models/codebook.pkl