def cluster(img_name, n_cluster=10, method='kmeans_his'):
img_list = []
desc_list = []
desc_final = []
threshold = 0.9
orb = cv2.ORB_create(nfeatures=1000)
#read the images
n_img = len(img_name)
for i in range(n_img):
img_list.append(cv2.imread(img_name[i], cv2.IMREAD_GRAYSCALE))
# make a distance matrix for evaluation
# make a list of descriptors for k means
img_dst = np.ones(shape=(n_img, n_img))
img_values = {}
for i in range(n_img):
img_values[img_name[i]] = key_desc(orb, img_list[i])
for i in range(n_img):
kp1, desc1 = img_values[img_name[i]]
if method == 'complete' or method == 'single' or method == 'average':
for j in range(i + 1, n_img):
kp2, desc2 = img_values[img_name[j]]
dist = orb_features(kp1, kp2, desc1, desc2)
dist1 = {
key: value
for key, value in dist.items() if (value <= threshold)
}
img_dst[i, j] = 1 / len(dist1)
img_dst[j, i] = 1 / len(dist1)
elif method == 'kmeans' or method == 'kmeans_his':
desc_list.extend(desc1)
desc_final.append(desc1)
if method == 'average':
cluster = AgglomerativeClustering(n_clusters=n_cluster,
affinity='precomputed',
linkage='average').fit(img_dst)
if method == 'single':
cluster = AgglomerativeClustering(n_clusters=n_cluster,
affinity='precomputed',
linkage='single').fit(img_dst)
if method == 'complete':
cluster = AgglomerativeClustering(n_clusters=n_cluster,
affinity='precomputed',
linkage='complete').fit(img_dst)
if method == 'kmeans' or method == 'kmeans_his':
np.random.seed(1)
patch_kmeans = KMeans(n_clusters=n_cluster)
cluster = patch_kmeans.fit(desc_list)
if method == 'kmeans_his':
preprocessed_image = []
for desc in desc_final:
histogram = build_histogram(desc, patch_kmeans)
preprocessed_image.append(histogram)
cluster = KMeans(n_clusters=n_cluster).fit(preprocessed_image)
print_list = [[] for i in range(n_cluster)]
for i in range(n_img):
print_list[cluster.labels_[i]].append(img_name[i])
return print_list
cv2.imwrite(output_img, new_img)
else:
print('error in finding the transformation matrix!')
elif sys.argv[1] == 'part3':
target_img = cv2.imread(sys.argv[2], cv2.IMREAD_GRAYSCALE)
source_img = cv2.imread(sys.argv[3], cv2.IMREAD_GRAYSCALE)
output_img = sys.argv[4]
threshold = 0.8
orb = cv2.ORB_create(nfeatures=500)
kp1, desc1 = key_desc(orb, target_img)
kp2, desc2 = key_desc(orb, source_img)
dist = orb_features(kp1, kp2, desc1, desc2)
dist1 = {key:value for key,value in dist.items() if (value <= threshold)}
final_inliers, final_proj, flag = ransac(4, dist1, kp1, kp2)
target_img = cv2.imread(sys.argv[2])
source_img = cv2.imread(sys.argv[3])
if flag != 0:
new_img, min_x, max_x, min_y, max_y = bilinear_interpolation(source_img, np.linalg.inv(final_proj), target_img)
panorama_img = panorama(new_img, target_img, min_x, max_x, min_y, max_y)
cv2.imwrite(output_img, panorama_img)
else:
print('error in running RANSAC!')
#!/usr/local//bin/python3
"""
This is a sample code to run orb_features and draw matches between images
"""
from orb import orb_features
import cv2
from matches import drawMatches
img1 = cv2.imread(
"/Users/rs/Documents/Indiana University/2nd Semester/CV/FInal project/data/pedestrian_crosswalk_sign/crosswalk0.jpg",
cv2.IMREAD_GRAYSCALE)
img = cv2.imread(
"/Users/rs/Documents/Indiana University/2nd Semester/CV/FInal project/data/pedestrian_crosswalk_sign/crosswalk2.jpg",
cv2.IMREAD_GRAYSCALE)
dist, kp1, kp2, desc1, desc2 = orb_features(img, img1)
# Setting the threshold
threshold = 0.8
# subsetting the key points based on the thresholds
dist1 = {key: value for key, value in dist.items() if (value <= threshold)}
# This draws the key points between the images
drawMatches(img, img1, dist1, kp1, kp2)
# -*- coding: utf-8 -*-
import cv2
import numpy as np
from orb import orb_features, update_image
from voc_tree import constructTree
from matcher import *
N = 10 #训练字典图片的数量
K = 5 #聚类K类
L = 3 #字典树L层
n = 21 #测试的图片的数量
T = 1 #相似度阈值
image_descriptors = orb_features(N) #提取特征
# print image_descriptors
FEATS = []
for feats in image_descriptors:
FEATS += [np.array(fv, dtype='float32') for fv in feats]
FEATS = np.vstack(FEATS) #将特征转化为np的数组
# print FEATS
treeArray = constructTree(K, L, np.vstack(FEATS)) #建立字典树，并打印结果
tree = Tree(K, L, treeArray)
# tree.build_tree(N, image_descriptors)
# print "the vector of image:"
# print tree.transform(2)
# print tree.imageIDs, tree.dbLengths