# the best 16, then update the visualizations dictionary
topResults = sorted(topResults, key=lambda r:r[0])[:16]
vis[j] = topResults
# update the progress bar
pbar.update(i)
# close the features database
pbar.finish()
featuresDB.close()
print("[INFO] writing visualizations to file...")
# loop over the top results
for (vwID, results) in vis.items():
# initialize the results montage
montage = ResultsMontage((64, 64), 4, 16)
# loop over the results
for (_, (x, y), imageID) in results:
# load the current image
p = str(imageID)
image = cv2.imread(p)
image = imutils.resize(image, width=320)
(h, w) = image.shape[:2]
# extract a 8x8 region surrounding the keypoint
(startX, endX) = (max(0, x - 16), min(w, x + 16))
(startY, endY) = (max(0, y - 16), min(h, y + 16))
roi = image[int(startY):int(endY), int(startX):int(endX)]
# add the ROI to the montage
# extract features from the query image and construct a bag-of-visual-words from it
(_, descs) = dad.describe(queryImage)
hist = bovw.describe(descs).tocoo()
# connect to redis and perform the search
redisDB = Redis(host="localhost", port=6379, db=0)
searcher = Searcher(redisDB,
args["bovw_db"],
args["features_db"],
idf=idf,
distanceMetric=distanceMetric)
sr = searcher.search(hist, numResults=20)
print("[INFO] search took: {:.2f}s".format(sr.search_time))
# initialize the results montage
montage = ResultsMontage((240, 320), 5, 20)
# loop over the individual results
for (i, (score, resultID, resultIdx)) in enumerate(sr.results):
# load the result image and display it
print("[RESULT] {result_num}. {result} - {score:.2f}".format(
result_num=i + 1, result=resultID, score=score))
result = cv2.imread("{}/{}".format(args["dataset"], resultID))
montage.addResult(result,
text="#{}".format(i + 1),
highlight=resultID in queryRelevant)
# show the output image of results
cv2.imshow("Results", imutils.resize(montage.montage, height=700))
cv2.waitKey(0)
searcher.finish()
print("[INFO] loading CALTECH Faces dataset...")
(training, testing, names) = load_caltech_faces(args["dataset"],
min_faces=21,
flatten=True,
test_size=0.25)
# compute the PCA (eigenfaces) representation of the data, then project the training data
# onto the eigenfaces subspace
print("[INFO] creating eigenfaces...")
pca = RandomizedPCA(n_components=args["num_components"], whiten=True)
trainData = pca.fit_transform(training.data)
# check to see if the PCA components should be visualized
if args["visualize"] > 0:
# initialize the montage for the components
montage = ResultsMontage((62, 47), 4, 16)
# loop over the first 16 individual components
for (i, component) in enumerate(pca.components_[:16]):
# reshape the component to a 2D matrix, then convert the data type to an unsigned
# 8-bit integer so it can be displayed with OpenCV
component = component.reshape((62, 47))
component = exposure.rescale_intensity(component,
out_range=(0,
255)).astype("uint8")
component = np.dstack([component] * 3)
montage.addResult(component)
# show the mean and principal component visualizations
# show the mean image
mean = pca.mean_.reshape((62, 47))