我们从Python开源项目中，提取了以下26个代码示例，用于说明如何使用cv2.CV_LOAD_IMAGE_GRAYSCALE。
def load_heatmaps(self, name): heatmaps = [] for step in range(self.step_total): try: file_name = '../../'+self.data_base+'/'+name+'/'+self.env_id+'_'+str(step)+'.jpg' temp = cv2.imread(file_name, cv2.CV_LOAD_IMAGE_GRAYSCALE) temp = cv2.resize(temp,(self.heatmap_width, self.heatmap_height)) temp = temp / 255.0 heatmaps += [temp] except Exception,e: print Exception,":",e continue print('load heatmaps: '+name+' done, size: '+str(np.shape(heatmaps))) return heatmaps
def test_read_mnist(self): """ Tests reading from the MNIST LMDB. """ lmdb_path = 'tests/mnist_test_lmdb' lmdb = tools.lmdb_io.LMDB(lmdb_path) keys = lmdb.keys(5) for key in keys: image, label, key = lmdb.read(key) image_path = 'tests/mnist_test/' + key + '.png' assert os.path.exists(image_path) image = cv2.imread(image_path, cv2.CV_LOAD_IMAGE_GRAYSCALE) for i in range(image.shape[0]): for j in range(image.shape[1]): self.assertEqual(image[i, j], image[i, j])
def main(input_pic): img = cv.imread(input_pic,cv.CV_LOAD_IMAGE_GRAYSCALE) img=sp.gaussian_filter(img,sigma=3) img= imresize(img,((len(img)/10),(len(img[0])/10))) img_arr=np.asarray(img,dtype="int32") LoG_arr=LoG_Filter(img_arr) cv.imwrite('LoG_image.jpg',LoG_arr) LoG_arr=cv.imread('LoG_image.jpg',cv.CV_LOAD_IMAGE_GRAYSCALE) Hist=genHistogram(LoG_arr) #print(Hist) for i in range(0,len(LoG_arr)): for j in range(0,len(LoG_arr[0])): if LoG_arr[i][j]<200: LoG_arr[i][j]=0 else: LoG_arr[i][j]=255 cv.imwrite('LoG_image.jpg',LoG_arr) #img_new=cv.imread('LoG_image.jpg',cv.CV_LOAD_IMAGE_GRAYSCALE)
def generate_hdf5(data, output='shit.h5'): lines = [] dst = 'tf_test/' imgs = [] labels = [] for (imgPath, bbx, landmarks) in data: im = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE) imgName = imgPath.split('/')[-1][:-4] bbx_sc = bbx.bbxScale(im.shape, scale=1.1) #print bbx_sc.x, bbx_sc.y, bbx_sc.w, bbx_sc.h im_sc = im[bbx_sc.y:bbx_sc.y+bbx_sc.h, bbx_sc.x:bbx_sc.x+bbx_sc.w] im_sc = cv2.resize(im_sc, (39, 39)) imgs.append(im_sc.reshape(39, 39, 1)) name = dst+imgName+'sc.jpg' lm_sc = bbx_sc.normalizeLmToBbx(landmarks) labels.append(lm_sc.reshape(10)) lines.append(name + ' ' + ' '.join(map(str, lm_sc.flatten())) + '\n') imgs, labels = np.asarray(imgs), np.asarray(labels) imgs = processImage(imgs) with h5py.File('shit.h5', 'w') as h5: h5['data'] = imgs.astype(np.float32) h5['landmark'] = labels.astype(np.float32)
def E(): data = getDataFromTxt(TXT) error = np.zeros((len(data), 3)) for i in range(len(data)): imgPath, bbox, landmarkGt = data[i] landmarkGt = landmarkGt[2:, :] img = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE) assert(img is not None) logger("process %s" % imgPath) landmarkP = NM(img, bbox) # real landmark landmarkP = bbox.reprojectLandmark(landmarkP) landmarkGt = bbox.reprojectLandmark(landmarkGt) error[i] = evaluateError(landmarkGt, landmarkP, bbox) return error
def E(): data = getDataFromTxt(TXT) error = np.zeros((len(data), 3)) for i in range(len(data)): imgPath, bbox, landmarkGt = data[i] landmarkGt = landmarkGt[:3, :] img = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE) assert(img is not None) logger("process %s" % imgPath) landmarkP = EN(img, bbox) # real landmark landmarkP = bbox.reprojectLandmark(landmarkP) landmarkGt = bbox.reprojectLandmark(landmarkGt) error[i] = evaluateError(landmarkGt, landmarkP, bbox) return error
def E(): data = getDataFromTxt(TXT) error = np.zeros((len(data), 5)) for i in range(len(data)): imgPath, bbox, landmarkGt = data[i] img = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE) assert(img is not None) logger("process %s" % imgPath) landmarkP = getResult(img, bbox) # real landmark landmarkP = bbox.reprojectLandmark(landmarkP) landmarkGt = bbox.reprojectLandmark(landmarkGt) error[i] = evaluateError(landmarkGt, landmarkP, bbox) return error
def decode(self, msg): fn = os.path.join(self.directory_, msg) if os.path.exists(fn): im = cv2.imread(fn, cv2.CV_LOAD_IMAGE_COLOR if self.color_ \ else cv2.CV_LOAD_IMAGE_GRAYSCALE) return im_resize(im, shape=self.shape_) else: raise Exception('File does not exist') # Basic type for image annotations
def format_image(image): if len(image.shape) > 2 and image.shape[2] == 3: image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) else: image = cv2.imdecode(image, cv2.CV_LOAD_IMAGE_GRAYSCALE) faces = cascade_classifier.detectMultiScale( image, scaleFactor = 1.3, minNeighbors = 5 ) # None is we don't found an image if not len(faces) > 0: return None max_area_face = faces[0] for face in faces: if face[2] * face[3] > max_area_face[2] * max_area_face[3]: max_area_face = face # Chop image to face face = max_area_face image = image[face[1]:(face[1] + face[2]), face[0]:(face[0] + face[3])] # Resize image to network size try: image = cv2.resize(image, (SIZE_FACE, SIZE_FACE), interpolation = cv2.INTER_CUBIC) / 255. except Exception: print("[+] Problem during resize") return None # cv2.imshow("Lol", image) # cv2.waitKey(0) return image # Load Model
def load_image_vector(img_path): try: M = cv2.imread(img_path, cv2.CV_LOAD_IMAGE_GRAYSCALE) except: read_pgm(img_path) M = cv2.resize(M, (IM_WIDTH, IM_HEIGHT)) M = M.reshape((1, IM_AREA)) return M[0]
def format_image(image): """ Function to format frame """ if len(image.shape) > 2 and image.shape[2] == 3: # determine whether the image is color image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) else: # Image read from buffer image = cv2.imdecode(image, cv2.CV_LOAD_IMAGE_GRAYSCALE) faces = cascade_classifier.detectMultiScale(image,scaleFactor = 1.3 ,minNeighbors = 5) if not len(faces) > 0: return None # initialize the first face as having maximum area, then find the one with max_area max_area_face = faces[0] for face in faces: if face[2] * face[3] > max_area_face[2] * max_area_face[3]: max_area_face = face face = max_area_face # extract ROI of face image = image[face[1]:(face[1] + face[2]), face[0]:(face[0] + face[3])] try: # resize the image so that it can be passed to the neural network image = cv2.resize(image, (48,48), interpolation = cv2.INTER_CUBIC) / 255. except Exception: print("----->Problem during resize") return None return image # Initialize object of EMR class
def get_full_size_labels(self, img_ids, timespan=None): """Get full sized labels.""" if timespan is None: timespan = self.get_default_timespan() with h5py.File(self.h5_fname, 'r') as h5f: num_ex = len(img_ids) y_full = [] for kk, ii in enumerate(img_ids): key = self.get_str_id(ii) data_group = h5f[key] if 'label_segmentation_full_size' in data_group: y_gt_group = data_group['label_segmentation_full_size'] num_obj = len(y_gt_group.keys()) y_full_kk = None for jj in xrange(min(num_obj, timespan)): y_full_jj_str = y_gt_group['{:02d}'.format(jj)][:] y_full_jj = cv2.imdecode( y_full_jj_str, cv2.CV_LOAD_IMAGE_GRAYSCALE).astype('float32') if y_full_kk is None: y_full_kk = np.zeros( [timespan, y_full_jj.shape[0], y_full_jj.shape[1]]) y_full_kk[jj] = y_full_jj y_full.append(y_full_kk) else: y_full.append(np.zeros([timespan] + list(data_group['orig_size'][:]))) return y_full
def get_full_size_labels(self, img_ids, timespan=None): """Get full sized labels.""" if timespan is None: timespan = self.get_default_timespan() with h5py.File(self.h5_fname, "r") as h5f: num_ex = len(img_ids) y_full = [] for kk, ii in enumerate(img_ids): key = self.get_str_id(ii) data_group = h5f[key] if "label_ins_seg_full" in data_group: y_gt_group = data_group["label_ins_seg_full"] num_obj = len(y_gt_group.keys()) y_full_kk = None for jj in range(min(num_obj, timespan)): y_full_jj_str = y_gt_group["{:03d}".format(jj)][:] y_full_jj = cv2.imdecode( y_full_jj_str, cv2.CV_LOAD_IMAGE_GRAYSCALE).astype(np.float32) if y_full_kk is None: y_full_kk = np.zeros( [timespan, y_full_jj.shape[0], y_full_jj.shape[1]]) y_full_kk[jj] = y_full_jj y_full.append(y_full_kk) else: y_full.append(np.zeros([timespan] + list(data_group["orig_size"][:]))) return y_full
def read_pgm(filename): img1 = cv2.imread(filename, cv2.CV_LOAD_IMAGE_GRAYSCALE) h, w = img1.shape[:2] vis0 = np.zeros((h,w), np.float32) vis0[:h, :w] = img1 return vis0 #This method is used to read cover and stego images. #We consider that stego images can be steganographied with differents keys (in practice this seems to be inefficient...)
def calculate_feature(bin_data): """ calculate the feature data of an image parameter : 'bin_data' is the binary stream format of an image return value : a tuple of ( keypoints, descriptors, (height,width) ) keypoints is like [ pt1, pt2, pt3, ... ] descriptors is a numpy array """ buff=numpy.frombuffer(bin_data,numpy.uint8) img_obj=cv2.imdecode(buff,cv2.CV_LOAD_IMAGE_GRAYSCALE) surf=cv2.FeatureDetector_create("SURF") surf.setInt("hessianThreshold",400) surf_extractor=cv2.DescriptorExtractor_create("SURF") keypoints=surf.detect(img_obj,None) keypoints,descriptors=surf_extractor.compute(img_obj,keypoints) res_keypoints=[] for point in keypoints: res_keypoints.append(point.pt) del buff del surf del surf_extractor del keypoints return res_keypoints,numpy.array(descriptors),img_obj.shape
def __init__(self): self.br = CvBridge() # If you subscribe /camera/depth_registered/hw_registered/image_rect topic, the depth image and rgb image are # already registered. So you don't need to call register_depth_to_rgb() # self.depth_image_sub = rospy.Subscriber("/camera/depth_registered/hw_registered/image_rect",Image,self.depth_callback) self.depth_image_sub = rospy.Subscriber("/camera/depth/image_rect",Image,self.depth_callback) self.rgb_image_sub = rospy.Subscriber("/camera/rgb/image_rect_color",Image,self.rgb_callback) self.ir_img = None self.rgb_img = None self.rgb_rmat = None self.rgb_tvec = None self.ir_rmat = None self.ir_tvec = None self.ir_to_rgb_rmat = None self.ir_to_rgb_tvec = None self.depth_image = None self.rgb_image = None self.load_extrinsics() self.load_intrinsics() self.depth_image = None self.rgb_image = None self.count = 0 # self.depth_image = cv2.imread("/home/chentao/depth.png", cv2.CV_LOAD_IMAGE_GRAYSCALE) # self.rgb_image = cv2.imread("/home/chentao/rgb.png")
def convert_to_binary_image(img_path, preview): img = cv2.imread(img_path) if preview: _preview_image("Original Message Image", img, keep_open=True) img_gray = cv2.imread(img_path, cv2.CV_LOAD_IMAGE_GRAYSCALE) if preview: _preview_image("Gray Scale Message Image", img_gray, keep_open=True) (thresh, img_bw) = cv2.threshold(img_gray, 128, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU) if preview: _preview_image("Black & White Message Image", img_bw) return img_bw
def compute(i): img_file = files[i] img = cv2.imread(img_file, cv2.CV_LOAD_IMAGE_GRAYSCALE) if img is None: print 'img {} is None, path correct? --> skip'.format(img_file) return kpts = fe.detect(img) _, descriptors = fe.extract(img, kpts) if descriptors is None or len(descriptors) == 0: print 'WARNING: no descriptors extracted, skip image', img_file sys.exit(1) # Hellinger normalization descriptors += np.finfo(np.float32).eps descriptors /= np.sum(descriptors, axis=1)[:,np.newaxis] descriptors = np.sqrt(descriptors) # output new_basename = os.path.join(args.outputfolder, os.path.basename(os.path.splitext(img_file)[0])) feat_filename = new_basename + '_' + args.detector \ + '_' + args.feature + '.pkl.gz' with gzip.open(feat_filename, 'wb') as f: cPickle.dump(descriptors, f, -1) progress.update(i+1)
def extract_image(filename, resize_height, resize_width): filename1 = 'train/'+filename+'.jpeg' image = cv2.imread(filename1,cv2.CV_LOAD_IMAGE_GRAYSCALE) #image = cv2.imread(filename1) image = cv2.resize(image, (resize_height, resize_width)) #b,g,r = cv2.split(image) #rgb_image = cv2.merge([r,g,b]) cv2.imwrite(filename+'.jpeg', image) return image
def main(img_dir, output_dir, pretrained_phocnet, deploy_proto, min_image_width_height, gpu_id): logging_format = '[%(asctime)-19s, %(name)s, %(levelname)s] %(message)s' logging.basicConfig(level=logging.INFO, format=logging_format) logger = logging.getLogger('Predict PHOCs') if gpu_id is None: caffe.set_mode_cpu() else: caffe.set_mode_gpu() caffe.set_device(gpu_id) logger.info('Loading PHOCNet...') phocnet = caffe.Net(deploy_proto, caffe.TEST, weights=pretrained_phocnet) # find all images in the supplied dir logger.info('Found %d word images to process', len(os.listdir(img_dir))) word_img_list = [cv2.imread(os.path.join(img_dir, filename), cv2.CV_LOAD_IMAGE_GRAYSCALE) for filename in sorted(os.listdir(img_dir)) if filename not in ['.', '..']] # push images through the PHOCNet logger.info('Predicting PHOCs...') predicted_phocs = net_output_for_word_image_list(phocnet=phocnet, word_img_list=word_img_list, min_img_width_height=min_image_width_height) # save everything logger.info('Saving...') np.save(os.path.join(output_dir, 'predicted_phocs.npy'), predicted_phocs) logger.info('Finished')
def get_word_image(self, gray_scale=True): col_type = None if gray_scale: col_type = cv2.CV_LOAD_IMAGE_GRAYSCALE else: col_type = cv2.CV_LOAD_IMAGE_COLOR # load the image ul = self.bounding_box['upperLeft'] wh = self.bounding_box['widthHeight'] img = cv2.imread(self.image_path, col_type) if not np.all(self.bounding_box['widthHeight'] == -1): img = img[ul[1]:ul[1]+wh[1], ul[0]:ul[0]+wh[0]] return img
def format_image(image): if len(image.shape) > 2 and image.shape[2] == 3: image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) else: image = cv2.imdecode(image, cv2.CV_LOAD_IMAGE_GRAYSCALE) faces = cascade_classifier.detectMultiScale( image, scaleFactor=1.3, minNeighbors=5 ) if not len(faces) > 0: return None for (x, y, w, h) in faces: cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2) cv2.putText(frame, str(curr_emotion), (x, y), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 255)) max_area_face = faces[0] for face in faces: if face[2] * face[3] > max_area_face[2] * max_area_face[3]: max_area_face = face face = max_area_face image = image[face[1]:(face[1] + face[2]), face[0]:(face[0] + face[3])] try: image = cv2.resize(image, (48, 48), interpolation=cv2.INTER_CUBIC) / 255. except Exception: print("[+] Problem during resize") return None return image
def im_from_file(f): a = numpy.asarray(bytearray(f.read()), dtype=numpy.uint8) return cv2.imdecode(a, cv2.CV_LOAD_IMAGE_GRAYSCALE)
def generate_bg(num_bg_images): found = False while not found: fname = "bgs/{:08d}.jpg".format(random.randint(0, num_bg_images - 1)) bg = cv2.imread(fname, cv2.CV_LOAD_IMAGE_GRAYSCALE) / 255. if (bg.shape[1] >= OUTPUT_SHAPE[1] and bg.shape[0] >= OUTPUT_SHAPE[0]): found = True x = random.randint(0, bg.shape[1] - OUTPUT_SHAPE[1]) y = random.randint(0, bg.shape[0] - OUTPUT_SHAPE[0]) bg = bg[y:y + OUTPUT_SHAPE[0], x:x + OUTPUT_SHAPE[1]] return bg
def manuallySegmentDisparities(): # Define Source Directories src_dir_anno = '../data/img/terra/405late_20161011194413_3_116_lb' src_dir_left = '/media/paloma/Data1/Linux_Data/TERRA/texas_field_tests/20161011/CS_405late_2016-10-11-19-44-13_PIF3_116_lb/qc_l_tr/rectified' src_dir_right = '/media/paloma/Data1/Linux_Data/TERRA/texas_field_tests/20161011/CS_405late_2016-10-11-19-44-13_PIF3_116_lb/qc_r_tl/rectified' # Read Source File Paths into alist src_xmlfiles = collectFilePaths(src_dir_anno, '.xml') src_imgfiles = collectFilePaths(src_dir_anno, '.jpg') src_imgfiles_left = collectFilePaths(src_dir_left, '.jpg') src_imgfiles_right = collectFilePaths(src_dir_right, '.jpg') # Source Image Checks assert (len(src_xmlfiles) == len(src_imgfiles)), "number of image and annotation files should be equal" assert (len(src_imgfiles_left) == len(src_imgfiles_right)), "number of left and right images should be equal" # Objects and Classes being called stemXMLParser = XMLParser('stem') dispComputer = DisparityComputer() comImgOps = CommonImageOperations() # Define Destination Directories dest_img_left = '/home/paloma/code/OpenCVReprojectImageToPointCloud/CS_405late_2016-10-11-19-44-13_PIF3_116_lb/rgb-image-' dest_disp = '/home/paloma/code/OpenCVReprojectImageToPointCloud/CS_405late_2016-10-11-19-44-13_PIF3_116_lb/disparity-image-' file_idx = 0 for (xmlfile, imgfile, imgfile_right) in zip(src_xmlfiles, src_imgfiles, src_imgfiles_right): print 'File Idx : ' + str(file_idx) xmlroot = (ET.parse(xmlfile)).getroot() img = cv2.imread(imgfile) img_left = cv2.imread(imgfile, cv2.CV_LOAD_IMAGE_GRAYSCALE) img_right = cv2.imread(imgfile_right, cv2.CV_LOAD_IMAGE_GRAYSCALE) mask_stem = stemXMLParser.getLabelMask(img, xmlroot) (disp_left, disp_left_fgnd, img_fgnd) = dispComputer.getDisparity(img_left, img_right) img_left = comImgOps.cropImage(img_left, numrows_crop=45, numcols_crop=35) disp_left = comImgOps.cropImage(disp_left, numrows_crop=45, numcols_crop=35) mask_stem = comImgOps.cropImage(mask_stem, numrows_crop=45, numcols_crop=35) cv2.imwrite(dest_img_left+str(file_idx)+'.ppm', img_left*mask_stem[:,:,1]) cv2.imwrite(dest_disp+str(file_idx)+'.pgm', disp_left*mask_stem[:,:,1]) file_idx = file_idx + 1
