def newimg(img): #Image will be taken for Deskewing newim = Deskew.deskew(img) #Deskew the image #print(newim) data = MyClust.get_all_points( newim) #Gives all points according to threshold print("Shape:", data.shape[0]) if (data.shape[0] < 300): print("Continue") else: print("Nice try !!!!") return ############# CLUSTERING ################# lm = MyClust.Get_Clusters( data, num_clusters) #Data of all points will be clustered into some points lm2 = np.array(Euclid.fun1(lm, num_clusters)) #Distance array of all clusters #print(lm2) lm2 = Ham.Shortest_path_way( lm2, num_clusters) #Order of the path it needed to travel #print(lm2) lm2 = np.array(lm2[0][:-1], dtype=np.int64) #print(lm2) mm = Ham.path_order( lm2, lm, num_clusters) #After sorting of the landmarks,path has been defined #print(mm) return (mm) #Returning path to comp2
def newimg(img_no): newim = Deskew.deskew(test_images[img_no]) #print(newim) data= MyClust.get_all_points(newim) ############# CLUSTERING ################# lm= MyClust.Get_Cluster(data,num_clusters) lm2= np.array(Euclid.fun1(lm,num_clusters)) #print(lm2) lm2= Ham.fun3(lm2,num_clusters) lm2= np.array(lm2[0],dtype= np.int64) order= lm2[:-1] mm= Ham.path_order(order,lm,num_clusters) #print(mm) return(mm)