I am currently working on developing an image classification model to identify different species of deer in the United States. As part of this process, I am utilizing Principal Component Analysis (PCA) to reduce the memory size of the images and optimize the run time of the model.
However, I have encountered a puzzling issue where all the new PCA-compressed images generated by my Deer_PCA function are larger in file size compared to the original images. For instance, the original image was 128 KB, but the compressed version after running it with n_components = 150 now stands at 293 KB. Can anyone shed some light on why this unexpected outcome is happening?
Below is the image that was processed using the function; make sure to place the image in an empty folder before executing the code:
Here is the resulting compressed image obtained after applying the Deer_PCA function:
Displayed below is the code implementation:
# Required packages
import cv2
import os,sys
from PIL import Image
import pandas as pd
from scipy.stats import stats
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
# Function to perform PCA on images within a specific folder and save them in another folder
def Deer_PCA(inpath, outpath,n_comp):
for image_path in os.listdir(inpath):
# Read input file
input_path = os.path.join(inpath, image_path)
print(input_path)
w_deer = cv2.cvtColor(cv2.imread(input_path), cv2.COLOR_BGR2RGB)
# Split channels
blue_2,green_2,red_2 = cv2.split(w_deer)
# Scale channels
w_blue = blue_2/255
w_green = green_2/255
w_red = red_2/255
# Perform PCA on each channel
pca_b2 = PCA(n_components=n_comp)
pca_b2.fit(w_blue)
trans_pca_b2 = pca_b2.transform(w_blue)
pca_g2 = PCA(n_components=n_comp)
pca_g2.fit(w_green)
trans_pca_g2 = pca_g2.transform(w_green)
pca_r2 = PCA(n_components=n_comp)
pca_r2.fit(w_red)
trans_pca_r2 = pca_r2.transform(w_red)
# Merge channels post-PCA
b_arr2 = pca_b2.inverse_transform(trans_pca_b2)
g_arr2 = pca_g2.inverse_transform(trans_pca_g2)
r_arr2 = pca_r2.inverse_transform(trans_pca_r2)
img_reduced2 = (cv2.merge((b_arr2, g_arr2, r_arr2)))
print("Merge Successful")
# Save output
fullpath = os.path.join(outpath, 'PCA_'+image_path)
cv2.imwrite(fullpath, img_reduced2*255)
print("Successfully saved\n")
# Check image sizes
original_image_path = '/Users/matthew_macwan/Downloads/CIS/I_Class_Deer/mule_deer_doe/mule deer doe_1.jpeg'
PCA_compressed_image_path = '/Users/matthew_macwan/Downloads/CIS/I_Class_Deer/mule_deer_doe/PCA_mule deer doe_1.jpeg'
print('Original Image:',sys.getsizeof(original_image_path))
print('PCA Image:',sys.getsizeof(PCA_compressed_image_path))