python：opencv比较直方图wird结果

Question

I'm using builtin opencv function to open image, remove background, crop image, and then calculate histogram of file, to compare it with histogram of different file.

To compare histograms I'm using BGR color space with function: cv2.compareHist(hist_1, hist_2, cv2.HISTCMP_CORREL)

My code is

def cv_histogram(image, channels=[0, 1, 2], hist_size=[10, 10, 10], hist_range=[0, 256, 0, 256, 0, 256], hist_type='BGR'):
    #convert to different color space if needed
    if hist_type=='HSV':    image = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
    elif hist_type=='GRAY': image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    elif hist_type=='RGB':  image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

    image_hist = cv2.calcHist([image], channels, None, hist_size, hist_range)
    image_hist = cv2.normalize(image_hist, image_hist).flatten()
    return image_hist

def cv_compare_images_histogram(img_base, img_compare, method='correlation'):
    hist_1 = cv_histogram(img_base)
    hist_2 = cv_histogram(img_compare)

    if method == "intersection":
        comparison = cv2.compareHist(hist_1, hist_2, cv2.HISTCMP_INTERSECT)
    else:
        comparison = cv2.compareHist(hist_1, hist_2, cv2.HISTCMP_CORREL)
    return comparison

im1 = image_remove_background(cv2.imread("1.jpg"), bg_lower_bgr, bg_upper_bgr)
im2 = image_remove_background(cv2.imread("2.jpg"), bg_lower_bgr, bg_upper_bgr)
sim = cv_compare_images_histogram(im1, im2)
img_new = image_stack(im1, im2)
cv2.imshow('img_new', img_new)
print("Histogram similarity is: ", sim)

as on screen below, images have different colors/objects, but I receive very high correlation: 0.9198019904818888

Script works perfect for most of files, any idea WHY so wired results?

Answer 1

After creating visual histograms for those two images and investigating more, the problem was, after removing background (replacing with black pixels), there was a huge spike in pixels with pitchblack color [0,0,0] which with bin size-10, resulted in very high correlation.

To resolve issue I had to create histograms without black pixels, by removing them from histogram range: hist_range=[1, 256, 1, 256, 1, 256]