Fast GLCM feature Computing using Python3

Question

** What I want to do is computing GLCM features using Python 3.0x in a fast way and the features mean value of the total group of images togeher with single feature value of an image should be painted on each images. A sample image without mean value is like this . And the Feature values include entropy, contrast, angular second moment etc. Any idiea for accelerating this process is appreciated. **

gray_level = 64    

def maxGrayLevel(img):
    max_gray_level = 0
    (height, width) = img.shape
    print(height, width)

    for y in range(height):
        for x in range(width):
            if img[y][x] > max_gray_level:
                max_gray_level = img[y][x]
    return max_gray_level + 1


def getGlcm(input, d_x, d_y):
    srcdata = input.copy()
    ret = [[0.0 for i in range(gray_level)] for j in range(gray_level)]
    (height, width) = input.shape
    max_gray_level = maxGrayLevel(input)

    # 若灰度级数大于gray_level，则将图像的灰度级缩小至gray_level，减小灰度共生矩阵的大小
    if max_gray_level > gray_level:
        for j in range(height):
            for i in range(width):
                srcdata[j][i] = srcdata[j][i] * gray_level / max_gray_level

    for j in range(height - d_y):
        for i in range(width - d_x):
            rows = srcdata[j][i]
            cols = srcdata[j + d_y][i + d_x]
            ret[rows][cols] += 1.0

    for i in range(gray_level):
        for j in range(gray_level):
            ret[i][j] /= float(height * width)

    return ret


def feature_computer(p):
    '''
    :param p: 单张灰度图片矩阵
    :return: 四个 GLCM 特征值
    '''
    Con = 0.0
    Ent = 0.0
    Asm = 0.0
    Idm = 0.0
    for i in range(gray_level):
        for j in range(gray_level):
            Con += (i - j) * (i - j) * p[i][j]
            Asm += p[i][j] * p[i][j]
            Idm += p[i][j] / (1 + (i - j) * (i - j))
            if p[i][j] > 0.0:
                Ent += p[i][j] * math.log(p[i][j])
    return Asm, Con, -Ent, Idm
def Put_text(im_path):
    # for im_path in files:
        im_name = im_path.split('\\')[-1]
        suffix_path = im_path.split('\\')[-2]
        new_path_head = r'I:\DATA\Texture-based-data\annot_texture'
        new_path = os.path.join(new_path_head, suffix_path)
        new_root_im_name = os.path.join(new_path, im_name)
        if not os.path.exists(new_path):
            os.makedirs(new_path)
        if not os.path.exists(new_root_im_name):
            im = cv2.imread(im_path)
            try:
                img_shape = im.shape
            except:
                print('imread error')
                return

            img = cv2.resize(im, (int(img_shape[1] / 2), int(img_shape[0] / 2)), interpolation=cv2.INTER_CUBIC)
            img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
            glcm_0 = getGlcm(img_gray, 1, 0)
            asm, con, ent, idm = feature_computer(glcm_0)



            imgzi = New_put_text('asm'+str(asm)+'\n'+'con'+str(con)+'\n'+'ent'+str(ent)+'\n'+'idm'+str(idm), img)


            cv2.imwrite(new_root_im_name, img)
            print(new_root_im_name, '\n', getImageVar(im), asm, con, ent, idm)
 if __name__ == '__main__':
        subfiles = [f for f in glob.glob(os.path.join(sub_files, r'*bmp'))]
        p = Pool(4)
        p.map(Put_text, subfiles)

Answer 1

Hey I used GLCM at my project too you can check it on https://github.com/ellengiacometti/LemonCV?files=1

I used greycoprops and it works pretty fast. Here is a piece of Trata Imagem.py for example:

glcm = greycomatrix(gray_BoundingBox, [5], [0], 256, 
symmetric=True, normed=True)
dissimilarity= greycoprops(glcm, 'dissimilarity')[0, 0]
correlation= greycoprops(glcm, 'correlation')[0, 0]
homogeneity = greycoprops(glcm,'homogeneity')[0, 0]
energy = greycoprops(glcm, 'energy')[0, 0]
contrast= greycoprops(glcm, 'contrast')[0, 0]
ASM = greycoprops(glcm,'ASM')[0,0]

I hope it works for you :)