Files
guilan-multimedia-lab/backend/processing/registry.py

343 lines
16 KiB
Python

import math
import cv2
import numpy as np
from .algorithms import (
ProcessingError,
bit_plane,
box_filter,
contrast_stretch,
gamma,
gray_slice,
gray_to_color_sinusoidal,
gray_to_rgb,
histogram_equalization,
histogram_matching,
hsi_intensity_filter,
hsi_to_rgb,
logarithmic,
local_equalization,
negative,
normalize_to_uint8,
pseudo_color_slices,
rgb_to_hsi,
roberts,
sobel,
to_gray,
weighted_average,
median_filter,
high_boost,
ensure_uint8,
)
CH_BASIC = "Basic"
CH3 = "Image Enhancement in the Spatial Domain"
CH4 = "Image Enhancement in the Frequency Domain"
CH6 = "Color Image Processing"
def odd_param(default=3, max_value=35):
return {"type": "int", "default": default, "min": 3, "max": max_value, "step": 2, "odd": True}
def float_param(default, min_value, max_value, step=0.1):
return {"type": "float", "default": default, "min": min_value, "max": max_value, "step": step}
def int_param(default, min_value, max_value, step=1):
return {"type": "int", "default": default, "min": min_value, "max": max_value, "step": step}
def select_param(default, choices):
return {"type": "select", "default": default, "choices": choices}
def bool_param(default=False):
return {"type": "bool", "default": default}
def crop(image, params):
x = max(0, int(params.get("x", 0)))
y = max(0, int(params.get("y", 0)))
width = int(params.get("width", image.shape[1] - x))
height = int(params.get("height", image.shape[0] - y))
if width <= 0 or height <= 0:
raise ProcessingError("Crop width and height must be positive.")
x2 = min(image.shape[1], x + width)
y2 = min(image.shape[0], y + height)
if x >= x2 or y >= y2:
raise ProcessingError("Crop rectangle is outside the image.")
return image[y:y2, x:x2]
def identity(image, params):
return image.copy()
def inverse_log(image, params):
c = float(params.get("c", 1.0))
normalized = image.astype(np.float32) / 255.0
transformed = np.expm1(normalized / max(c, 1e-8))
transformed /= max(float(np.max(transformed)), 1e-8)
return ensure_uint8(np.round(transformed * 255.0))
def threshold(image, params):
level = int(params.get("level", 128))
high = int(params.get("high", 255))
low = int(params.get("low", 0))
gray = to_gray(image)
return gray_to_rgb(np.where(gray >= level, high, low).astype(np.uint8))
def histeq(image, params):
mode = params.get("mode", "intensity")
if image.ndim == 2 or mode == "grayscale":
return histogram_equalization(image, params)
if mode == "rgb":
channels = [histogram_equalization(image[:, :, idx], params)[:, :, 0] for idx in range(3)]
return np.stack(channels, axis=2).astype(np.uint8)
hsi = rgb_to_hsi(image)
intensity = np.round(hsi[..., 2] * 255).astype(np.uint8)
hsi[..., 2] = histogram_equalization(intensity, params)[:, :, 0].astype(np.float32) / 255.0
return hsi_to_rgb(hsi)
def gaussian_noise(image, params):
mean = float(params.get("mean", 0))
variance = float(params.get("variance", 0.01))
sigma = math.sqrt(max(variance, 0.0)) * 255.0
noise = np.random.default_rng().normal(mean * 255.0, sigma, size=image.shape)
return ensure_uint8(np.round(image.astype(np.float32) + noise))
def salt_pepper_noise(image, params):
amount = float(params.get("amount", 0.03))
salt_ratio = float(params.get("salt_ratio", 0.5))
output = image.copy()
rng = np.random.default_rng()
mask = rng.random(image.shape[:2])
salt = mask < amount * salt_ratio
pepper = (mask >= amount * salt_ratio) & (mask < amount)
output[salt] = 255
output[pepper] = 0
return output
def speckle_noise(image, params):
variance = float(params.get("variance", 0.04))
noise = np.random.default_rng().normal(0, math.sqrt(max(variance, 0.0)), size=image.shape)
return ensure_uint8(np.round(image.astype(np.float32) + image.astype(np.float32) * noise))
def gaussian_filter(image, params):
size = int(params.get("size", 3))
variance = float(params.get("variance", 1.0))
if size < 3 or size % 2 == 0:
raise ProcessingError("size must be an odd integer >= 3.")
sigma = math.sqrt(max(variance, 1e-8))
return cv2.GaussianBlur(image, (size, size), sigmaX=sigma, sigmaY=sigma, borderType=cv2.BORDER_REFLECT)
def max_filter(image, params):
size = int(params.get("size", 3))
if size < 3 or size % 2 == 0:
raise ProcessingError("size must be an odd integer >= 3.")
return cv2.dilate(image, np.ones((size, size), np.uint8))
def min_filter(image, params):
size = int(params.get("size", 3))
if size < 3 or size % 2 == 0:
raise ProcessingError("size must be an odd integer >= 3.")
return cv2.erode(image, np.ones((size, size), np.uint8))
def laplacian_slide(image, params):
mask_name = params.get("mask", "cross")
kernels = {
"cross": np.array([[0, 1, 0], [1, -5, 1], [0, 1, 0]], dtype=np.float32),
"diagonal": np.array([[1, 1, 1], [1, -9, 1], [1, 1, 1]], dtype=np.float32),
"zero_sum_cross": np.array([[0, 1, 0], [1, -4, 1], [0, 1, 0]], dtype=np.float32),
"zero_sum_diagonal": np.array([[1, 1, 1], [1, -8, 1], [1, 1, 1]], dtype=np.float32),
}
kernel = kernels.get(mask_name)
if kernel is None:
raise ProcessingError("Unknown Laplacian mask.")
channels = [cv2.filter2D(image[:, :, idx], cv2.CV_32F, kernel, borderType=cv2.BORDER_REFLECT) for idx in range(image.shape[2])]
result = np.stack(channels, axis=2)
return normalize_to_uint8(result) if params.get("mode", "sharpen") == "detail" else ensure_uint8(result)
def gradient_abs_sum(image, params):
operator = params.get("operator", "sobel")
gray = to_gray(image).astype(np.float32)
if operator == "roberts":
gx = np.array([[-1, 0], [0, 1]], dtype=np.float32)
gy = np.array([[0, -1], [1, 0]], dtype=np.float32)
else:
gx = np.array([[-1, -2, -1], [0, 0, 0], [1, 2, 1]], dtype=np.float32)
gy = np.array([[-1, 0, 1], [-2, 0, 2], [-1, 0, 1]], dtype=np.float32)
fx = cv2.filter2D(gray, cv2.CV_32F, gx, borderType=cv2.BORDER_REFLECT)
fy = cv2.filter2D(gray, cv2.CV_32F, gy, borderType=cv2.BORDER_REFLECT)
return gray_to_rgb(normalize_to_uint8(np.abs(fx) + np.abs(fy)))
def rgb_channel(image, params):
channel = params.get("channel", "r")
index = {"r": 0, "g": 1, "b": 2}.get(channel, 0)
return gray_to_rgb(image[:, :, index])
def hsi_view(image, params):
component = params.get("component", "i")
hsi = rgb_to_hsi(image)
index = {"h": 0, "s": 1, "i": 2}.get(component, 2)
return gray_to_rgb(np.round(hsi[:, :, index] * 255.0).astype(np.uint8))
def fft_spectrum(image, params):
gray = to_gray(image).astype(np.float32)
spectrum = np.fft.fftshift(np.fft.fft2(gray))
mode = params.get("mode", "log_magnitude")
if mode == "phase":
return gray_to_rgb(normalize_to_uint8(np.angle(spectrum)))
magnitude = np.abs(spectrum)
if mode == "log_magnitude":
magnitude = np.log1p(magnitude)
return gray_to_rgb(normalize_to_uint8(magnitude))
def distance_grid(shape):
rows, cols = shape
u = np.arange(rows) - rows / 2
v = np.arange(cols) - cols / 2
vv, uu = np.meshgrid(v, u)
return np.sqrt(uu**2 + vv**2)
def frequency_filter(image, params):
gray = to_gray(image).astype(np.float32)
d0 = float(params.get("cutoff", 40))
order = int(params.get("order", 2))
family = params.get("family", "gaussian")
kind = params.get("kind", "lowpass")
d = distance_grid(gray.shape)
if family == "ideal":
mask = (d <= d0).astype(np.float32)
elif family == "butterworth":
mask = 1.0 / (1.0 + (d / max(d0, 1e-8)) ** (2 * max(order, 1)))
else:
mask = np.exp(-(d**2) / (2.0 * max(d0, 1e-8) ** 2))
if kind == "highpass":
mask = 1.0 - mask
if params.get("output", "image") == "mask":
return gray_to_rgb(normalize_to_uint8(mask))
f = np.fft.fftshift(np.fft.fft2(gray))
result = np.real(np.fft.ifft2(np.fft.ifftshift(f * mask)))
return gray_to_rgb(normalize_to_uint8(result))
def frequency_laplacian(image, params):
gray = to_gray(image).astype(np.float32)
rows, cols = gray.shape
u = np.arange(rows) - rows / 2
v = np.arange(cols) - cols / 2
vv, uu = np.meshgrid(v, u)
h = -4.0 * (np.pi**2) * (uu**2 + vv**2)
f = np.fft.fftshift(np.fft.fft2(gray))
result = np.real(np.fft.ifft2(np.fft.ifftshift(f * h)))
return gray_to_rgb(normalize_to_uint8(result))
def correlation(image, params):
kernel = np.array(params.get("kernel", [[1, 1, 1], [1, 1, 1], [1, 1, 1]]), dtype=np.float32)
kernel /= max(float(np.sum(np.abs(kernel))), 1e-8)
gray = to_gray(image).astype(np.float32)
return gray_to_rgb(normalize_to_uint8(cv2.filter2D(gray, cv2.CV_32F, kernel, borderType=cv2.BORDER_REFLECT)))
def convolution(image, params):
kernel = np.array(params.get("kernel", [[1, 1, 1], [1, 1, 1], [1, 1, 1]]), dtype=np.float32)
return correlation(image, {"kernel": np.flipud(np.fliplr(kernel)).tolist()})
def bone_scan_workflow(image, params):
gray_rgb = gray_to_rgb(to_gray(image))
lap_detail = laplacian_slide(gray_rgb, {"mask": "zero_sum_diagonal", "mode": "detail"})
sharpened = ensure_uint8(gray_rgb.astype(np.float32) + lap_detail.astype(np.float32))
sobel_img = gradient_abs_sum(gray_rgb, {"operator": "sobel"})
smooth_sobel = box_filter(sobel_img, {"size": 5})
mask = normalize_to_uint8((sharpened.astype(np.float32) * smooth_sobel.astype(np.float32)) / 255.0)
summed = ensure_uint8(gray_rgb.astype(np.float32) + mask.astype(np.float32))
return gamma(summed, {"gamma": float(params.get("gamma", 0.5)), "c": 1.0})
def operation(id, label, chapter, slide_group, func, params=None, supports="both"):
return {
"id": id,
"label": label,
"chapter": chapter,
"slide_group": slide_group,
"params": params or {},
"supports": supports,
"func": func,
}
OPERATIONS = [
operation("crop", "Crop", CH_BASIC, "Workspace", crop, {"x": int_param(0, 0, 4000), "y": int_param(0, 0, 4000), "width": int_param(256, 1, 8000), "height": int_param(256, 1, 8000)}),
operation("identity", "Identity", CH3, "Point Processing", identity),
operation("negative", "Negative", CH3, "Point Processing", negative),
operation("log", "Log", CH3, "Point Processing", logarithmic, {"c": float_param(1.44, 0.1, 5, 0.05)}),
operation("inverse_log", "Inverse Log", CH3, "Point Processing", inverse_log, {"c": float_param(1.0, 0.1, 5, 0.05)}),
operation("gamma", "Power-Law / Gamma", CH3, "Point Processing", gamma, {"gamma": float_param(1.0, 0.1, 5, 0.05), "c": float_param(1.0, 0.1, 3, 0.05)}),
operation("threshold", "Thresholding", CH3, "Point Processing", threshold, {"level": int_param(128, 0, 255), "low": int_param(0, 0, 255), "high": int_param(255, 0, 255)}),
operation("contrast_stretch", "Contrast Stretching", CH3, "Piecewise Linear", contrast_stretch, {"low": int_param(30, 0, 254), "high": int_param(220, 1, 255)}),
operation("gray_slice", "Gray-Level Slicing", CH3, "Piecewise Linear", gray_slice, {"start": int_param(96, 0, 255), "end": int_param(160, 0, 255), "preserve_background": bool_param(True)}),
operation("bit_plane", "Bit-Plane Slicing", CH3, "Piecewise Linear", bit_plane, {"bit": int_param(7, 0, 7)}),
operation("histeq", "histeq()", CH3, "Histogram Processing", histeq, {"mode": select_param("intensity", ["intensity", "rgb", "grayscale"])}),
operation("hist_match", "Histogram Specification", CH3, "Histogram Processing", histogram_matching, {"target": select_param("uniform", ["uniform", "dark", "bright", "bimodal"])}),
operation("local_equalization", "Local Enhancement", CH3, "Histogram Processing", local_equalization, {"size": odd_param(7, 31)}),
operation("gaussian_noise", "Add Gaussian Noise", CH3, "Noise and Denoising", gaussian_noise, {"mean": float_param(0, -1, 1, 0.01), "variance": float_param(0.01, 0, 0.2, 0.005)}),
operation("salt_pepper_noise", "Add Salt & Pepper Noise", CH3, "Noise and Denoising", salt_pepper_noise, {"amount": float_param(0.03, 0, 0.5, 0.01), "salt_ratio": float_param(0.5, 0, 1, 0.05)}),
operation("speckle_noise", "Add Speckle Noise", CH3, "Noise and Denoising", speckle_noise, {"variance": float_param(0.04, 0, 0.3, 0.01)}),
operation("box_filter", "Box / Average Filter", CH3, "Smoothing Linear Filters", box_filter, {"size": odd_param(3, 35)}),
operation("weighted_average", "Weighted Average Filter", CH3, "Smoothing Linear Filters", weighted_average, {"size": odd_param(3, 35)}),
operation("gaussian_filter", "Gaussian fspecial Filter", CH3, "Smoothing Linear Filters", gaussian_filter, {"size": odd_param(3, 35), "variance": float_param(1.0, 0.01, 25, 0.1)}),
operation("median_filter", "Median Filter", CH3, "Order-Statistics Filters", median_filter, {"size": odd_param(3, 25)}),
operation("max_filter", "Max Filter", CH3, "Order-Statistics Filters", max_filter, {"size": odd_param(3, 25)}),
operation("min_filter", "Min Filter", CH3, "Order-Statistics Filters", min_filter, {"size": odd_param(3, 25)}),
operation("laplacian_slide", "Laplacian Masks", CH3, "Sharpening Spatial Filters", laplacian_slide, {"mask": select_param("cross", ["cross", "diagonal", "zero_sum_cross", "zero_sum_diagonal"]), "mode": select_param("sharpen", ["sharpen", "detail"])}),
operation("gradient_abs_sum", "Gradient abs(imfilter Gx)+abs(imfilter Gy)", CH3, "Gradient Operator", gradient_abs_sum, {"operator": select_param("sobel", ["sobel", "roberts"])}),
operation("sobel", "Sobel Magnitude", CH3, "Gradient Operator", sobel),
operation("roberts", "Roberts Magnitude", CH3, "Gradient Operator", roberts),
operation("high_boost", "High-Boost Filtering", CH3, "High-Boost Filtering", high_boost, {"amplification": float_param(1.5, 1, 6, 0.1), "size": odd_param(3, 35)}),
operation("bone_scan_workflow", "Bone Scan Workflow Preset", CH3, "Combining Spatial Enhancement Methods", bone_scan_workflow, {"gamma": float_param(0.5, 0.1, 2, 0.05)}),
operation("fft_spectrum", "FFT/DFT Spectrum View", CH4, "DFT and FFT", fft_spectrum, {"mode": select_param("log_magnitude", ["magnitude", "log_magnitude", "phase"])}),
operation("frequency_filter", "Ideal/Butterworth/Gaussian Frequency Filter", CH4, "Frequency Domain Filtering", frequency_filter, {"family": select_param("gaussian", ["ideal", "butterworth", "gaussian"]), "kind": select_param("lowpass", ["lowpass", "highpass"]), "cutoff": float_param(40, 1, 512, 1), "order": int_param(2, 1, 10), "output": select_param("image", ["image", "mask"])}),
operation("frequency_laplacian", "Laplacian in Frequency Domain", CH4, "Sharpening Highpass Filtering", frequency_laplacian),
operation("convolution", "Convolution Utility", CH4, "Convolution", convolution),
operation("correlation", "Correlation Utility", CH4, "Correlation", correlation),
operation("rgb_channel", "RGB Channel View", CH6, "RGB color model", rgb_channel, {"channel": select_param("r", ["r", "g", "b"])}),
operation("hsi_view", "HSI Component View", CH6, "HSI color model", hsi_view, {"component": select_param("i", ["h", "s", "i"])}),
operation("hsi_intensity_filter", "HSI Intensity Processing", CH6, "HSI color model", hsi_intensity_filter, {"method": select_param("smooth", ["smooth", "sharpen"]), "size": odd_param(3, 25)}),
operation("pseudo_color_slices", "Pseudocolor Intensity Slicing", CH6, "Pseudocolor Image Processing", pseudo_color_slices),
operation("gray_to_color_sinusoidal", "Gray-Level to Color Transform", CH6, "Gray level to color transformation", gray_to_color_sinusoidal, {"hue_frequency": float_param(1, 0.2, 4, 0.1), "saturation_frequency": float_param(0.5, 0.1, 4, 0.1), "intensity_frequency": float_param(0.25, 0.1, 4, 0.1)}),
]
OPERATION_MAP = {item["id"]: item for item in OPERATIONS}
def operation_metadata():
return [{key: value for key, value in item.items() if key != "func"} for item in OPERATIONS]
def apply_registered_operation(image, operation_id, params=None):
item = OPERATION_MAP.get(operation_id)
if item is None:
raise ProcessingError(f"Unsupported operation '{operation_id}'.")
return ensure_uint8(item["func"](ensure_uint8(image), params or {}))