cang-ying/tools/vision-analyzer.py

#!/usr/bin/env python3
"""铸渊之眼 · 视觉分析器 · 定量对比两张图的风格一致性

用法:
  python3 vision-analyzer.py <image1.jpg> <image2.jpg>   # 对比两张图
  python3 vision-analyzer.py <image.jpg>                  # 分析单张图
  
输出JSON: style_consistency_score, color_palettes, texture_similarity, composition_analysis
"""

import sys
import json
import colorsys
from PIL import Image
import numpy as np

def analyze_image(path, label):
    """分析单张图片的视觉特征"""
    img = Image.open(path).convert('RGB')
    w, h = img.size
    arr = np.array(img)

    # 1. 整体色调分析 — HSV直方图
    hsv_arr = np.array([colorsys.rgb_to_hsv(r/255, g/255, b/255) 
                        for r,g,b in arr.reshape(-1, 3)])
    hue_hist = np.histogram(hsv_arr[:,0], bins=12, range=(0,1))[0]
    sat_hist = np.histogram(hsv_arr[:,1], bins=8, range=(0,1))[0]
    val_hist = np.histogram(hsv_arr[:,2], bins=8, range=(0,1))[0]
    
    # 主色调
    dominant_hues = []
    for i in np.argsort(hue_hist)[-3:]:
        hue_name = ["红","橙","黄","黄绿","绿","青绿","青","蓝","紫","品红","粉红","红"][i]
        dominant_hues.append(hue_name)
    
    # 2. 构图分析 — 9宫格亮度和边缘密度
    grid_mask = np.zeros(h, dtype=int)
    for i in range(1,9):
        grid_mask = np.where(np.arange(h) < h*i/9, i, grid_mask)
    
    # 简化：水平/垂直分三区的平均亮度
    bands_h = [arr[h*i//3:h*(i+1)//3, :, :].mean() for i in range(3)]
    bands_v = [arr[:, w*i//3:w*(i+1)//3, :].mean() for i in range(3)]
    
    # 3. 纹理复杂度 — 标准差
    texture_std = arr.std(axis=(0,1)).mean()
    
    # 4. 色彩丰富度
    color_variance = hsv_arr[:,1].std()
    
    # 5. 亮暗对比度
    contrast = arr.max() - arr.min()
    avg_brightness = arr.mean()
    
    return {
        "label": label,
        "size": [w, h],
        "dominant_hues": dominant_hues,
        "avg_brightness": round(float(avg_brightness), 1),
        "contrast": round(float(contrast), 1),
        "texture_std": round(float(texture_std), 1),
        "color_variance": round(float(color_variance), 3),
        "horizontal_brightness": [round(float(b), 1) for b in bands_h],
        "vertical_brightness": [round(float(b), 1) for b in bands_v],
        "hue_distribution": [int(h) for h in hue_hist],
        "sat_distribution": [int(s) for s in sat_hist],
        "val_distribution": [int(v) for v in val_hist]
    }

def compare_images(a, b):
    """对比两张图并给出风格一致性评分"""
    # 色调相似度 — hue分布的相关性
    h1, h2 = np.array(a["hue_distribution"]), np.array(b["hue_distribution"])
    if h1.sum() > 0 and h2.sum() > 0:
        h1_norm, h2_norm = h1/h1.sum(), h2/h2.sum()
        hue_corr = np.corrcoef(h1_norm, h2_norm)[0,1]
    else:
        hue_corr = 0
    hue_score = max(0, float(hue_corr))
    
    # 亮度相似度
    bright_diff = abs(a["avg_brightness"] - b["avg_brightness"])
    bright_score = max(0, 1 - bright_diff / 100)
    
    # 纹理相似度
    tex_diff = abs(a["texture_std"] - b["texture_std"])
    tex_score = max(0, 1 - tex_diff / 50)
    
    # 色彩丰富度相似度
    cv_diff = abs(a["color_variance"] - b["color_variance"])
    cv_score = max(0, 1 - cv_diff * 10)
    
    # 综合评分
    consistency = round(float(hue_score * 0.35 + bright_score * 0.25 + tex_score * 0.25 + cv_score * 0.15) * 100, 1)
    
    verdict = (
        "✅ 高度一致" if consistency >= 85 else
        "🟢 基本一致" if consistency >= 70 else
        "🟡 有差异" if consistency >= 50 else
        "🔴 严重不一致"
    )
    
    return {
        "style_consistency_score": consistency,
        "verdict": verdict,
        "breakdown": {
            "色调相似度": round(float(hue_score * 100), 1),
            "亮度相似度": round(float(bright_score * 100), 1),
            "纹理相似度": round(float(tex_score * 100), 1),
            "色彩丰富度相似度": round(float(cv_score * 100), 1)
        },
        "issues": []
    }

if __name__ == "__main__":
    if len(sys.argv) < 2:
        print(json.dumps({"error": "usage: vision-analyzer.py <image1> [image2]"}))
        sys.exit(1)
    
    if len(sys.argv) == 2:
        result = analyze_image(sys.argv[1], sys.argv[1])
    else:
        a = analyze_image(sys.argv[1], sys.argv[1])
        b = analyze_image(sys.argv[2], sys.argv[2])
        comparison = compare_images(a, b)
        result = {
            "image_a": a,
            "image_b": b,
            "comparison": comparison
        }
    
    print(json.dumps(result, ensure_ascii=False, indent=2))