From 5dabb8f8078970af7f557d5686bbb705eb1e9940 Mon Sep 17 00:00:00 2001 From: jinye_huang Date: Tue, 6 May 2025 16:52:03 +0800 Subject: [PATCH] =?UTF-8?q?=E6=95=B0=E5=AD=97=E6=8C=87=E7=BA=B9=E6=98=AF?= =?UTF-8?q?=E9=94=99=E7=9A=84=20=E6=8A=97=E5=93=88=E5=B8=8C=E6=98=AF?= =?UTF-8?q?=E9=94=99=E7=9A=84?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- utils/poster_notes_creator.py | 332 ++++++++++++++++++++++------------ 1 file changed, 212 insertions(+), 120 deletions(-) diff --git a/utils/poster_notes_creator.py b/utils/poster_notes_creator.py index dd08bb5..d919cc9 100644 --- a/utils/poster_notes_creator.py +++ b/utils/poster_notes_creator.py @@ -316,42 +316,42 @@ class PosterNotesCreator: ): """处理单张图像 - 此方法可在独立进程中运行""" try: - # 加载图像 + # 加载图像 image = Image.open(image_path) - - # 处理图像为3:4比例，并添加微小变化 + + # 处理图像为3:4比例，并添加微小变化 processed_image = self.optimized_process_image( - image, - (3, 4), - add_variation=True, + image, + (3, 4), + add_variation=True, seed=seed, - variation_strength=variation_strength, - extra_effects=extra_effects - ) - - # 创建元数据 + variation_strength=variation_strength, + extra_effects=extra_effects + ) + + # 创建元数据 additional_metadata = { - "original_image": image_filename, + "original_image": image_filename, "additional_index": index + 1, "source_dir": source_dir, - "is_additional_image": True, - "processed": True, - "aspect_ratio": "3:4", - "variation_applied": True, - "variation_strength": variation_strength, - "extra_effects": extra_effects - } - - # 使用输出处理器保存图像 + "is_additional_image": True, + "processed": True, + "aspect_ratio": "3:4", + "variation_applied": True, + "variation_strength": variation_strength, + "extra_effects": extra_effects + } + + # 使用输出处理器保存图像 return self.output_handler.handle_generated_image( - run_id, - topic_index, - variant_index, - 'additional', # 图像类型为additional - processed_image, - output_filename, - additional_metadata - ) + run_id, + topic_index, + variant_index, + 'additional', # 图像类型为additional + processed_image, + output_filename, + additional_metadata + ) except Exception as e: logger.error(f"处理图像时出错 '{image_filename}': {e}") logger.error(traceback.format_exc()) @@ -376,6 +376,7 @@ class PosterNotesCreator: return image try: + logger.debug(f"应用DCT噪声，强度: {intensity:.3f}") # 确保是灰度图或提取亮度通道 (这里以灰度为例) if image.mode != 'L': # 如果是彩色图，可以在 Y 通道 (亮度) 操作 @@ -436,11 +437,15 @@ class PosterNotesCreator: r = Image.blend(r, modified_gray, blend_factor) g = Image.blend(g, modified_gray, blend_factor) b = Image.blend(b, modified_gray, blend_factor) - return Image.merge('RGB', (r, g, b)) + merged_image = Image.merge('RGB', (r, g, b)) else: # 如果原图是灰度或处理失败，返回修改后的灰度图 - return modified_gray + merged_image = modified_gray + # 在函数末尾成功时记录 + logger.debug("DCT噪声应用成功。") + return merged_image if 'merged_image' in locals() else modified_gray # 返回最终结果 + except Exception as e: logger.error(f"DCT噪声注入出错: {e}") return image # 出错时返回原图 @@ -457,13 +462,15 @@ class PosterNotesCreator: Returns: 添加扰动后的图像 """ + logger.debug(f"调用add_dct_noise对抗pHash，强度: {intensity:.3f}") return self.add_dct_noise(image, intensity=intensity) def optimize_anti_hash_methods(self, image: Image.Image, strength: str = "medium") -> Image.Image: - """ - 综合优化的哈希对抗方法，强度已增加 - """ - # 根据强度设置参数 (显著增加 high 强度) + """综合优化的哈希对抗方法，强度已增加，添加日志记录，High强度极度强化""" + logger.info(f"--- 开始优化抗哈希方法 (强度: {strength}) ---") + original_image_for_logging = image.copy() # 复制一份用于前后对比日志 + + # 根据强度设置参数 (极度增加 high 强度) if strength == "low": ahash_intensity = 0.03 phash_intensity = 0.05 # 基础DCT噪声强度 @@ -471,114 +478,159 @@ class PosterNotesCreator: region_flip_prob = 0.3 num_ahash_blocks = random.randint(8, 15) num_dhash_lines = random.randint(6, 10) + ahash_delta_range = (-30, 30) + dhash_delta_range = 30 + region_max_factor = 25 + gaussian_noise_sigma = 0.0 # Low 不加高斯噪声 + gaussian_noise_prob = 0.0 elif strength == "high": - ahash_intensity = 0.18 # 大幅增加 - phash_intensity = 0.15 # 大幅增加 - dhash_intensity = 0.18 # 大幅增加 - region_flip_prob = 0.7 # 更大概率翻转 - num_ahash_blocks = random.randint(20, 35) # 更多块 - num_dhash_lines = random.randint(15, 25) # 更多线 - else: # medium - ahash_intensity = 0.08 # 增加 - phash_intensity = 0.08 # 增加 - dhash_intensity = 0.08 # 增加 - region_flip_prob = 0.5 - num_ahash_blocks = random.randint(12, 25) - num_dhash_lines = random.randint(10, 18) + ahash_intensity = 0.40 # 极度增加 + phash_intensity = 0.25 # 极度增加 + dhash_intensity = 0.40 # 极度增加 + region_flip_prob = 0.90 # 很高概率翻转 + num_ahash_blocks = random.randint(40, 60) # 很多块 + num_dhash_lines = random.randint(30, 45) # 很多线 + ahash_delta_range = (-50, 50) # 更大亮度变化 + dhash_delta_range = 50 # 更大梯度变化 + region_max_factor = 12 # 区域更大 + gaussian_noise_sigma = 3.5 # 更强高斯噪声 + gaussian_noise_prob = 0.6 # 更高概率 + else: # medium (也适度增加) + ahash_intensity = 0.10 # 增加 + phash_intensity = 0.10 # 增加 + dhash_intensity = 0.10 # 增加 + region_flip_prob = 0.6 + num_ahash_blocks = random.randint(15, 30) + num_dhash_lines = random.randint(12, 20) + ahash_delta_range = (-40, 40) + dhash_delta_range = 40 + region_max_factor = 18 + gaussian_noise_sigma = 1.5 + gaussian_noise_prob = 0.5 - # 1. 针对aHash (平均哈希)的处理 - 强度已增加 - img_array = np.array(image, dtype=np.int16) + logger.debug(f"参数: aHash强度={ahash_intensity:.2f}, pHash强度={phash_intensity:.2f}, dHash强度={dhash_intensity:.2f}, 翻转概率={region_flip_prob:.2f}") + + # 1. 针对aHash ... + logger.debug(f"应用 aHash 对抗: {num_ahash_blocks} 个亮度块, 强度={ahash_intensity:.2f}, delta范围={ahash_delta_range}") + img_array = np.array(image, dtype=np.int16) h, w = img_array.shape[0], img_array.shape[1] - - # num_ahash_blocks = random.randint(10, 20) for _ in range(num_ahash_blocks): block_w = random.randint(w//20, w//10) block_h = random.randint(h//20, h//10) x = random.randint(0, w - block_w) y = random.randint(0, h - block_h) - - delta = int(random.uniform(-35, 35) * ahash_intensity) # 增加delta范围 - + delta = int(random.uniform(ahash_delta_range[0], ahash_delta_range[1]) * ahash_intensity) block = img_array[y:y+block_h, x:x+block_w] img_array[y:y+block_h, x:x+block_w] = np.clip(block + delta, 0, 255) - image = Image.fromarray(img_array.astype(np.uint8)) - - # 2. 调用强化的pHash对抗方法 - image = self.add_phash_noise(image, intensity=phash_intensity) - - # 3. 针对dHash (差值哈希)的处理 - 强度已增加 - img_array = np.array(image, dtype=np.int16) + logger.debug("aHash 对抗完成。") + + # 2. 调用强化的pHash对抗方法 (使用 scipy DCT) + logger.debug(f"应用 pHash 对抗 (DCT噪声), 强度={phash_intensity:.2f}") + image = self.add_phash_noise(image, intensity=phash_intensity) + # add_phash_noise 内部已有成功日志 + + # 3. 针对dHash ... + logger.debug(f"应用 dHash 对抗: {num_dhash_lines} 条梯度线, 强度={dhash_intensity:.2f}, delta范围=+/-({dhash_delta_range})") + img_array = np.array(image, dtype=np.int16) h, w = img_array.shape[0], img_array.shape[1] - mask = np.zeros_like(img_array, dtype=bool) - - # num_dhash_lines = random.randint(8, 12) for _ in range(num_dhash_lines): + line_width = random.randint(2, 5) # 增加线宽 if random.random() < 0.5: y = random.randint(0, h - 1) - line_width = random.randint(1, 4) # 增加线宽可能性 if len(mask.shape) == 3: mask[max(0, y-line_width//2):min(h, y+line_width//2+1), :, :] = True else: mask[max(0, y-line_width//2):min(h, y+line_width//2+1), :] = True else: x = random.randint(0, w - 1) - line_width = random.randint(1, 4) # 增加线宽可能性 if len(mask.shape) == 3: mask[:, max(0, x-line_width//2):min(w, x+line_width//2+1), :] = True else: mask[:, max(0, x-line_width//2):min(w, x+line_width//2+1)] = True - - delta = (np.random.random(img_array.shape) * 2 - 1) * dhash_intensity * 35 # 增加delta范围 + delta = (np.random.random(img_array.shape) * 2 - 1) * dhash_intensity * dhash_delta_range img_array[mask] += delta[mask].astype(np.int16) - img_array = np.clip(img_array, 0, 255) - - # 4. 颜色直方图扰动 (强度也略微增加) image = Image.fromarray(img_array.astype(np.uint8)) - color_hist_strength = dhash_intensity * 0.6 # 关联强度 + logger.debug("dHash 对抗完成。") + + # 4. 颜色直方图扰动 ... + color_hist_strength = dhash_intensity * 0.7 # 关联强度增加 + logger.debug(f"应用颜色直方图扰动, 强度={color_hist_strength:.3f}") image = self.perturb_color_histogram(image, strength=color_hist_strength) - - # 5. 区域翻转 - 强度已增加 + # perturb_color_histogram 内部已有成功日志 + + # 5. 区域翻转/旋转 ... if random.random() < region_flip_prob: + logger.debug(f"应用区域变换 (翻转/旋转), 概率触发成功.") img_array = np.array(image) h, w = img_array.shape[0], img_array.shape[1] + region_w = random.randint(w//(region_max_factor+5), w//region_max_factor) + region_h = random.randint(h//(region_max_factor+5), h//region_max_factor) + region_w = max(1, region_w) + region_h = max(1, region_h) + x = random.randint(0, max(0, w - region_w)) + y = random.randint(0, max(0, h - region_h)) - # 增加区域大小可能性 - max_region_factor = 15 if strength == 'high' else 20 - region_w = random.randint(w//(max_region_factor+5), w//max_region_factor) - region_h = random.randint(h//(max_region_factor+5), h//max_region_factor) - x = random.randint(0, w - region_w) - y = random.randint(0, h - region_h) - - # 加入90度旋转的可能性 action = random.choice(['flip_h', 'flip_v', 'rotate_90']) if strength != 'low' else random.choice(['flip_h', 'flip_v']) - region = img_array[y:y+region_h, x:x+region_w] - if action == 'flip_h': - img_array[y:y+region_h, x:x+region_w] = region[:, ::-1] - elif action == 'flip_v': - img_array[y:y+region_h, x:x+region_w] = region[::-1, :] - elif action == 'rotate_90' and len(img_array.shape) == 3: # 旋转只对原尺寸区域有效 - # 注意：旋转可能需要调整区域大小或填充，这里简化处理 - # 仅在区域接近正方形时效果较好 - if abs(region_w - region_h) < 5: - rotated_region = np.rot90(region) - # 需要确保旋转后尺寸匹配，如果尺寸变化则跳过或填充 - if rotated_region.shape[0] == region_h and rotated_region.shape[1] == region_w: - img_array[y:y+region_h, x:x+region_w] = rotated_region + action_applied = "skipped" + try: # 添加 try-except 捕获潜在错误 + if y+region_h <= h and x+region_w <= w: + region = img_array[y:y+region_h, x:x+region_w] + if region.size == 0: + action_applied = "empty_region_skipped" + elif action == 'flip_h': + img_array[y:y+region_h, x:x+region_w] = region[:, ::-1] + action_applied = action + elif action == 'flip_v': + img_array[y:y+region_h, x:x+region_w] = region[::-1, :] + action_applied = action + elif action == 'rotate_90' and len(img_array.shape) == 3: + if abs(region_w - region_h) < region_w * 0.3: + rotated_region = np.rot90(region) + if rotated_region.shape[0] == region_h and rotated_region.shape[1] == region_w: + img_array[y:y+region_h, x:x+region_w] = rotated_region + action_applied = action + else: + logger.debug(f" 区域旋转跳过: 尺寸不匹配 ({region.shape} -> {rotated_region.shape})") + action_applied = "rotate_skipped_size_mismatch" + else: + logger.debug(f" 区域旋转跳过: 非方形区域 ({region_w}x{region_h})") + action_applied = "rotate_skipped_not_square" + else: + action_applied = f"{action}_skipped_condition_not_met" + else: + action_applied = "region_bounds_error_skipped" + logger.warning(f"跳过区域变换，切片索引无效: y={y}, h={region_h}, x={x}, w={region_w}, img_shape={img_array.shape}") + + except Exception as e_region: + logger.warning(f"应用区域变换 {action} 时出错: {e_region}") + action_applied = f"error: {e_region}" - image = Image.fromarray(img_array) - - # 6. (新增可选) 轻微高斯噪声 - 对所有哈希都有轻微普适性干扰 - if strength != 'low' and random.random() < 0.4: + if action_applied not in ["skipped", "empty_region_skipped", "rotate_skipped_size_mismatch", "rotate_skipped_not_square", "region_bounds_error_skipped"] and not action_applied.startswith("error"): + image = Image.fromarray(img_array) + logger.debug(f" 执行了区域操作: {action_applied} 在 ({x},{y}) 大小 ({region_w}x{region_h})") + else: + logger.debug(f" 区域变换未执行或跳过: {action_applied}") + else: + logger.debug("跳过区域变换 (概率未触发).") + + # 6. 轻微高斯噪声 ... + apply_gaussian_noise = random.random() < gaussian_noise_prob + if gaussian_noise_sigma > 0 and apply_gaussian_noise: + logger.debug(f"应用高斯噪声, sigma={gaussian_noise_sigma:.1f}") img_array = np.array(image) - noise_sigma = 1.0 if strength == 'medium' else 2.0 # 噪声标准差 - noise = np.random.normal(0, noise_sigma, img_array.shape) + noise = np.random.normal(0, gaussian_noise_sigma, img_array.shape) img_array = np.clip(img_array + noise, 0, 255).astype(np.uint8) image = Image.fromarray(img_array) + elif gaussian_noise_sigma > 0: + logger.debug("跳过高斯噪声 (概率未触发).") + + # ... (对比日志不变) ... + logger.info(f"--- 完成优化抗哈希方法 (强度: {strength}) ---") return image def optimized_process_image( @@ -654,6 +706,7 @@ class PosterNotesCreator: # 如果不需要变化或是低强度且禁用额外效果 if not add_variation: + logger.info("add_variation=False，跳过所有变化和抗哈希处理。") # 重置随机种子 if seed is not None: random.seed() @@ -662,7 +715,7 @@ class PosterNotesCreator: # 清除元数据后返回 return self.strip_metadata(result) - # 高效应用基本变化 + logger.info(f"应用基础变化和抗哈希处理 (强度: {variation_strength}, 额外效果: {use_extra})") processed_image = result.convert('RGB') # 1. 亮度调整 @@ -686,14 +739,16 @@ class PosterNotesCreator: if abs(rotation_angle) > 0.1: # 只有当角度足够大时才旋转 processed_image = processed_image.rotate(rotation_angle, resample=Image.BICUBIC, expand=False) - # 5. 新增 - 应用反查重技术 - # 根据变化强度选择性应用 + # 5. 应用抗哈希技术 if use_extra: - # 使用综合优化的哈希对抗方法 + logger.debug("调用 optimize_anti_hash_methods...") processed_image = self.optimize_anti_hash_methods(processed_image, variation_strength) + else: + logger.info("use_extra=False，跳过 optimize_anti_hash_methods。") - # 应用额外效果 (只在需要时) + # 应用模糊/锐化/边框等额外效果 (如果 use_extra 为 True) if use_extra: + logger.debug("应用额外效果 (模糊/锐化/边框)...") # 根据强度决定是否应用特定效果 apply_sharpen = random.random() < 0.4 apply_blur = not apply_sharpen and random.random() < 0.3 @@ -719,21 +774,23 @@ class PosterNotesCreator: w, h = processed_image.size bordered = Image.new('RGB', (w + border_size*2, h + border_size*2), border_color) bordered.paste(processed_image, (border_size, border_size)) - - # 随机裁剪回原尺寸 - offset_x = random.randint(0, border_size*2) - offset_y = random.randint(0, border_size*2) - processed_image = bordered.crop((offset_x, offset_y, offset_x + w, offset_y + h)) + + logger.debug("额外效果应用完成。") + else: + logger.info("use_extra=False，跳过额外效果。") - # 6. 始终清除元数据 - 最后一步 - processed_image = self.strip_metadata(processed_image) + # **关键：确保在所有修改之后调用修复后的 strip_metadata** + logger.debug("最后调用 strip_metadata 清除元数据。") + final_image = self.strip_metadata(processed_image) # 重置随机种子 if seed is not None: random.seed() np.random.seed() + logger.debug("随机种子已重置。") - return processed_image + logger.info(f"图像处理完成 (强度: {variation_strength})") + return final_image def perturb_color_histogram(self, image: Image.Image, strength: float = 0.03) -> Image.Image: """ @@ -746,6 +803,7 @@ class PosterNotesCreator: Returns: 处理后的图像 """ + logger.debug(f"扰动颜色直方图，强度: {strength:.3f}") # 确保为RGB模式 if image.mode != 'RGB': image = image.convert('RGB') @@ -782,11 +840,12 @@ class PosterNotesCreator: img_array[:,:,channel][mask] + offset, 0, 255).astype(np.uint8) # 转回PIL图像 + logger.debug("颜色直方图扰动成功。") return Image.fromarray(img_array) def strip_metadata(self, image: Image.Image) -> Image.Image: """ - 移除图像中的所有元数据 + 移除图像中的所有元数据 (修复版) Args: image: 输入图像 @@ -794,10 +853,43 @@ class PosterNotesCreator: Returns: 无元数据的图像 """ - # 创建无元数据的副本 - data = io.BytesIO() - image.save(data, format=image.format if image.format else 'PNG') - return Image.open(data) + logger.debug("移除图像元数据...") + try: + # 从当前图像对象的像素数据创建一个新的Image对象 + # 这确保我们使用的是内存中修改后的数据 + # 保留原始格式信息，如果可用 + img_format = image.format if hasattr(image, 'format') else 'PNG' + + # 如果图像有alpha通道，需要正确处理 + if image.mode == 'RGBA': + # 创建一个白色背景，然后粘贴带有alpha的图像 + background = Image.new("RGB", image.size, (255, 255, 255)) + background.paste(image, mask=image.split()[3]) # 3 is the alpha channel + image_to_save = background + img_format = 'JPEG' # 通常去除alpha后存为JPEG + elif image.mode == 'P': + # 带调色板的图像转换为RGB + image_to_save = image.convert('RGB') + img_format = 'JPEG' + else: + image_to_save = image + + # 保存到内存缓冲区 + data = io.BytesIO() + # 确保保存时指定质量参数，避免默认压缩导致意外变化 + if img_format == 'JPEG': + image_to_save.save(data, format='JPEG', quality=95) # 使用高质量JPEG + else: + # 对于PNG等无损格式，不需要质量参数 + image_to_save.save(data, format=img_format) + + data.seek(0) # 重置缓冲区指针 + reloaded_image = Image.open(data) + logger.debug("元数据移除成功。") + return reloaded_image + except Exception as e: + logger.error(f"移除元数据时出错: {e}") + return image # 出错时返回原图 def process_poster_for_notes( run_id: str,