[Cherry-Pick]bugfix: unexpected change of the constant IMAGE_LABELS (#…

…4961)

* bugfix: unexpected change of the constant IMAGE_LABELS

* update doc

docs/pipeline_usage/tutorials/ocr_pipelines/PaddleOCR-VL.en.md

@@ -6,7 +6,7 @@ comments: true
 
 PaddleOCR-VL is a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. This innovative model efficiently supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption. Through comprehensive evaluations on widely used public benchmarks and in-house benchmarks, PaddleOCR-VL achieves SOTA performance in both page-level document parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference speeds. These strengths make it highly suitable for practical deployment in real-world scenarios.
 
-On January 29, 2026, we released PaddleOCR-VL-1.5. PaddleOCR-VL-1.5 not only significantly improved the accuracy on the OmniDocBench v1.5 evaluation set to 94.5%, but also innovatively supports irregular-shaped bounding box localization. As a result, PaddleOCR-VL-1.5 demonstrates outstanding performance in real-world scenarios such as Skew, Warping, Screen Photography, Illumination, and Scanning. In addition, the model has added new capabilities for seal (stamp) recognition and text detection and recognition, with key metrics continuing to lead the industry.
+**On January 29, 2026, we released PaddleOCR-VL-1.5. PaddleOCR-VL-1.5 not only significantly improved the accuracy on the OmniDocBench v1.5 evaluation set to 94.5%, but also innovatively supports irregular-shaped bounding box localization. As a result, PaddleOCR-VL-1.5 demonstrates outstanding performance in real-world scenarios such as Skew, Warping, Screen Photography, Illumination, and Scanning. In addition, the model has added new capabilities for seal (stamp) recognition and text detection and recognition, with key metrics continuing to lead the industry.**
 
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/paddleocr-vl-1.5_metrics.png"/>
 

docs/pipeline_usage/tutorials/ocr_pipelines/PaddleOCR-VL.md

@@ -6,7 +6,7 @@ comments: true
 
 PaddleOCR-VL 是一款先进、高效的文档解析模型，专为文档中的元素识别设计。其核心组件为 PaddleOCR-VL-0.9B，这是一种紧凑而强大的视觉语言模型（VLM），它由 NaViT 风格的动态分辨率视觉编码器与 ERNIE-4.5-0.3B 语言模型组成，能够实现精准的元素识别。该模型支持 109 种语言，并在识别复杂元素（如文本、表格、公式和图表）方面表现出色，同时保持极低的资源消耗。通过在广泛使用的公开基准与内部基准上的全面评测，PaddleOCR-VL 在页级级文档解析与元素级识别均达到 SOTA 表现。它显著优于现有的基于Pipeline方案和文档解析多模态方案以及先进的通用多模态大模型，并具备更快的推理速度。这些优势使其非常适合在真实场景中落地部署。
 
-2026年1月29日，我们发布了PaddleOCR-VL-1.5。PaddleOCR-VL-1.5不仅以94.5%精度大幅刷新了评测集OmniDocBench v1.5，更创新性地支持了异形框定位，使得PaddleOCR-VL-1.5 在扫描、倾斜、弯折、屏幕拍摄及复杂光照等真实场景中均表现优异。此外，模型还新增了印章识别与文本检测识别能力，关键指标持续领跑。
+**2026年1月29日，我们发布了PaddleOCR-VL-1.5。PaddleOCR-VL-1.5不仅以94.5%精度大幅刷新了评测集OmniDocBench v1.5，更创新性地支持了异形框定位，使得PaddleOCR-VL-1.5 在扫描、倾斜、弯折、屏幕拍摄及复杂光照等真实场景中均表现优异。此外，模型还新增了印章识别与文本检测识别能力，关键指标持续领跑。**
 
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/paddleocr_vl_1_5/paddleocr-vl-1.5_metrics.png"/>
 

paddlex/inference/pipelines/paddleocr_vl/pipeline.py

@@ -272,7 +272,7 @@ def get_layout_parsing_results(
         id2pixel_key_map = {}
         image_path_to_obj_map = {}
         vis_image_labels = IMAGE_LABELS + ["seal"]
-        image_labels = [] if use_ocr_for_image_block else IMAGE_LABELS
+        image_labels = [] if use_ocr_for_image_block else IMAGE_LABELS.copy()
         if not use_chart_recognition:
             image_labels += ["chart"]
             vis_image_labels += ["chart"]

paddlex/inference/pipelines/paddleocr_vl/result.py

@@ -268,7 +268,7 @@ def __init__(self, data) -> None:
             "markdown_ignore_labels", []
         )
         self.skip_order_labels = [
-            label for label in SKIP_ORDER_LABELS + markdown_ignore_labels
+            label for label in SKIP_ORDER_LABELS.copy() + markdown_ignore_labels
         ]
 
     def _to_img(self) -> dict[str, np.ndarray]: