一种保守的OCR启用工作流，用于南非包装食品的R214钠筛查
A Conservative OCR-Enabled Workflow for R214 Sodium Screening of South African Packaged Foods
浏览论文内容
中文总结 AI 辅助
本研究提出一种保守的基于图像的工作流，结合OCR和视觉语言模型，对南非包装食品进行R214钠筛查，能识别明确案例并将不确定案例归入审查，避免强制决策。
中文摘要 AI 辅助
使用食品包装图像监测钠和盐含量是否符合南非R214钠限值，在筛查决策需要产品身份、营养事实面板证据、报告基础和类别特定阈值时具有挑战性。本研究提出了一种保守的基于图像的工作流，该工作流结合了区域检测、光学字符识别（OCR）、产品身份和钠证据提取、R214类别分配、确定性阈值比较以及独立的视觉语言模型比较。评估使用了来自真实世界南非食品包装数据集的442种包装食品产品和3929张完整包装图像。YOLO26s小型检测器生成了4195个区域裁剪，严格的后期处理为每个产品生成一行钠证据。集成工作流产生了290个超出R214范围、139个审查、7个通过筛查和6个未通过筛查的结果。独立的Qwen2.5-VL 7B视觉语言模型工作流产生了387个超出R214范围、31个审查、20个通过筛查和4个未通过筛查的结果。两种工作流在442种产品中的415种（93.9%）上精确匹配了R214类别分配，在442种产品中的416种（94.1%）上匹配了分配类别是否在R214范围内。最终筛查结果的一致性为442种产品中的307种，即69.5%。对60种产品的手动验证显示，严格结果一致性低于监管状态一致性，而所有手动信息不足案例都被两种自动化工作流排除在通过筛查和未通过筛查之外。研究结果表明，保守的基于图像的筛查可以组织包装证据、识别明确案例，并将不确定案例分配给审查而非强制做出通过或未通过筛查的决定。
英文摘要
Using food package images to monitor sodium and salt content against South Africa's R214 sodium limits is challenging when screening decisions require product identity, nutrition facts panel evidence, reporting basis, and category-specific thresholds. This study presents a conservative image-based workflow that combines region detection, optical character recognition (OCR), product identity and sodium evidence extraction, R214 category assignment, deterministic threshold comparison, and independent vision language model comparison. The evaluation used 442 packaged food products and 3 929 full package images from a real-world South African food packaging dataset. A YOLO26s small detector generated 4 195 region crops, and strict post-processing produced one sodium evidence row per product. The integrated workflow produced 290 OUTSIDE R214 SCOPE, 139 REVIEW, seven SCREEN-PASS, and six SCREEN-FAIL outcomes. The independent Qwen2.5-VL 7B vision language model workflow produced 387 OUTSIDE R214 SCOPE, 31 REVIEW, twenty SCREEN-PASS, and four SCREEN-FAIL outcomes. The workflows agreed on exact R214 category assignment for 415 of 442 products (93.9%) and on whether the assigned category was within R214 scope for 416 of 442 products (94.1%). Final screening outcome agreement was 307 out of 442 products, or 69.5%. Manual verification on 60 products showed lower strict outcome agreement than regulated status agreement, while all manual INSUFFICIENT DATA cases were kept out of SCREEN-PASS and SCREEN-FAIL by both automated workflows. The findings show that conservative image-based screening can organise package evidence, identify clear cases, and assign uncertain cases to REVIEW rather than forcing SCREEN-PASS or SCREEN-FAIL decisions.
发表机构
- University of the Western Cape（西开普大学）
机构由 AI 辅助整理，请以论文原文为准。
