基于图像的面部瘢痕伤残等级评估方法及相关设备
By using image processing technology and pre-trained models to assess the disability level of facial scars, the problem of complex and error-prone manual measurements is solved, and automated and accurate assessment is achieved.
CN116778282BActive Publication Date: 2026-07-17PING AN TECH (SHENZHEN) CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- PING AN TECH (SHENZHEN) CO LTD
- Filing Date
- 2023-06-20
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies for assessing facial scar disability levels suffer from problems such as complex manual measurements and large errors, leading to inaccurate assessments.
Method used
By acquiring target images, performing region division and segmentation, using a pre-trained target segmentation model to segment faces and reference objects, combining region division results and masks to create a portrait of facial scar disability indicators, and finally evaluating the level based on the single-indicator portrait results.
Benefits of technology
It enables automated and accurate assessment of facial scar disability levels, improving assessment efficiency and accuracy, and solving the error problem caused by manual measurement.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116778282B_ABST
Abstract
本申请涉及医疗健康技术领域，揭示了一种基于图像的面部瘢痕伤残等级评估方法及相关设备，其中方法包括：获取目标图像，其中，所述目标图像中包含目标对象的人脸对应的图像区域和目标参照物对应的图像区域，两个所述图像区域不重叠；对所述目标图像进行区域划分，得到区域划分结果；将所述目标图像输入预训练的目标分割模型分别进行人脸和所述目标参照物的分割，得到人脸掩膜和参照物掩膜；根据所述区域划分结果、所述人脸掩膜和所述参照物掩膜进行每个面部瘢痕伤残指标的画像，得到单指标画像结果；根据各个所述单指标画像结果进行面部瘢痕伤残等级的评估，得到所述目标对象对应的面部瘢痕伤残等级评估结果。从而实现了面部瘢痕伤残等级的准确评估。
Need to check novelty before this filing date? Find Prior Art