Facial Expression Dataset (Sri Lankan)

The Facial Expression Dataset (Sri Lankan) is a culturally specific dataset created to enhance the accuracy of emotion recognition models in Sri Lankan contexts. Existing datasets, often based on foreign samples, fail to account for cultural differences in facial expressions, affecting model performance. This dataset bridges that gap, using high-quality data sourced from over 100 video clips of professional Sri Lankan actors to ensure expressive and clear facial imagery.The dataset captures actors’ emotions in frames where they face the camera directly, with backgrounds removed to focus on facial features. Images are labeled and organized in folders by emotion, following the FER2013 dataset structure. This makes it ideal for fine-tuning models using transfer learning, especially for applications in mental health and emotion-based AI systems.By utilizing culturally relevant data, this dataset improves emotion recognition accuracy for Sri Lankan users, helping researchers and developers build more effective and context-aware models.斯里兰卡人脸表情数据集（Sri Lankan Facial Expression Dataset）是一款文化特异性数据集，旨在提升情绪识别模型在斯里兰卡本土语境下的识别精度。现有数据集多基于海外样本构建，未充分考量人脸表情的文化差异，进而影响模型实际应用性能。本数据集填补了这一研究空白，其高质量数据源自100余段专业斯里兰卡演员的视频片段，可确保采集到生动清晰的面部表情图像。数据集采集演员正对镜头时的情绪表达帧，并移除背景以突出面部特征；所有图像均已完成标注，且参照FER2013数据集的组织架构，按情绪类别进行文件夹分组。该设计使得本数据集非常适合基于迁移学习的模型微调，尤其适用于心理健康领域及基于情绪的AI系统相关应用。通过采用贴合本土文化的训练数据，本数据集可提升斯里兰卡用户群体的情绪识别精度，助力研究人员与开发者构建更高效、更具场景适配性的情绪识别模型。

搜集汇总

背景与挑战

背景概述

Facial Expression Dataset (Sri Lankan) 是一个针对斯里兰卡文化背景的面部表情数据集，包含931张高质量图像，覆盖愤怒、恐惧、快乐、中立和悲伤五种情感，旨在解决现有数据集因文化差异导致的情感识别模型性能不足问题。该数据集基于100多个专业演员的视频片段构建，已分割为训练集和验证集，并遵循FER2013结构，便于用于迁移学习和情感识别AI系统的开发。