scampion/OHSDA
收藏资源简介：
--- license: cc-by-4.0 --- extract from https://data.mendeley.com/datasets/c5mfhr2xcz/1 # Offline Handwritten Signature Database based on Age Annotation (OHSDA) Published: 27 February 2023 Version 1 DOI: 10.17632/c5mfhr2xcz.1 Contributors: Sathish Kumar , Dr Shivanand Gornale ## Description Handwritten signature analysis is the endeavoring research in many verification and recognition system problem. As per our best of knowledge there is less number of publicly available datasets which have age class annotation for signature. With this motivation, own dataset is created. The nature of this own offline handwritten signature database is described below. • In-house total of 6010 signatures were collected randomly in 601 healthy volunteers (330 males; 271 females; Age range 18-50 years) • From each individual 10 signatures acquired on a white A4 paper sheet using blue or black colored ball pen. • To avoid geometrical variations, the papers with sample signatures have been scanned using the EPSON DS 1630 color scanner with a resolution of 300 DPI. • The signature samples consist of multilingual scripts of Kannada, Hindi, Marathi, and English. • The participants who had knowledge of English and other regional languages, have been educated about the purpose of collection of signature samples. Male signatures age range will start from ‘male signatures 18-50 years’ and female signature will starts from ‘female signatures 18-50 years’. All Scanned Offline Signature samples are in .jpg format, the male signatures start with 'm' and female signatures start with 'f'. Download All 109 MB Files Female Signatures 18-50 years Male Signatures 18-50 years Steps to reproduce Handwritten signatures are socially and legally accepted behavioral biometric data for authenticating the documents like letters, contracts, wills, MOU’s, etc. for validation in day to day life. However, it is observed that very less effort is done on age identification based on offline handwritten signatures. These signatures contain multilingual texts. Therefore, to bridge this research gap, the proposed database is used to identify writer’s age group from handwritten signatures of individuals. The signature samples were collected from various educational institutions and some village are for diversity purpose. • In-house total of 6010 signatures were collected randomly in 601 healthy volunteers (330 males; 271 females; Age range 18-50 years) • From each individual 10 signatures acquired on a white A4 paper sheet using blue or black colored ball pen. • To avoid geometrical variations, the papers with sample signatures have been scanned using the EPSON DS 1630 color scanner with a resolution of 300 DPI. • The signature samples consist of multilingual scripts of Kannada, Hindi, Marathi, and English. • The participants who had knowledge of English and other regional languages, have been educated about the purpose of collection of signature samples. All participants gave written informed consent, and the study was approved by the institutional ethics committee. Institutions Rani Channamma University Categories Biometrics, Age Diversity
许可证：CC BY 4.0 数据来源：https://data.mendeley.com/datasets/c5mfhr2xcz/1 # 基于年龄标注的离线手写签名数据集（OHSDA） 发布时间：2023年2月27日 版本：1 DOI：10.17632/c5mfhr2xcz.1 贡献者： 萨蒂什·库马尔（Sathish Kumar）、希瓦南德·戈纳尔博士（Dr Shivanand Gornale） ## 数据集说明 手写签名分析是诸多验证与识别系统研究中的热点方向。据我们所知，目前公开可用的、带有签名年龄类别标注的数据集数量极少。基于此研究动机，我们构建了本数据集。本离线手写签名数据集的具体情况说明如下： • 本机构从601名健康志愿者中随机采集了共计6010份手写签名样本，其中男性330名，女性271名，年龄跨度为18至50岁。 • 每位志愿者提供10份手写签名，均使用蓝色或黑色圆珠笔在白色A4纸上书写完成。 • 为避免几何形变，所有携带签名样本的纸张均使用爱普生（EPSON）DS 1630彩色扫描仪以300 DPI的分辨率进行扫描。 • 签名样本包含卡纳达语、印地语、马拉地语以及英语四种语言的手写字体。 • 所有知晓英语及其他地方语言的志愿者，均已被告知本签名样本采集的目的。 男性签名样本的命名前缀为"male signatures 18-50 years"，女性签名样本的命名前缀为"female signatures 18-50 years"。 所有扫描得到的离线签名样本均为.jpg格式，男性签名样本文件名以'm'开头，女性签名样本文件名以'f'开头。 下载全部（109 MB）文件 18-50岁女性签名样本 18-50岁男性签名样本 ## 数据集复现说明 手写签名作为一种被社会与法律广泛认可的行为生物特征数据，可用于日常文书（如信件、合同、遗嘱、谅解备忘录（MOU）等）的身份验证。然而，目前基于离线手写签名进行年龄识别的相关研究极少。此类签名包含多语言文本，为填补这一研究空白，本数据集可用于基于个体手写签名识别其年龄组别。 本数据集的签名样本采集自多所教育机构及部分乡村，以保证样本的多样性。 • 本机构从601名健康志愿者中随机采集了共计6010份手写签名样本，其中男性330名，女性271名，年龄跨度为18至50岁。 • 每位志愿者提供10份手写签名，均使用蓝色或黑色圆珠笔在白色A4纸上书写完成。 • 为避免几何形变，所有携带签名样本的纸张均使用爱普生（EPSON）DS 1630彩色扫描仪以300 DPI的分辨率进行扫描。 • 签名样本包含卡纳达语、印地语、马拉地语以及英语四种语言的手写字体。 • 所有知晓英语及其他地方语言的志愿者，均已被告知本签名样本采集的目的。 所有参与者均签署了书面知情同意书，本研究已通过机构伦理委员会审查批准。 ## 所属机构 拉妮·查纳玛大学（Rani Channamma University） ## 分类 生物特征识别、年龄多样性
Offline Handwritten Signature Database based on Age Annotation (OHSDA)
基本信息
- 发布日期：2023年2月27日
- 版本：1
- DOI：10.17632/c5mfhr2xcz.1
- 贡献者：Sathish Kumar, Dr Shivanand Gornale
- 许可证：CC-BY-4.0
数据集描述
- 样本数量：共6010个签名样本，来自601名健康志愿者（330名男性，271名女性），年龄范围18-50岁。
- 采集方式：每位志愿者提供10个签名，使用蓝色或黑色圆珠笔在白色A4纸上书写。
- 扫描设备：使用EPSON DS 1630彩色扫描仪，分辨率为300 DPI。
- 语言多样性：签名样本包含多种语言，包括Kannada, Hindi, Marathi, 和 English。
- 文件格式：所有扫描的签名样本为.jpg格式，男性签名文件名以m开头，女性签名文件名以f开头。
数据集用途
- 研究目的：用于识别个人年龄组，填补基于离线手写签名的年龄识别研究空白。
- 收集地点：样本从多个教育机构和村庄收集，以确保多样性。
伦理与合规性
- 参与者知情同意：所有参与者均提供书面知情同意。
- 伦理批准：研究已获得机构伦理委员会的批准。
