five

Human and Mouse Eyes for Pupil Semantic Segmentation

收藏
Zenodo2021-02-01 更新2026-05-25 收录
下载链接:
https://zenodo.org/record/4488164
下载链接
链接失效反馈
官方服务:
资源简介:
A dataset composed of 11897 grayscale images of humans (4285) and mouse (7612) eyes. In different experimental conditions: head-fixation sessions (HF: 5061), 2-photon Ca2+ imaging ( 2P: 2551), and human eyes (H: 4285). The dataset contains 1596 eye blinks, 841 images in the mouse, and 755 photos in the human datasets. Five human raters segmented the pupil in all pictures (one per image) by manual placement of an ellipse or polygon over the pupil area. Raters flagged blinks using the same code. All the photos are illuminated using infrared (IR, 850 nm) light sources. The dataset contains 2 folders: 'fullFrames': contains all the grayscale images in png format. 'annotation': contains a folder called 'png' with pupil mask in the red channel. There is also a file called 'annotations.csv' containing a list with a description of each file in the dataset in this folder. Description of the fields in annotations.csv: filename: [string] with the file name eye: [0,1] if true an eye is present in the picture blink: [0,1] if true the subject is blinking exp: [string] what kind of experiments w: [int] resolution width h: [int] resolution height roi_x: [int] roi x coordinate roi_y: [int] roi y coordinate roi_w: [int] roi width-height (128x128) sub: [int] subject's label

本数据集共包含11897张灰度眼部图像,其中人类眼部图像4285张、小鼠眼部图像7612张。 实验涵盖三类范式:头部固定实验范式(head-fixation sessions,HF:5061张图像)、双光子钙成像(2-photon Ca²+ imaging,2P:2551张图像)以及人类眼部实验(H:4285张图像)。 本数据集共包含1596个眼部眨眼事件,其中小鼠眼部图像集中有841张含眨眼的图像,人类眼部图像集中有755张含眨眼的图像。 5名人类标注员对所有图像的瞳孔区域进行手动标注:通过在瞳孔区域手动绘制椭圆或多边形的方式,为每张图像标注对应的瞳孔区域。标注员采用统一的编码规则标记眨眼事件。 所有图像均采用红外(infrared,IR,850 nm)光源进行照明。 本数据集包含两个文件夹: - "fullFrames":存储所有PNG格式的灰度图像; - "annotation":内含一个名为"png"的子文件夹,其中存储的瞳孔掩码图像的红色通道即为瞳孔区域掩码。 该文件夹中还包含一个"annotations.csv"文件,其中列出了本数据集内所有文件的相关描述信息。 以下为"annotations.csv"各字段的详细说明: - filename:[字符串类型] 对应图像文件的文件名; - eye:[0或1] 若取值为1,则图像中存在眼部区域; - blink:[0或1] 若取值为1,则对应受试者处于眨眼状态; - exp:[字符串类型] 对应实验的类型; - w:[整数类型] 图像分辨率的宽度值; - h:[整数类型] 图像分辨率的高度值; - roi_x:[整数类型] 感兴趣区域(region of interest,ROI)的X轴坐标; - roi_y:[整数类型] 感兴趣区域的Y轴坐标; - roi_w:[整数类型] 感兴趣区域的宽高(固定为128×128像素); - sub:[整数类型] 受试者的唯一标识标签。
提供机构:
Zenodo
创建时间:
2021-02-01
二维码
社区交流群
二维码
科研交流群
商业服务