BCCD Dataset
BCCD Dataset is a small-scale dataset for blood cells detection.
Thanks the original data and annotations from cosmicad and akshaylamba. The original dataset is re-organized into VOC format. BCCD Dataset is under MIT licence.
You can download the .rec
format for mxnet directly. The .rec
file can be load by mxnet.image.ImageDetIter.
Data preparation
Data preparation is important to use machine learning. In this project, the Faster R-CNN algorithm from keras-frcnn for Object Detection is used. From this dataset, nicolaschen1 developed two Python scripts to make preparation data (CSV file and images) for recognition of abnormalities in blood cells on medical images.
- export.py: it creates the file "test.csv" with all data needed: filename, class_name, x1,y1,x2,y2.
- plot.py: it plots the boxes for each image and save it in a new directory.
Overview of dataset
-
You can see a example of the labeled cell image.
We have three kind of labels :
- RBC (Red Blood Cell)
- WBC (White Blood Cell)
- Platelets (θ‘ε°ζΏ)
-
The structure of the
BCCD_dataset
βββ BCCD β βββ Annotations β β βββ BloodImage_00XYZ.xml (364 items) β βββ ImageSets # Contain four Main/*.txt which split the dataset β βββ JPEGImages β βββ BloodImage_00XYZ.jpg (364 items) βββ dataset β βββ mxnet # Some preprocess scripts for mxnet βββ scripts β βββ split.py # A script to generate four .txt in ImageSets β βββ visualize.py # A script to generate labeled img like example.jpg βββ example.jpg # A example labeled img generated by visualize.py βββ LICENSE βββ README.md
-
The
JPEGImages
:- Image Type : jpeg(JPEG)
- Width x Height : 640 x 480
-
The
Annotations
: The VOC format.xml
for Object Detection, automatically generate by the label tools. Below is an example of.xml
file.<annotation> <folder>JPEGImages</folder> <filename>BloodImage_00000.jpg</filename> <path>/home/pi/detection_dataset/JPEGImages/BloodImage_00000.jpg</path> <source> <database>Unknown</database> </source> <size> <width>640</width> <height>480</height> <depth>3</depth> </size> <segmented>0</segmented> <object> <name>WBC</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>260</xmin> <ymin>177</ymin> <xmax>491</xmax> <ymax>376</ymax> </bndbox> </object> ... <object> ... </object> </annotation>