Text detector based on FCOS architecture with MobileNetV2-like as a backbone for indoor/outdoor scenes with more or less horizontal text.
The key benefit of this model compared to the base model is its smaller size and faster performance.
Metric | Value |
---|---|
F-measure (harmonic mean of precision and recall on ICDAR2013) | 88.45% |
GFlops | 7.78 |
MParams | 2.26 |
Source framework | PyTorch* |
Name: input
, shape: [1x3x704x704] - An input image in the format [1xCxHxW], where:
Expected color order - BGR.
boxes
is a blob with shape: [N, 5], where N is the number of detected bounding boxes. For each detection, the description has the format: [x_min
, y_min
, x_max
, y_max
, conf
], where:x_min
, y_min
) - coordinates of the top left bounding box cornerx_max
, y_max
) - coordinates of the bottom right bounding box corner.conf
- confidence for the predicted classlabels
is a blob with shape: [N], where N is the number of detected bounding boxes. In case of text detection, it is equal to 0
for each detected box.[*] Other names and brands may be claimed as the property of others.