This is a text spotting model that simultaneously detects and recognizes text. The model detects symbol sequences separated by space and performs recognition without a dictionary. The model is built on top of the Mask-RCNN framework with additional attention-based text recognition head.
Symbols set is alphanumeric:
This model is a Mask-RCNN-based text detector with ResNet50 backbone and additional text features output.
|Word spotting hmean ICDAR2015, without a dictionary||61.01%|
Hmean Word spotting is defined and measured according to the Incidental Scene Text (ICDAR2015) challenge.
im_data, shape: [1x3x768x1280]. An input image in the [1xCxHxW] format. The expected channel order is BGR.
im_info, shape: [1x3]. Image information: processed image height, processed image width, and processed image scale with respect to the original image resolution.
classes, shape: . Contiguous integer class ID for every detected object,
0for background (no object detected).
scores, shape: . Detection confidence scores in the [0, 1] range for every object.
boxes, shape: [100x4]. Bounding boxes around every detected object in the (top_left_x, top_left_y, bottom_right_x, bottom_right_y) format.
raw_masks, shape: [100x2x28x28]. Segmentation heatmaps for all classes for every output bounding box.
text_features, shape [100x64x28x28]. Text features that are fed to a text recognition head.
[*] Other names and brands may be claimed as the property of others.