Pelee-Text: A Tiny Convolutional Neural Network for Multi-oriented Scene Text Detection

Pelee-Text++: A Tiny Neural Network for Scene Text Detection

“…The proposed approaches have used different techniques for dealing with scene text detection, most of them are focused on regression [6,28,31,51,57], segmentation [4,8,56,56], or the combination of both techniques [35,38,39,52,63]. Additionally, some proposals have merged the detection and recognition tasks as a jointed pipeline for improving their results [34,38], or had even used knowledge distillation [68].…”

“…In the vein of regression methods, generally, this type of approaches generate two points (x min , y min , x max , y max ) [28], four points ( [6,18,29,63], or adaptive number of points [51] as a bounding box prediction. Furthermore, they predict offsets from predefined anchorboxes [6,28,29], direct regression for predicting offsets from a single point [18], or even shape regression [57].…”

“…Related to text detection, there exist few works using lightweight mobile-oriented neural networks [6,7,9]. Some of the approaches based on tiny neural network models [7,9] are limited to the detection of horizontal text.…”

“…Some of the approaches based on tiny neural network models [7,9] are limited to the detection of horizontal text. In this vein, our previous work, Pelee-Text [6], introduced a light architecture for multi-oriented scene text detection, reaching competitive results in several datasets with a model size of 40 Megabytes.…”

“…Pelee-Text [6] and Pelee-Text++ are compact neural networks for text detection that have reached a good trade-off between efficiency and effectiveness, becoming promising approaches to mobile applications. Both use the same kind of convolutional blocks: (i) stem block, (ii) transitional blocks, and (iii) dense blocks.…”