Learning Markov Clustering Networks for Scene Text Detection
This addresses the problem of fast and robust detection of multioriented text in images for computer vision applications, offering a novel method with significant speed and accuracy improvements.
The paper tackles scene text detection by proposing the Markov Clustering Network (MCN), which converts images into Stochastic Flow Graphs and uses Markov clustering to predict bounding boxes without Non-Maximum Suppression, achieving state-of-the-art performance on MSRA-TD500 with an F-score of 0.83 and real-time inference at 34 FPS.
A novel framework named Markov Clustering Network (MCN) is proposed for fast and robust scene text detection. MCN predicts instance-level bounding boxes by firstly converting an image into a Stochastic Flow Graph (SFG) and then performing Markov Clustering on this graph. Our method can detect text objects with arbitrary size and orientation without prior knowledge of object size. The stochastic flow graph encode objects' local correlation and semantic information. An object is modeled as strongly connected nodes, which allows flexible bottom-up detection for scale-varying and rotated objects. MCN generates bounding boxes without using Non-Maximum Suppression, and it can be fully parallelized on GPUs. The evaluation on public benchmarks shows that our method outperforms the existing methods by a large margin in detecting multioriented text objects. MCN achieves new state-of-art performance on challenging MSRA-TD500 dataset with precision of 0.88, recall of 0.79 and F-score of 0.83. Also, MCN achieves realtime inference with frame rate of 34 FPS, which is $1.5\times$ speedup when compared with the fastest scene text detection algorithm.