SEMPANet: A Modified Path Aggregation Network with Squeeze-Excitation for Scene Text Detection

Recently, various object detection frameworks have been applied to text detection tasks and have achieved good performance in the final detection. With the further expansion of text detection application scenarios, the research value of text detection topics has gradually increased. Text detection in natural scenes is more challenging for horizontal text based on a quadrilateral detection box and for curved text of any shape. Most networks have a good effect on the balancing of target samples in text detection, but it is challenging to deal with small targets and solve extremely unbalanced data. We continued to use PSENet to deal with such problems in this work. On the other hand, we studied the problem that most of the existing scene text detection methods use ResNet and FPN as the backbone of feature extraction, and improved the ResNet and FPN network parts of PSENet to make it more conducive to the combination of feature extraction in the early stage. A SEMPANet framework without an anchor and in one stage is proposed to implement a lightweight model, which is embodied in the training time of about 24 h. Finally, we selected the two most representative datasets for oriented text and curved text to conduct experiments. On ICDAR2015, the improved network’s latest results further verify its effectiveness; it reached 1.01% in F-measure compared with PSENet-1s. On CTW1500, the improved network performed better than the original network on average.

A Straightforward and Efficient Instance-Aware Curved Text Detector

A challenging aspect of scene text detection is to handle curved texts. In order to avoid the tedious manual annotations for training curve text detector, and to overcome the limitation of regression-based text detectors to irregular text, we introduce straightforward and efficient instance-aware curved scene text detector, namely, look more than twice (LOMT), which makes the regression-based text detection results gradually change from loosely bounded box to compact polygon. LOMT mainly composes of curve text shape approximation module and component merging network. The shape approximation module uses a particle swarm optimization-based text shape approximation method (called PSO-TSA) to fine-tune the quadrilateral text detection results to fit the curved text. The component merging network merges incomplete text sub-parts of text instances into more complete polygon through instance awareness, called ICMN. Experiments on five text datasets demonstrate that our method not only achieves excellent performance but also has relatively high speed. Ablation experiments show that PSO-TSA can solve the text’s shape optimization problem efficiently, and ICMN has a satisfactory merger effect.

Texts as Lines: Text Detection with Weak Supervision

Scene text detection methods based on deep learning have recently shown remarkable improvement. Most text detection methods train deep convolutional neural networks with full masks requiring pixel accuracy for good quality training. Normally, a skilled engineer needs to drag tens of points to create a full mask for the curved text. Therefore, data labelling based on full masks is time consuming and laborious, particularly for curved texts. To reduce the labelling cost, a weakly supervised method is first proposed in this paper. Unlike the other detectors (e.g., PSENet or TextSnake) that use full masks, our method only needs coarse masks for training. More specifically, the coarse mask for one text instance is a line across the text region in our method. Compared with full mask labelling, data labelling using the proposed method could save labelling time while losing much annotation information. In this context, a network pretrained on synthetic data with full masks is used to enhance the coarse masks in a real image. Finally, the enhanced masks are fed back to train our network. Analysis of experiments performed using the model shows that the performance of our method is close to that of the fully supervised methods on ICDAR2015, CTW1500, Total-Text, and MSRA-TD5000.

Multi Orientation Text Detection in Natural Imagery

Constant advancement and growth in digital technology is swiftly changing the scenario of text detection from hard copy images to natural images. An in-depth study of the previous research work reveals that though a lot of research work has been done on text detection and recognition in natural scene images, but most of the researchers have concluded their survey either on a horizontal or near to horizontal texts. Their survey somewhat speaks about multi-orientation text detection, but the curved text detection in natural images escaped their attention. It has necessitated exploration on the vital aspect of text detection field where detailed study of horizontal, near to horizontal, multi-orientation, and curved text finds a place in a single cover. To achieve this goal, the present study will focus on fundamental understanding, existing challenges, and the proven algorithms for text detection in natural images. The authors discuss the future perspective of recent advances in text detection in natural images with various benchmark datasets and performance metrics.

Learning to Read Irregular Text with Attention Mechanisms

We present a robust end-to-end neural-based model to attentively recognize text in natural images. Particularly, we focus on accurately identifying irregular (perspectively distorted or curved) text, which has not been well addressed in the previous literature. Previous research on text reading often works with regular (horizontal and frontal) text and does not adequately generalize to processing text with perspective distortion or curving effects. Our work proposes to overcome this difficulty by introducing two learning components: (1) an auxiliary dense character detection task that helps to learn text specific visual patterns, (2) an alignment loss that provides guidance to the training of an attention model. We show with experiments that these two components are crucial for achieving fast convergence and high classification accuracy for irregular text recognition. Our model outperforms previous work on two irregular-text datasets: SVT-Perspective and CUTE80, and is also highly-competitive on several regular-text datasets containing primarily horizontal and frontal text.

An Effective Edge and Texture Based Approach towards Curved Videotext Detection and Extraction

In present day video text greatly helps video indexing and retrieval system as they often carry significant semantic information. Video text analysis is challenging due to varying background, multiple orientations and low contrast between text and non-text regions. Proposed approach explores a new framework for curved video text detection and recognition where from the observation that curve text regions can be well defined by edges size and uniform texture, Probable curved text edge detection is accomplished by processing wavelet sub bands followed by text localization by utilizing fast texture descriptor LU-transform. Binarization is achieved by maximal H-transform. A Connected Component filtering method followed by B-Spline curve fitting on centroid of each character vertically aligns each oriented character. The aligned text string is recognized by optical character recognition (OCR). Experiments on various curved video frames shows that proposed method is efficacious and robust in detecting and recognizing curved videotext.