Scene Text Research Articles

DPNet: Scene text detection based on dual perspective CNN-transformer.

With the continuous advancement of deep learning, research in scene text detection has evolved significantly. However, complex backgrounds and various text forms complicate the task of detecting text from images. CNN is a deep learning algorithm that automatically extracts features through convolution operation. In the task of scene text detection, it can capture local text features in images, but it lacks global attributes. In recent years, inspired by the application of transformers in the field of computer vision, it can capture the global information of images and describe them intuitively. Therefore, this paper proposes scene text detection based on dual perspective CNN-transformer. The channel enhanced self-attention module (CESAM) and spatial enhanced self-attention module (SESAM) proposed in this paper are integrated into the traditional ResNet backbone network. This integration effectively facilitates the learning of global contextual information and positional relationships of text, thereby alleviating the challenge of detecting small target text. Furthermore, this paper introduces a feature decoder designed to refine the effective text information within the feature map and enhance the perception of detailed information. Experiments show that the method proposed in this paper significantly improves the robustness of the model for different types of text detection. Compared to the baseline, it achieves performance improvements of 2.51% (83.81 vs. 81.3) on the Total-Text dataset, 1.87% (86.07 vs. 84.2) on the ICDAR 2015 dataset, and 3.63% (86.72 vs. 83.09) on the MSRA-TD500 dataset, while also demonstrating better visual effects.

A New Contrastive Learning based Vision Transformer for Sentiment Analysis using Scene Text Images

A New Contrastive Learning based Vision Transformer for Sentiment Analysis using Scene Text Images

A Comparative Model for Blurred Text Detection in Wild Scene Using Independent Component Analysis (ICA) and Enhanced Genetic Algorithm (Using a Bird Approach) with Classifiers

The advent of the study of Scene Text Detection and Recognition has exposed some significant challenges text recognition faces, such as blurred text detection. This study proposes a comparative model for detecting blurred text in wild scenes using independent component analysis (ICA) and enhanced genetic algorithm (E-GA) with support vector machine (SVM) and k-nearest neighbors (KNN) as classifiers. The proposed model aims to improve the accuracy of blurred text detection in challenging environments with complex backgrounds, noise, and illumination variations. The proposed model consists of three main stages: preprocessing, feature extraction, and classification. In the preprocessing stage, the input image is first preprocessed to remove noise and enhance edges using a median filter and a Sobel filter, respectively. Then, the blurred text regions are extracted using the Laplacian of Gaussian (LoG) filter. In the feature extraction stage, ICA is used to extract independent components from the blurred text regions. The extracted components are then fed into an E-GA-based feature selection algorithm to select the most discriminative features. The E-GA simply fine tunes the selection functionalities of the traditional GA using a bird approach. The selected features are then normalized and fed into the SVM and KNN classifiers. Experimental results on a benchmarking dataset (ICDAR 2019 LSVT) shows that the model outperforms state-of-the-art methods in terms of detection accuracy, precision, recall, and F1-score. The proposed model achieves an overall accuracy of 95.13% for SVM and 88.69% for KNN, which is significantly higher than the already existing methods which for SVM is 93%. In conclusion, the proposed model provides a promising approach for detecting blurred text in wild scenes. The combination of ICA, E-GA, and SVM/KNN classifiers enhances the robustness and accuracy of the detection system, which can be beneficial for a wide range of applications, such as text recognition, document analysis, and security systems.

ACP-Net: Asymmetric Center Positioning Network for Real-Time Text Detection

Scene text detection is crucial across numerous application fields. However, despite the emphasis on real-time performance in scene text detection, most existing detection models utilize the Feature Pyramid Network (FPN) for feature extraction, often disregarding its inherent limitations. Integrating high-resolution multi-channel features into FPN requires substantial computational resources. While FPN treats local and global features equally and is stable in various applications, its suitability for text-specific features is questionable. To this end, we propose the Asymmetric Center Positioning Network (ACP-Net) to replace FPN, achieving accuracy and real-time text detection in complex scenarios. ACP-Net features an asymmetric feature structure with independent branches for global and local information, along with an adaptive weighted fusion module to capture long-range dependencies effectively. In addition, a text center positioning module enhances text feature understanding by learning feature centers. Comprehensive evaluations across various terminals confirmed ACP-Net’s superior accuracy and speed.

Soft set-based MSER end-to-end system for occluded scene text detection, recognition and prediction

The presence of unpredictable occlusions on natural scene text is a significant challenge, exacerbating the difficulties already posed on text detection and recognition by the variability of such images. Addressing the need for a robust, consistently performing approach that can effectively address the above challenges, this paper presents a new Soft Set-based end-to-end system for text detection, recognition and prediction in occluded natural scene images. This is the first approach to integrate text detection, recognition and prediction, unlike existing systems developed for end-to-end text spotting (text detection and recognition) only. For candidate text components detection, the proposed combination of Soft Sets with Maximally Stable Extremal Regions (SS-MSER) improves text detection and spotting in natural scene images, irrespectively of the presence of arbitrarily orientated and shaped text, complex backgrounds and occlusion. Furthermore, a Graph Recurrent Neural Network is proposed for grouping candidate text components into text lines and for fitting accurate bounding boxes to each word. Finally, a Convolutional Recurrent Neural Network (CRNN) is proposed for the recognition of text and for predicting missing characters due to occlusion. Experimental results on a new occluded scene text dataset (OSTD) and on the most relevant benchmark natural scene text datasets demonstrate that the proposed system outperforms the state-of-the-art in text detection, recognition and prediction. The code and dataset are available at https://github.com/alloydas/Softset-MSER-Based-Occluded-Scene-Text-Spotting/blob/master/Soft_set_MSER.ipynb

GRNet: a graph reasoning network for enhanced multi-modal learning in scene text recognition

Abstract Recent advancements in scene text recognition have predominantly focused on leveraging textual semantics. However, an over-reliance on linguistic priors can impede a model’s ability to handle irregular text scenes, including non-standard word usage, occlusions, severe distortions, or stretching. The key challenges lie in effectively localizing occlusions, perceiving multi-scale text, and inferring text based on scene context. To address these challenges and enhance visual capabilities, we introduce the Graph Reasoning Model (GRM). The GRM employs a novel feature fusion method to align spatial context information across different scales, beginning with a feature aggregation stage that extracts rich spatial contextual information from various feature maps. Visual reasoning representations are then obtained through graph convolution. We integrate the GRM module with a language model to form a two-stream architecture called GRNet. This architecture combines pure visual predictions with joint visual-linguistic predictions to produce the final recognition results. Additionally, we propose a dynamic iteration refinement for the language model to prevent over-correction of prediction results, ensuring a balanced contribution from both visual and linguistic cues. Extensive experiments demonstrate that GRNet achieves state-of-the-art average recognition accuracy across six mainstream benchmarks. These results highlight the efficacy of our multi-modal approach in scene text recognition, particularly in challenging scenarios where visual reasoning plays a crucial role.

HPNet: Text Detection Network with Hybrid Attention and Pixel Aggregation for Irregularly-Shaped Nearby Texts

Scene text detection is a challenging topic in computer vision, characterized by complex illumination, irregular shape, and arbitrary size. While recent advancements have been made in scene text detection, it remains difficult to simultaneously distinguish nearby text and accommodate irregularly shaped text. Therefore, this paper introduces HPNet, an enhanced text detector, based on the segmentation method that predicts two-scale results. To improve the shape robustness, the Hybrid Attentional Feature Fusion (HAFF) module is integrated into Feature Pyramid Networks (FPN) to dynamically perform feature fusion. Additionally, to distinguish nearby text, the model predicts the text region covering text instances and the text kernel covering the central region of the text. The improved Pixel Aggregation (PA) algorithm is then utilized to guide the expansion from the text kernel to the text region. Experiments on IC15, Total-Text, and CTW1500 validate the effectiveness of these improvements and the superiority of HPNet. Compared with the previous method PSENet for nearby texts, the proposed HPNet has improved inference speed by 63.6% and F-measure metric by 2.6%, 3.7%, and 2.5% on three datasets, respectively.

Visual place recognition from end-to-end semantic scene text features.

We live in a visual world where text cues are abundant in urban environments. The premise for our work is for robots to capitalize on these text features for visual place recognition. A new technique is introduced that uses an end-to-end scene text detection and recognition technique to improve robot localization and mapping through Visual Place Recognition (VPR). This technique addresses several challenges such as arbitrary shaped text, illumination variation, and occlusion. The proposed model captures text strings and associated bounding boxes specifically designed for VPR tasks. The primary contribution of this work is the utilization of an end-to-end scene text spotting framework that can effectively capture irregular and occluded text in diverse environments. We conduct experimental evaluations on the Self-Collected TextPlace (SCTP) benchmark dataset, and our approach outperforms state-of-the-art methods in terms of precision and recall, which validates the effectiveness and potential of our proposed approach for VPR.

Improving Scene Text Retrieval via Stylized Middle Modality

Scene text retrieval addresses the challenge of localizing and searching for all text instances within scene images based on a query text. This cross-modal task has significant applications in various domains, such as intelligent transportation systems and social media analysis. In practice, ensuring consistency of the same content between two modalities is crucial in improving retrieval accuracy. This paper addresses the issue by introducing a stylized middle modality, which fuses the graphical query text with the style of the extracted text proposal. To this end, we propose a stylized middle modality learning (SM \({}^{2}\) L) framework. The proposed stylized middle modality enables the network to jointly enforce constraints on visual feature coherence and text semantic feature consistency in the optimization phase, thereby minimizing the modality gap in the retrieval space. This brings in two major advantages: 1) SM \({}^{2}\) L will pave the way to seamlessly benefit the scene text retrieval and 2) the proposed learning paradigm enables the machine to avoid adding redundant computing resources in the inference phase. Substantial experiments demonstrate that the proposed method outperforms the state-of-the-art retrieval performance considerably.

A novel domain independent scene text localizer

Text localization across multiple domains is crucial for applications like autonomous driving and tracking marathon runners. This work introduces DIPCYT, a novel model that utilizes Domain Independent Partial Convolution and a Yolov5-based Transformer for text localization in scene images from various domains, including natural scenes, underwater, and drone images. Each domain presents unique challenges: underwater images suffer from poor quality and degradation, drone images suffer from tiny text and loss of shapes, and scene images suffer from arbitrarily oriented, shaped text. Additionally, license plates in drone images may not provide rich semantic information compared to other text types due to loss of contextual information between characters. To tackle these challenges, DIPCYT employs new partial convolution layers within Yolov5 and integrates Transformer detection heads with a novel Fourier Positional Convolutional Block Attention Module (FPCBAM). This approach leverages common text properties across domains, such as contextual (global) and spatial (local) relationships. Experimental results demonstrate that DIPCYT outperforms existing methods, achieving F-scores of 0.90, 0.90, 0.77, 0.85, 0.85, and 0.88 on Total-Text, ICDAR 2015, ICDAR 2019 MLT, CTW1500, Drone, and Underwater datasets, respectively.

Scene Chinese Recognition with Local and Global Attention

Recently, scene Chinese recognition has attracted increasing attention. While mainstream scene text recognition methods exhibit outstanding performance in English recognition, they are considerably limited in Chinese recognition, due to inter-class similarity, intra-class variability, and complex combination of components in scene Chinese text. In this paper, we design Adaptive Position Encoding(APE) to enhance the model’s ability to perceive spatial information. Based on APE, we have innovatively designed Local Attention Module (LAM) and Global Attention Module (GAM). Specifically, LAM captures local features to identify common characteristics among characters of the same category, addressing the issue of intra-class variability. Meanwhile, LAM captures global features to identify the subordination relationships of Chinese character components. By integrating LAM and GAM, combining both local and global features, it is possible to find differences in the details among features that are fundamentally similar, thus solving the problem of inter-class similarity. Further, we contrive the transformer encoder–decoder structure to identify the vast variety of Chinese characters. Based on the Local/Global Attention Module and transformer encoder–decoder framework, we devise the novel sequence-to-sequence Local and Global Attention Network(LGANet), where both the backbone and the encoder/decoder are composed of attention mechanisms. Subsequent experiments on the Chinese scene dataset show that the recognition accuracy of our proposed LGANet is 77.3% and the normalized editing distance is 88.6%, both of which achieve the SOTA results in Fig. 1.

An End-to-End Scene Text Recognition for Bilingual Text

Text localization and recognition from natural scene images has gained a lot of attention recently due to its crucial role in various applications, such as autonomous driving and intelligent navigation. However, two significant gaps exist in this area: (1) prior research has primarily focused on recognizing English text, whereas Arabic text has been underrepresented, and (2) most prior research has adopted separate approaches for scene text localization and recognition, as opposed to one integrated framework. To address these gaps, we propose a novel bilingual end-to-end approach that localizes and recognizes both Arabic and English text within a single natural scene image. Specifically, our approach utilizes pre-trained CNN models (ResNet and EfficientNetV2) with kernel representation for localization text and RNN models (LSTM and BiLSTM) with an attention mechanism for text recognition. In addition, the AraElectra Arabic language model was incorporated to enhance Arabic text recognition. Experimental results on the EvArest, ICDAR2017, and ICDAR2019 datasets demonstrated that our model not only achieves superior performance in recognizing horizontally oriented text but also in recognizing multi-oriented and curved Arabic and English text in natural scene images.

ESRNet: an exploring sample relationships network for arbitrary-shaped scene text detection

ESRNet: an exploring sample relationships network for arbitrary-shaped scene text detection

Rethinking Multilingual Scene Text Spotting: A Novel Benchmark and a Character-Level Feature Based Approach

End-to-end multilingual scene text spotting aims to integrate scene text detection and recognition into a unified framework. Actually, the accuracy of text recognition largely depends on the accuracy of text detection. Due to the lackage of benchmarks with adequate and high-quality character-level annotations for multilingual scene text spotting, most of the existing methods train on the benchmarks only with word-level annotations. However, the performance of multilingual scene text spotting are not that satisfied training on the existing benchmarks, especially for those images with special layout or words out of vocabulary. In this paper, we proposed a simple YOLO-like baseline named CMSTR for character-level multilingual scene text spotting simultaneously and efficiently. Technically, for each text instance, we represent the character sequence as ordered points and model them with learnable explicit point queries. After passing a single decoder, the point queries have encoded requisite text semantics and locations, thus can be further decoded to the center line, boundary, script, and confidence of text via very simple prediction heads in parallel. Furthermore, we show the surprisingly good extensibility of our method, in terms of character class, language type, and task. On the one hand, DeepSolo not only performs well in English scenes but also masters the Chinese transcription with complex font structure and a thousand-level character classes. On the other hand, based on the extensibility of DeepSolo, we launch DeepSolo++ for multilingual text spotting, making a further step to let Transformer decoder with explicit points solo for multilingual text detection, recognition, and script identification all at once.

Turning a CLIP Model Into a Scene Text Spotter.

We exploit the potential of the large-scale Contrastive Language-Image Pretraining (CLIP) model to enhance scene text detection and spotting tasks, transforming it into a robust backbone, FastTCM-CR50. This backbone utilizes visual prompt learning and cross-attention in CLIP to extract image and text-based prior knowledge. Using predefined and learnable prompts, FastTCM-CR50 introduces an instance-language matching process to enhance the synergy between image and text embeddings, thereby refining text regions. Our Bimodal Similarity Matching (BSM) module facilitates dynamic language prompt generation, enabling offline computations and improving performance. FastTCM-CR50 offers several advantages: 1) It can enhance existing text detectors and spotters, improving performance by an average of 1.6% and 1.5%, respectively. 2) It outperforms the previous TCM-CR50 backbone, yielding an average improvement of 0.2% and 0.55% in text detection and spotting tasks, along with a 47.1% increase in inference speed. 3) It showcases robust few-shot training capabilities. Utilizing only 10% of the supervised data, FastTCM-CR50 improves performance by an average of 26.5% and 4.7% for text detection and spotting tasks, respectively. 4) It consistently enhances performance on out-of-distribution text detection and spotting datasets, particularly the NightTime-ArT subset from ICDAR2019-ArT and the DOTA dataset for oriented object detection.

Batch-transformer for scene text image super-resolution

Batch-transformer for scene text image super-resolution

Self-supervised memory learning for scene text image super-resolution

Computerised recognition of low-resolution scene text images has been a persistent challenge. To improve the recognition performance, image quality enhancement via image super-resolution technology provides an intuitive solution. Typical deep learning-based scene text image super-resolution methods assume that the image quality degradation from high-resolution images to their corresponding low-resolution counterparts can be represented by mapping well-distributed samples, which limits their reconstruction performance in a practical text recognition system. For real-world scenarios this assumption typically does not hold since image degradations arise from multiple sources during image capture and processing. In this paper, to alleviate this problem, we propose a novel self-supervised end-to-end memory network model for scene text image super-resolution. In particular, after extracting enriched and finer representations from low-resolution text images via a spatial refinement block, we introduce a memory-based network to yield an improved super-resolution model that can handle complex degradation sources. Furthermore, to boost the effectiveness of our method, we design a multi-term loss to exploit textual structure information, where, in addition to the traditional reconstruction loss, we embed a character perceptual loss and a boundary enhancement loss. Extensive experiments on different datasets demonstrate that our proposed MNTSR method effectively improves the recognition accuracy for several scene text image recognition models and achieves state-of-the-art results. The source code is made available at https://github.com/xyzhu1/MNTSR.

Rectification of Curved Scene Text Based on B-Spline Curve Fitting

Rectification of Curved Scene Text Based on B-Spline Curve Fitting

DPGS: Cross-cooperation guided dynamic points generation for scene text spotting

End-to-end text spotting aims to combine scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. While polygon or segmentation-based methods eliminate heuristic post-processing, they still face challenges such as background noise and high computational burden. In this study, we introduce DPGS, a coarse-to-fine learning framework that lets Dynamic Points Generation for text Spotting. DPGS simultaneously learns character representations for both detection and recognition tasks. Specifically, for each text instance, we represent the character sequence as ordered points and model them with learnable point queries. This approach progressively selects appropriate key points covering character and leverages group attention to associate similar information from different positions, improving detection accuracy. After passing through a single decoder, the point queries encode text semantics and locations, facilitating decoding to central line, boundary, script, and confidence of text through simple prediction heads. Additionally, we introduce an adaptive cooperative criterion to combine more useful feature knowledge, enhancing training efficiency. Extensive experiments show the superiority of our DPGS when handling scene text detection and recognition tasks. Compared to their respective top-1 methods, DPGS has significantly improved the average recognition accuracy by 3.7%, 1.9%, and 0.7% on the Total-Text, ICDAR15, and CTW1500 datasets, respectively.

Transformer-based end-to-end attack on text CAPTCHAs with triplet deep attention

Websites frequently use text-based captcha images to distinguish whether the user is a person or not. Previous research mainly focuses on different training strategies and neglects the characteristics of the text-based captcha images themselves, resulting in low accuracy. For text-based captcha images characterized by rotation, distortion, and non-character elements, we propose an end-to-end attack using a Transformer-based method with triplet deep attention. Firstly, the features of text-based captchas are extracted using ResNet45 with triplet deep attention module and Transformer encoder. The TDA module is capable of learning rotational and distortion features of characters. Subsequently, based on self-attention mechanism, design query, key, and value, and adopt the query enhancement module to enhance the query. The query enhancement module can strengthen character localization and reduce attention drift towards non-character elements. Finally, the feature maps are transformed into probabilities of character for the final text recognition. Experiments are conducted on captcha datasets based on Roman characters from 9 popular websites, achieving average word accuracy of 91.14%. To evaluate the performance of our method on data with small samples, experiments are conducted different scales of training data. Additionally, we use the method on Chinese text-based captcha tasks and achieve average word accuracy of 99.60%. The effectiveness of the method is also explored under conditions of lack of illumination and scene text recognition, where background interference is present.