Text Detection Method Research Articles

A Text Detection Method Based on Multi-Scale Selective Fusion Feature Pyramid and Multi-Semantic Spatial Network for Visual IoT

A Text Detection Method Based on Multi-Scale Selective Fusion Feature Pyramid and Multi-Semantic Spatial Network for Visual IoT

Scene Text Detection and Recognition Using Maximally Stable Extremal Region

In recent years, scene text detection and recognition have become important research areas in computer vision and machine learning. Traditional text detection and recognition methods may struggle with detecting and recognizing text in images with low resolution, complex backgrounds, and varying font sizes. The proposed methodology addresses these challenges by combining multiple algorithms and using deep learning techniques. In this paper, we propose a method for scene text detection based on Maximally Stable Extremal Regions (MSER) combined with Stroke Width Transform (SWT) and recognition using Convolutional Recurrent Neural Networks (CRNN). Our method consists of two stages: text detection and text recognition. To detect text, we use MSER and SWT to extract candidate text regions from the input and then, we eradicate non-text regions using image to image translation. Finally, to recognize text, CRNN is used to recognize the text present in the detected regions. Our CRNN architecture consists of convolutional and recurrent layers, which enable us to capture both spatial and temporal features of the text. The methodology is evaluated on various benchmark datasets and has obtained good results with accuracy of 96% when compared to existing methods.

DADNet: text detection of arbitrary shapes from drone perspective based on boundary adaptation

The rapid development of drone technology has made drones one of the essential tools for acquiring aerial information. The detection and localization of text information through drones greatly enhance their understanding of the environment, enabling tasks of significant importance such as community commercial planning and autonomous navigation in intelligent environments. However, the unique perspective and complex environment during drone photography lead to various challenges in text detection, including diverse text shapes, large-scale variations, and background interference, making traditional methods inadequate. To address this issue, we propose a drone-based text detection method based on boundary adaptation. We first conduct an in-depth analysis of text characteristics from a drone’s perspective. Using ResNet50 as the backbone network, we introduce the proposed Hybrid Text Attention Mechanism into the backbone network to enhance the perception of text regions in the feature extraction module. Additionally, we propose a Spatial Feature Fusion Module to adaptively fuse text features of different scales, thereby enhancing the model’s adaptability. Furthermore, we introduce a text detail transformer by incorporating a local feature extractor into the transformer of the text detail boundary iteration optimization module. This enables the precise optimization and localization of text boundaries by reducing the interference of complex backgrounds, eliminating the need for complex post-processing. Extensive experiments on challenging text detection datasets and drone-based text detection datasets validate the high robustness and state-of-the-art performance of our proposed method, laying a solid foundation for practical applications.

A Historical Handwritten French Manuscripts Text Detection Method in Full Pages

Historical handwritten manuscripts pose challenges to automated recognition techniques due to their unique handwriting styles and cultural backgrounds. In order to solve the problems of complex text word misdetection, omission, and insufficient detection of wide-pitch curved text, this study proposes a high-precision text detection method based on improved YOLOv8s. Firstly, the Swin Transformer is used to replace C2f at the end of the backbone network to solve the shortcomings of fine-grained information loss and insufficient learning features in text word detection. Secondly, the Dysample (Dynamic Upsampling Operator) method is used to retain more detailed features of the target and overcome the shortcomings of information loss in traditional upsampling to realize the text detection task for dense targets. Then, the LSK (Large Selective Kernel) module is added to the detection head to dynamically adjust the feature extraction receptive field, which solves the cases of extreme aspect ratio words, unfocused small text, and complex shape text in text detection. Finally, in order to overcome the CIOU (Complete Intersection Over Union) loss in target box regression with unclear aspect ratio, insensitive to size change, and insufficient correlation between target coordinates, Gaussian Wasserstein Distance (GWD) is introduced to modify the regression loss to measure the similarity between the two bounding boxes in order to obtain high-quality bounding boxes. Compared with the State-of-the-Art methods, the proposed method achieves optimal performance in text detection, with the precision and mAP@0.5 reaching 86.3% and 82.4%, which are 8.1% and 6.7% higher than the original method, respectively. The advancement of each module is verified by ablation experiments. The experimental results show that the method proposed in this study can effectively realize complex text detection and provide a powerful technical means for historical manuscript reproduction.

Correction: DC-PSENet: a novel scene text detection method integrating double ResNet-based and changed channels recursive feature pyramid

Correction: DC-PSENet: a novel scene text detection method integrating double ResNet-based and changed channels recursive feature pyramid

(HTBNet)Arbitrary Shape Scene Text Detection with Binarization of Hyperbolic Tangent and Cross-Entropy.

The existing segmentation-based scene text detection methods mostly need complicated post-processing, and the post-processing operation is separated from the training process, which greatly reduces the detection performance. The previous method, DBNet, successfully simplified post-processing and integrated post-processing into a segmentation network. However, the training process of the model took a long time for 1200 epochs and the sensitivity to texts of various scales was lacking, leading to some text instances being missed. Considering the above two problems, we design the text detection Network with Binarization of Hyperbolic Tangent (HTBNet). First of all, we propose the Binarization of Hyperbolic Tangent (HTB), optimized along with which the segmentation network can expedite the initial convergent speed by reducing the number of epochs from 1200 to 600. Because features of different channels in the same scale feature map focus on the information of different regions in the image, to better represent the important features of all objects in the image, we devise the Multi-Scale Channel Attention (MSCA). Meanwhile, considering that multi-scale objects in the image cannot be simultaneously detected, we propose a novel module named Fused Module with Channel and Spatial (FMCS), which can fuse the multi-scale feature maps from channel and spatial dimensions. Finally, we adopt cross-entropy as the loss function, which measures the difference between predicted values and ground truths. The experimental results show that HTBNet, compared with lightweight models, has achieved competitive performance and speed on Total-Text (F-measure:86.0%, FPS:30) and MSRA-TD500 (F-measure:87.5%, FPS:30).

A Multi-Scale Natural Scene Text Detection Method Based on Attention Feature Extraction and Cascade Feature Fusion.

Scene text detection is an important research field in computer vision, playing a crucial role in various application scenarios. However, existing scene text detection methods often fail to achieve satisfactory results when faced with text instances of different sizes, shapes, and complex backgrounds. To address the challenge of detecting diverse texts in natural scenes, this paper proposes a multi-scale natural scene text detection method based on attention feature extraction and cascaded feature fusion. This method combines global and local attention through an improved attention feature fusion module (DSAF) to capture text features of different scales, enhancing the network's perception of text regions and improving its feature extraction capabilities. Simultaneously, an improved cascaded feature fusion module (PFFM) is used to fully integrate the extracted feature maps, expanding the receptive field of features and enriching the expressive ability of the feature maps. Finally, to address the cascaded feature maps, a lightweight subspace attention module (SAM) is introduced to partition the concatenated feature maps into several sub-space feature maps, facilitating spatial information interaction among features of different scales. In this paper, comparative experiments are conducted on the ICDAR2015, Total-Text, and MSRA-TD500 datasets, and comparisons are made with some existing scene text detection methods. The results show that the proposed method achieves good performance in terms of accuracy, recall, and F-score, thus verifying its effectiveness and practicality.

Enhances the recognition accuracy of the complex text for online production labels by improving convolutional recurrent neural network

In the process of production, the label on the product provides the basic product information. Due to the complex text contained on the product labels, the high accuracy recognition for online production labels has always been a challenging problem. To address this issue, a more effective method for complex text detection by improving the convolutional recurrent neural network has been proposed to enhance the recognition accuracy of complex text. Firstly, the SE-DenseNet feature extraction network has been introduced for feature extraction, aiming to improve the model’s depth and feature extraction capacity. Then, the Bi-GRU network is utilized to learn and model the hidden states and spatial features extracted by SE-DenseNet, anticipate preliminary sequence results, reduce model parameters, and improve the model’s calculation performance. Finally, the CTC network is employed for transcription to convert each feature sequence prediction output by Bi-GRU into a label sequence, achieving complex text recognition. Experimental results on the SVT, IIIT-5K, ICDAR2013 public dataset, and a self-built dataset demonstrate that the proposed model achieves superior outcomes on both public and self-built datasets. Remarkably, the model exhibits the highest recognition accuracy of 93.2% on the ICDAR2013 public dataset, demonstrating its potential to support complex text recognition for online production labels.

CPN: Complementary Proposal Network for Unconstrained Text Detection

Existing methods for scene text detection can be divided into two paradigms: segmentation-based and anchor-based. While Segmentation-based methods are well-suited for irregular shapes, they struggle with compact or overlapping layouts. Conversely, anchor-based approaches excel for complex layouts but suffer from irregular shapes. To strengthen their merits and overcome their respective demerits, we propose a Complementary Proposal Network (CPN) that seamlessly and parallelly integrates semantic and geometric information for superior performance. The CPN comprises two efficient networks for proposal generation: the Deformable Morphology Semantic Network, which generates semantic proposals employing an innovative deformable morphological operator, and the Balanced Region Proposal Network, which produces geometric proposals with pre-defined anchors. To further enhance the complementarity, we introduce an Interleaved Feature Attention module that enables semantic and geometric features to interact deeply before proposal generation. By leveraging both complementary proposals and features, CPN outperforms state-of-the-art approaches with significant margins under comparable computation cost. Specifically, our approach achieves improvements of 3.6%, 1.3% and 1.0% on challenging benchmarks ICDAR19-ArT, IC15, and MSRA-TD500, respectively. Code for our method will be released.

Text Detection Method With Emphasis on Text Component Importance and Lightweight Design

Text Detection Method With Emphasis on Text Component Importance and Lightweight Design

A Terminal Tube Text Detection and Recognition Method Based on Improved YOLOv7-Tiny and CRNN

A Terminal Tube Text Detection and Recognition Method Based on Improved YOLOv7-Tiny and CRNN

Extraction of Text from Images Using Deep Learning

In the recent scenario, it is important to extract the text from various formats, including handwritten and documents. The ability to accurately detect and recognize text, is a crucial task in many fields, such as OCR systems, document analysis, and image processing. Convolutional neural networks (CNN) and bidirectional long short-term memory (BiLSTM) are used in a unique method for text detection. Additionally, CNN consist of six sequential layers by using Adam optimizer and SoftMax. The proposed approach is designed effectively to handle the variability and complexity of text in both handwritten and document formats. The proposed approach achieved a significant improvement in text detection and recognition accuracy, with 88.5 percentage while comparing with the existing techniques of CNN and LSTM which has an accuracy of 81.8 percentage.

Research on the Innovation of Enterprise Accounting Management under the Financial Shared Service Model

Abstract Financial shared services not only improve operational efficiency and reduce management costs but also realize auxiliary data analysis and management decision-making work, creating more value for enterprises. This paper builds a financial shared service system based on image recognition and extraction of financial bills to realize the functions of financial content recognition, voucher generation, application recognition, and administrative approval. We perform pre-processing tasks like binarization and edge detection on the financial bill image to identify the form lines. We then use the Hough transform to solve the function of the form lines, rotate, and correct the tilt angle. The form structure and financial text detection method are created based on the accurate form line detection. Analysis of two companies using the system of this paper reveals that the number of entered field information can be reduced by 91.48% of the entry workload after optimizing the system of this paper. The economic efficiency of labor costs can be significantly improved by reducing the time spent by reimbursement personnel in the reimbursement process by approximately 4,400 hours per month. By using the system in this paper, a new document can be created and submitted for approval in just 11 minutes, which reduces the document time by 86.25%. The constructed scores for the four first-level indicators, A, B, C, and D, range from 80 to 90 points, resulting in a total score of 87.417 points for the comprehensive evaluation. The construction of the financial shared service system in this paper consolidates the enterprise financial business into a centralized processing system, thereby enhancing the quality and efficiency of enterprise accounting management.

Ship name text detection method with scene priors fusion

Ship name text detection method with scene priors fusion

The use of Scene Text Detection methods for news crawl extraction

News crawl extraction is a subset of media monitoring. It is not directly related to the broadcast itself and not spoken by any anchor or guest - therefore its content cannot be inspected via speech-to-text tools. News crawl content is only available as text in video frames so its extraction can be done using Scene Text Detection techniques. This work tests the most used deep learning Scene Text Detection methods (both regression and semantic segmentation approaches) to see if they can be used as a base in news crawl extraction. Our investigation shows that regression based model CTPN performs better for our particular purpose that the semantic segmentation based EAST and CRAFT models.

A pseudo-color image-based cylindrical object surface text detection method

A pseudo-color image-based cylindrical object surface text detection method

Detect Arbitrary-Shaped Text via Adaptive Thresholding and Localization Quality Estimation

The two-stage scene text detection algorithms based on Mask R-CNN have achieved good performances on multiple challenging benchmarks. However, their effectiveness is degraded due to artificially setting constant thresholds and low localization quality of candidate boxes. In this paper, we present a novel scene text detection method based on Mask R-CNN and the proposed method, named LOAD, proposes adaptive threshold module and localization quality estimation module to address the above two problems. We propose two kinds of adaptive thresholds which are used for the filtering of candidate boxes and the binarization of pixels respectively. We introduce the self-attention mechanism to obtain the global information for generating the adaptive thresholds. Besides, we introduce the localization quality estimation into our model to obtain more accurate candidate boxes for subsequent segmentation. Comparative experiments are conducted on five benchmarks(ICDAR 2015, ICDAR 2017, MSRA-TD500, Total-Text and CTW1500), and the results demonstrate that the proposed method achieves the state-of-the-art performance with an F-measure of 91.0%, 78.7%, 87.4%, 90.6% and 86.0%. We also provide adequate ablation experiments to demonstrate the effectiveness of the proposed components.

Vietnamese Scene Text Detection Methodbased on Deep Learning

This paper proposes an efficient method for detecting Vietnamese text in outdoor scene images. Essentially, the text detection method presented here is based on the idea of utilizing deep learning network architectures to learn various geometric properties in order to reconstruct polygonal representations of text regions. The effectiveness of the method has been evaluated on four real-world outdoor scene image datasets, including the ICDAR 2015, Total-Text, VinText, and VnSceneText datasets. Experimental results show that the proposed method can detect text of various shapes and sizes with high and consistent accuracy. Specifically, the method achieved Precision, Recall, and Hmean scores of 87.53%, 86.94%, and 87.23%, respectively, on the test datasets, 84.32%, 88.17%, and 86.20% on a different dataset, 85.63%, 87.94%, and 86.77% on yet another dataset, and 85.14%, 87.23%, and 86.17% on the last dataset. The experimental results indicate that this approach is feasible for detecting Vietnamese text in outdoor scene images.

Kernel Proposal Network for Arbitrary Shape Text Detection.

Segmentation-based methods have achieved great success for arbitrary shape text detection. However, separating neighboring text instances is still one of the most challenging problems due to the complexity of texts in scene images. In this article, we propose an innovative kernel proposal network (dubbed KPN) for arbitrary shape text detection. The proposed KPN can separate neighboring text instances by classifying different texts into instance-independent feature maps, meanwhile avoiding the complex aggregation process existing in segmentation-based arbitrary shape text detection methods. To be concrete, our KPN will predict a Gaussian center map for each text image, which will be used to extract a series of candidate kernel proposals (i.e., dynamic convolution kernel) from the embedding feature maps according to their corresponding keypoint positions. To enforce the independence between kernel proposals, we propose a novel orthogonal learning loss (OLL) via orthogonal constraints. Specifically, our kernel proposals contain important self-information learned by network and location information by position embedding. Finally, kernel proposals will individually convolve all embedding feature maps for generating individual embedded maps of text instances. In this way, our KPN can effectively separate neighboring text instances and improve the robustness against unclear boundaries. To the best of our knowledge, our work is the first to introduce the dynamic convolution kernel strategy to efficiently and effectively tackle the adhesion problem of neighboring text instances in text detection. Experimental results on challenging datasets verify the impressive performance and efficiency of our method. The code and model are available at https://github.com/GXYM/KPN.

IDBNet: Improved differentiable binarisation network for natural scene text detection

AbstractThe text in the natural scene can express rich semantic information, which helps people understand and analyse daily things. This paper focuses on the problems of discrete text spatial distribution and variable text geometric size in natural scenes with complex backgrounds and proposes an end‐to‐end natural scene text detection method based on DBNet. The authors first use IResNet as the backbone network, which does not increase network parameters while retaining more text features. Furthermore, a module with Transformer is introduced in the feature extraction stage to strengthen the correlation between high‐level feature pixels. Then, the authors add a spatial pyramid pooling structure in the end of feature extraction, which realises the combination of local and global features, enriches the expressive ability of feature maps, and alleviates the detection limitations caused by the geometric size of features. Finally, to better integrate the features of each level, a dual attention module is embedded after multi‐scale feature fusion. Extensive experiments on the MSRA‐TD500, CTW1500, ICDAR2015, and MLT2017 data set are conducted. The results showed that IDBNet can improve the average precision, recall, and F‐measure of a text compared with the state of art text detection methods and has higher predictive ability and practicability.