CVTD: A Robust Car-Mounted Video Text Detector

Text perception is crucial for understanding the semantics of outdoor scenes,making it a key requirement for building intelligent systems for driver assistance or autonomous driving.Text information in car-mounted videos can assist drivers in making decisions.However,Car-mounted video text images pose challenges such as complex backgrounds,small fonts,and the need for real-time detection.We proposed a robust Car-mounted Video Text Detector(CVTD).It is a lightweight text detection model based on ResNet18 for feature extraction,capable of detecting text in arbitrary shapes.Our model efficiently extracted global text positions through the Coordinate Attention Threshold Activation(CATA)and enhanced the representation capability through stacking two Feature Pyramid Enhancement Fusion Modules(FPEFM),strengthening feature representation,and integrating text local features and global position information,reinforcing the representation capability of the CVTD model.The enhanced feature maps,when acted upon by Text Activation Maps(TAM),effectively distinguished text foreground from non-text regions.Additionally,we collected and annotated a dataset containing 2200 images of Car-mounted Video Text(CVT)under various road conditions for training and evaluating our model’s performance.We further tested our model on four other challenging public natural scene text detection benchmark datasets,demonstrating its strong generalization ability and real-time detection speed.This model holds potential for practical applications in real-world scenarios.

YOLOv5ST:A Lightweight and Fast Scene Text Detector

Scene text detection is an important task in computer vision.In this paper,we present YOLOv5 Scene Text(YOLOv5ST),an optimized architecture based on YOLOv5 v6.0 tailored for fast scene text detection.Our primary goal is to enhance inference speed without sacrificing significant detection accuracy,thereby enabling robust performance on resource-constrained devices like drones,closed-circuit television cameras,and other embedded systems.To achieve this,we propose key modifications to the network architecture to lighten the original backbone and improve feature aggregation,including replacing standard convolution with depth-wise convolution,adopting the C2 sequence module in place of C3,employing Spatial Pyramid Pooling Global(SPPG)instead of Spatial Pyramid Pooling Fast(SPPF)and integrating Bi-directional Feature Pyramid Network(BiFPN)into the neck.Experimental results demonstrate a remarkable 26%improvement in inference speed compared to the baseline,with only marginal reductions of 1.6%and 4.2%in mean average precision(mAP)at the intersection over union(IoU)thresholds of 0.5 and 0.5:0.95,respectively.Our work represents a significant advancement in scene text detection,striking a balance between speed and accuracy,making it well-suited for performance-constrained environments.

Embedded System Based Raspberry Pi 4 for Text Detection and Recognition

Detecting and recognizing text from natural scene images presents a challenge because the image quality depends on the conditions in which the image is captured,such as viewing angles,blurring,sensor noise,etc.However,in this paper,a prototype for text detection and recognition from natural scene images is proposed.This prototype is based on the Raspberry Pi 4 and the Universal Serial Bus(USB)camera and embedded our text detection and recognition model,which was developed using the Python language.Our model is based on the deep learning text detector model through the Efficient and Accurate Scene Text Detec-tor(EAST)model for text localization and detection and the Tesseract-OCR,which is used as an Optical Character Recognition(OCR)engine for text recog-nition.Our prototype is controlled by the Virtual Network Computing(VNC)tool through a computer via a wireless connection.The experiment results show that the recognition rate for the captured image through the camera by our prototype can reach 99.75%with low computational complexity.Furthermore,our proto-type is more performant than the Tesseract software in terms of the recognition rate.Besides,it provides the same performance in terms of the recognition rate with a huge decrease in the execution time by an average of 89%compared to the EasyOCR software on the Raspberry Pi 4 board.

Text Detection in Natural Scene Images Using Morphological Component Analysis and Laplacian Dictionary

Text in natural scene images usually carries abundant semantic information. However, due to variations of text and complexity of background, detecting text in scene images becomes a critical and challenging task. In this paper, we present a novel method to detect text from scene images. Firstly, we decompose scene images into background and text components using morphological component analysis(MCA), which will reduce the adverse effects of complex backgrounds on the detection results.In order to improve the performance of image decomposition,two discriminative dictionaries of background and text are learned from the training samples. Moreover, Laplacian sparse regularization is introduced into our proposed dictionary learning method which improves discrimination of dictionary. Based on the text dictionary and the sparse-representation coefficients of text, we can construct the text component. After that, the text in the query image can be detected by applying certain heuristic rules. The results of experiments show the effectiveness of the proposed method.

A Modified Method for Scene Text Detection by ResNet

In recent years,images have played a more and more important role in our daily life and social communication.To some extent,the textual information contained in the pictures is an important factor in understanding the content of the scenes themselves.The more accurate the text detection of the natural scenes is,the more accurate our semantic understanding of the images will be.Thus,scene text detection has also become the hot spot in the domain of computer vision.In this paper,we have presented a modified text detection network which is based on further research and improvement of Connectionist Text Proposal Network(CTPN)proposed by previous researchers.To extract deeper features that are less affected by different images,we use Residual Network(ResNet)to replace Visual Geometry Group Network(VGGNet)which is used in the original network.Meanwhile,to enhance the robustness of the models to multiple languages,we use the datasets for training from multi-lingual scene text detection and script identification datasets(MLT)of 2017 International Conference on Document Analysis and Recognition(ICDAR2017).And apart from that,the attention mechanism is used to get more reasonable weight distribution.We found the proposed models achieve 0.91 F1-score on ICDAR2011 test,better than CTPN trained on the same datasets by about 5%.

CNN and Fuzzy Rules Based Text Detection and Recognition from Natural Scenes

In today’s real world, an important research part in image processing isscene text detection and recognition. Scene text can be in different languages,fonts, sizes, colours, orientations and structures. Moreover, the aspect ratios andlayouts of a scene text may differ significantly. All these variations appear assignificant challenges for the detection and recognition algorithms that are consideredfor the text in natural scenes. In this paper, a new intelligent text detection andrecognition method for detectingthe text from natural scenes and forrecognizingthe text by applying the newly proposed Conditional Random Field-based fuzzyrules incorporated Convolutional Neural Network (CR-CNN) has been proposed.Moreover, we have recommended a new text detection method for detecting theexact text from the input natural scene images. For enhancing the presentation ofthe edge detection process, image pre-processing activities such as edge detectionand color modeling have beenapplied in this work. In addition, we have generatednew fuzzy rules for making effective decisions on the processes of text detectionand recognition. The experiments have been directedusing the standard benchmark datasets such as the ICDAR 2003, the ICDAR 2011, the ICDAR2005 and the SVT and have achieved better detection accuracy intext detectionand recognition. By using these three datasets, five different experiments havebeen conducted for evaluating the proposed model. And also, we have comparedthe proposed system with the other classifiers such as the SVM, the MLP and theCNN. In these comparisons, the proposed model has achieved better classificationaccuracywhen compared with the other existing works.

Mask Text Detector:一种检测自然场景下任意形状的文本分割网络

近年来场景文本检测技术飞速发展,提出一种可适用于任意形状文本检测的新颖算法Mask Text Detector.该算法在Mask R-CNN的基础上,用anchor-free的方法替代了原本的RPN层生成建议框,减少了超参、模型参数和计算量.还提出LQCS(Localization Quality and Classification Score)joint regression,能够将坐标质量和类别分数关联到一起,消除预测阶段不一致的问题.为了让网络区分复杂样本,结合传统的边缘检测算法提出Socle-Mask分支生成分割掩码.该模块在水平和垂直方向上分区别提取纹理特征,并加入通道自注意力机制,让网络自主选择通道特征.我们在三个具有挑战性的数据集(Total-Text、CTW1500和ICDAR2015)中进行了广泛的实验,验证了该算法具有很好的文本检测性能.

Label Enhancement for Scene Text Detection

Segmentation-based scene text detection has drawn a great deal of attention,as it can describe the text instance with arbitrary shapes based on its pixel-level prediction.However,most segmentation-based methods suffer from complex post-processing to separate the text instances which are close to each other,resulting in considerable time consumption during the inference procedure.A label enhancement method is proposed to construct two kinds of training labels for segmentation-based scene text detection in this paper.The label distribution learning(LDL)method is used to overcome the problem brought by pure shrunk text labels that might result in suboptimal detection perfor⁃mance.The experimental results on three benchmarks demonstrate that the proposed method can consistently improve the performance with⁃out sacrificing inference speed.

Adaptive Multi-Scale HyperNet with Bi-Direction Residual Attention Module forScene Text Detection

Scene text detection is an important step in the scene text reading system.There are still two problems during the existing text detection methods:(1)The small receptive of the convolutional layer in text detection is not sufficiently sensitive to the target area in the image;(2)The deep receptive of the convolutional layer in text detection lose a lot of spatial feature information.Therefore,detecting scene text remains a challenging issue.In this work,we design an effective text detector named Adaptive Multi-Scale HyperNet(AMSHN)to improve texts detection performance.Specifically,AMSHN enhances the sensitivity of target semantics in shallow features with a new attention mechanism to strengthen the region of interest in the image and weaken the region of no interest.In addition,it reduces the loss of spatial feature by fusing features on multiple paths,which significantly improves the detection performance of text.Experimental results on the Robust Reading Challenge on Reading Chinese Text on Signboard(ReCTS)dataset show that the proposed method has achieved the state-of-the-art results,which proves the ability of our detector on both particularity and universality applications.

Label distribution learning for scene text detection

Recently,segmentation-based scene text detection has drawn a wide research interest due to its flexibility in describing scene text instance of arbitrary shapes such as curved texts.However,existing methods usually need complex post-processing stages to process ambiguous labels,i.e.,the labels of the pixels near the text boundary,which may belong to the text or background.In this paper,we present a framework for segmentation-based scene text detection by learning from ambiguous labels.We use the label distribution learning method to process the label ambiguity of text annotation,which achieves a good performance without using additional post-processing stage.Experiments on benchmark datasets demonstrate that our method produces better results than state-of-the-art methods for segmentation-based scene text detection.

A Method for Detecting and Recognizing Yi Character Based on Deep Learning

Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition,we present a deep learning-based approach for Yi character detection and recognition.In the detection stage,an improved Differentiable Binarization Network(DBNet)framework is introduced to detect Yi characters,in which the Omni-dimensional Dynamic Convolution(ODConv)is combined with the ResNet-18 feature extraction module to obtain multi-dimensional complementary features,thereby improving the accuracy of Yi character detection.Then,the feature pyramid network fusion module is used to further extract Yi character image features,improving target recognition at different scales.Further,the previously generated feature map is passed through a head network to produce two maps:a probability map and an adaptive threshold map of the same size as the original map.These maps are then subjected to a differentiable binarization process,resulting in an approximate binarization map.This map helps to identify the boundaries of the text boxes.Finally,the text detection box is generated after the post-processing stage.In the recognition stage,an improved lightweight MobileNetV3 framework is used to recognize the detect character regions,where the original Squeeze-and-Excitation(SE)block is replaced by the efficient Shuffle Attention(SA)that integrates spatial and channel attention,improving the accuracy of Yi characters recognition.Meanwhile,the use of depth separable convolution and reversible residual structure can reduce the number of parameters and computation of the model,so that the model can better understand the contextual information and improve the accuracy of text recognition.The experimental results illustrate that the proposed method achieves good results in detecting and recognizing Yi characters,with detection and recognition accuracy rates of 97.5%and 96.8%,respectively.And also,we have compared the detection and recognition algorithms proposed in this paper with other typical algorithms.In these comparisons,the proposed model achieves better detection and recognition results with a certain reliability.

Scene text detection and recognition： recent advances and future trends

Text, as one of the most influential inventions of humanity, has played an important role in human life, so far from ancient times. The rich and precise information embod- ied in text is very useful in a wide range of vision-based ap- plications, therefore text detection and recognition in natu- ral scenes have become important and active research topics in computer vision and document analysis. Especially in re- cent years, the community has seen a surge of research efforts and substantial progresses in these fields, though a variety of challenges （e.g. noise, blur, distortion, occlusion and varia- tion） still remain. The purposes of this survey are three-fold： 1） introduce up-to-date works, 2） identify state-of-the-art al- gorithms, and 3） predict potential research directions in the future. Moreover, this paper provides comprehensive links to publicly available resources, including benchmark datasets, source codes, and online demos. In summary, this literature review can serve as a good reference for researchers in the areas of scene text detection and recognition.

A learning-based method to detect and segment text from scene images

This paper proposes a learning-based method for text detection and text segmentation in natural scene images. First, the input image is decomposed into multiple connected-components (CCs) by Niblack clustering algorithm. Then all the CCs including text CCs and non-text CCs are verified on their text features by a 2-stage classification module, where most non-text CCs are discarded by an attentional cascade classifier and remaining CCs are further verified by an SVM. All the accepted CCs are output to result in text only binary image. Experiments with many images in different scenes showed satisfactory performance of our proposed method.

Robust Video Text Detection with Morphological Filtering Enhanced MSER

Video text detection is a challenging problem, since video image background is generally complex and its subtitles often have the problems of color bleeding, fuzzy boundaries and low contrast due to video lossy compression and low resolution. In this paper, we propose a robust framework to solve these problems. Firstly, we exploit gradient amplitude map （GAM） to enhance the edge of an input image, which can overcome the problems of color bleeding and fuzzy boundaries. Secondly, a two-direction morphological filtering is developed to filter background noise and enhance the contrast between background and text. Thirdly, maximally stable extremal region （MSER） is applied to detect text regions with two extreme colors, and we use the mean intensity of the regions as the graph cuts＇ label set, and the Euclidean distance of three channels in HSI color space as the graph cuts smooth term, to get optimal segmentations. Finally, we group them into text lines using the geometric characteristics of the text, and then corner detection, multi-frame verification, and some heuristic rules are used to eliminate non-text regions. We test our scheme with some challenging videos, and the results prove that our text detection framework is more robust than previous methods.

Detection of text in images using SUSAN edge detector

Text embedded in images is one of many important cues for indexing and retrieval of images and videos. In the paper, we present a novel method of detecting text aligned either horizontally or vertically, in which a pyramid structure is used to represent an image and the features of the text are extracted using SUSAN edge detector. Text regions at each level of the pyramid are identified according to the autocorrelation analysis. New techniques are introduced to split the text regions into basic ones and merge them into text lines. By evaluating the method on a set of images, we obtain a very good performance of text detection.

A CCD based machine vision system for real-time text detection

Text detection and recognition is a hot topic in computer vision,which is considered to be the further development of the traditional optical character recognition(OCR)technology.With the rapid development of machine vision system and the wide application of deep learning algorithms,text recognition has achieved excellent performance.In contrast,detecting text block from complex natural scenes is still a challenging task.At present,many advanced natural scene text detection algorithms have been proposed,but most of them run slow due to the complexity of the detection pipeline and can not be applied to industrial scenes.In this paper,we proposed a CCD based machine vision system for realtime text detection in invoice images.In this system,we applied optimizations from several aspects including the optical system,the hardware architecture,and the deep learning algorithm to improve the speed performance of the machine vision system.The experimental data confirms that the optimization methods can significantly improve the running speed of the machine vision system and make it meeting the real-time text detection requirements in industrial scenarios.

A Character Flow Framework for Multi-Oriented Scene Text Detection

Scene text detection plays a significant role in various applications,such as object recognition,document management,and visual navigation.The instance segmentation based method has been mostly used in existing research due to its advantages in dealing with multi-oriented texts.However,a large number of non-text pixels exist in the labels during the model training,leading to text mis-segmentation.In this paper,we propose a novel multi-oriented scene text detection framework,which includes two main modules:character instance segmentation(one instance corresponds to one character),and character flow construction(one character flow corresponds to one word).We use feature pyramid network(FPN)to predict character and non-character instances with arbitrary directions.A joint network of FPN and bidirectional long short-term memory(BLSTM)is developed to explore the context information among isolated characters,which are finally grouped into character flows.Extensive experiments are conducted on ICDAR2013,ICDAR2015,MSRA-TD500 and MLT datasets to demonstrate the effectiveness of our approach.The F-measures are 92.62%,88.02%,83.69%and 77.81%,respectively.

Robust Text Detection in Natural Scenes Using Text Geometry and Visual Appearance

This paper proposes a new two-phase approach to robust text detection by integrating the visual appearance and the geometric reasoning rules. In the first phase, geometric rules are used to achieve a higher recall rate. Specifically, a robust stroke width transform(RSWT) feature is proposed to better recover the stroke width by additionally considering the cross of two strokes and the continuousness of the letter border. In the second phase, a classification scheme based on visual appearance features is used to reject the false alarms while keeping the recall rate. To learn a better classifier from multiple visual appearance features, a novel classification method called double soft multiple kernel learning(DS-MKL) is proposed. DS-MKL is motivated by a novel kernel margin perspective for multiple kernel learning and can effectively suppress the influence of noisy base kernels. Comprehensive experiments on the benchmark ICDAR2005 competition dataset demonstrate the effectiveness of the proposed two-phase text detection approach over the state-of-the-art approaches by a performance gain up to 4.4% in terms of F-measure.

TextRail:复杂自然场景下的不规则文本检测算法

文本检测是文本识别的前提和基础。复杂自然场景下,受透视、遮挡、变形等因素影响,图像质量难以保证,同时图像中的文字形式丰富多样,多呈不规则形状,加上复杂背景的干扰,致使文本检测难度大、精确度低。针对文本形状不规则的场景,提出了一种文本边轨模型(TextRail),该模型基于文本上、下边界基准点表示文本区域的思想,实现对任意形状文本的高效检测。TextRail使用全卷积网络(full convolutional network,FCN)及特征金字塔网络(feature pyramid network,FPN)提取文本图像特征;将特征送入检测头网络,实现文本区域上下边界基准点的预测,将预测结果通过位置感知非极大抑制(locality-aware non-maximum suppression,LNMS)合并,得到最终的上下边界基准点;采用薄板样条插值(thin plate spline,TPS)的方法实现对不规则文本的自动矫正。通过大量的实验验证,TextRail在F1分值上优于其他文本检测模型。同时TextRail模型可以准确表示出文字的朝向、弯曲和变形情况,有效提升了不规则文本检测的准确率和鲁棒性。

BURST-LDA: A NEW TOPIC MODEL FOR DETECTING BURSTY TOPICS FROM STREAM TEXT

Topic models such as Latent Dirichlet Allocation(LDA) have been successfully applied to many text mining tasks for extracting topics embedded in corpora. However, existing topic models generally cannot discover bursty topics that experience a sudden increase during a period of time. In this paper, we propose a new topic model named Burst-LDA, which simultaneously discovers topics and reveals their burstiness through explicitly modeling each topic's burst states with a first order Markov chain and using the chain to generate the topic proportion of documents in a Logistic Normal fashion. A Gibbs sampling algorithm is developed for the posterior inference of the proposed model. Experimental results on a news data set show our model can efficiently discover bursty topics, outperforming the state-of-the-art method.