EAST: An Efficient and Accurate Scene Text Detector

Text detection in natural scenes is fundamental for text image analysis. In this paper, we propose a context-based approach for robust and fast text detection. Our main contribution is that we introduce a new concept of key region, which is described with context according to stroke properties, appearance consistency and specific spatial distribution of text line. With such context descriptors, we adopt SVM to learn a context-based classifier to find key regions in candidate regions. Therein, candidate regions are connected components generated by local binarization algorithm in the areas, which are detected by an offline learned text patch detector. Experimental results on two benchmark datasets demonstrate that our approach has achieved competitive performances compared with the state-of-the-art algorithms including the stroke width transform (SWT) [1] and the hybrid approach based on CRFs [2] with speedup rates of about 1.7x~4.4x.

Scene texts refer to arbitrary text found in images captured by cameras in real-world settings. The tasks of text detection and recognition are critical components of computer vision, with applications spanning scene understanding, information retrieval, robotics, and autonomous driving. Despite significant advancements in deep learning methods, achieving accurate text detection and recognition in complex images remains a formidable challenge for robust real-world applications. Several factors contribute to these challenges. First, the diversity of text shapes, fonts, colors, and styles complicates detection efforts. Second, the myriad combinations of characters, often with unstable attributes, make complete detection difficult, especially when background interruptions obscure character strokes and shapes. Finally, effective coordination of multiple sub-tasks in end-to-end learning is essential for success. This research aimed to tackle these challenges by enhancing text discriminative representation. This study focused on two interconnected problems: Scene Text Recognition (STR), which involves recognizing text from scene images, and Scene Text Detection (STD), which entails simultaneously detecting and recognizing multiple texts within those images. This research focuses on implementing and evaluating the Efficient and Accurate Scene Text Detector (EAST) algorithm for text detection and recognition in natural scene images. The study aims to compare the performance of three prominent Optical Character Recognition (OCR) techniques—TesseractOCR, PaddleOCR, and EasyOCR. The EAST model was applied to a series of sample test images, and the results were visually represented with bounding boxes highlighting the detected text regions. The inference times for each image were recorded, highlighting the algorithm's efficiency, with average times of 0.446, 0.439, and 0.440 seconds for the respective test images. These results indicate that the EAST algorithm is accurate and operates in real-time, making it suitable for applications requiring immediate text recognition.

Text in images provides rich and accurate high-level semantic information, which is of great significance for many potential applications such as scene understanding, image and video retrieval. As a necessary means of understanding scene text, text detection has been widely concerned in the field of computer vision in recent years. However, due to the diversity of text scale and the uncertainty of image quality, text detection in natural scenes is still a challenging problem. Inspired by the successful application of deep neural network in target detection task, this paper proposes a text detection method based on multi-level feature extraction combined with deep learning technology. The multi-level feature extraction designed by this method can capture the details of the text, which is conducive to enhance the robustness of the algorithm to small-scale text and low-resolution images. In addition, the method is end-to-end, and can output text detection results directly. This paper evaluates the method on several standard datasets, and the experimental results prove the effectiveness of the proposed method.

Text detection in natural scenes is a current research hotspot. The Efficient and Accurate Scene Text (EAST) detector model has fast detection speed and good performance but is ineffective in detecting long text regions owing to its small receptive field. In this study, we built upon the EAST model by improving the bounding box’s shrinking algorithm to make the model more accurate in predicting short edges of text regions; altering the loss function from balanced cross-entropy to Focal loss; improving the model’s learning ability on hard, positive examples; and adding a feature enhancement module (FEM) to increase the receptive field of the EAST model and enhance its detection ability for long text regions. The improved EAST model achieved better detection results on both the ICDAR2015 dataset and the Street Sign Text Detection (SSTD) dataset proposed in this paper. The precision and F1 scores of the model also demonstrated advantages over other models on the ICDAR2015 dataset. A comparison of the text detection effects between the improved EAST model and the EAST model showed that the proposed FEM was more effective in increasing the EAST detector’s receptive field, which indicates that it can improve the detection of long text regions.

Scene Text Deblurring in Non-stationary Video Sequences

Scene text detection and recognition are vital challenging tasks in computer vision, which are to detect and recognize sequences of texts in natural scenes. Recently, researchers have investigated a lot of state-of-the-art methods to improve the accuracy and efficiency of text detection and recognition. However, there has been little research on text detection and recognition in natural scenes in Vietnam. In this paper, a deep learning-based empirical investigation of Vietnamese scene text detection and recognition is presented. Firstly, four detection models including differentiable binarization network (DBN), pyramid mask text detector (PMTD), pixel aggregation network (PAN), and Fourier contour embedding network (FCEN), are employed to detect text regions from the images. Then, four text recognition models including convolutional recurrent neural network (CRNN), self-attention text recognition network (SATRN), no-recurrence sequence-to-sequence text recognizer (NRTR), and RobustScanner (RS) are also investigated to recognize the texts. Moreover, data augmentation methods are also applied to enrich data for improving the accuracy and enhancing the performance of scene text detection and recognition. To validate the effectiveness of scene text detection and recognition models, the VinText dataset is employed for evaluation. Empirical results show that PMTD and SATRN achieve the highest scores among the others for text detection and recognition, respectively. For knowledge-sharing, our implementation is publicly available at https://github.com/ThorPham/VN_scene_text_detection_recognition.

The non-maximum suppression (NMS) algorithm, which merges neighboring bounding boxes as the detection result, is widely utilized in object detection methods. However, the traditional NMS algorithm is not suitable for text detection in natural scenes, especially for long texts and dense texts. In this paper, we observe that the coordinates of candidate bounding boxes are presented in skew distribution. On this observation, an improved NMS algorithm called SD-NMS (Skew Distribution NMS) is designed. First, the mode and the median of the coordinate set are counted to filter out the redundant bounding boxes. Then the left bounding boxes are merged for the location of the text regions. The SD-NMS method improves the detection ability of the model without extra model training and can be easily embedded in text detection methods. The experimental results show that our method obtains F-measure more than other NMS methods in public data sets ICDAR2015 and MSRATD500.

With the increasing popularity of practical vision systems and smart phones, text detection in natural scenes becomes a critical yet challenging task. Most existing methods have focused on detecting horizontal or near-horizontal texts. In this paper, we propose a system which detects texts of arbitrary orientations in natural images. Our algorithm is equipped with a two-level classification scheme and two sets of features specially designed for capturing both the intrinsic characteristics of texts. To better evaluate our algorithm and compare it with other competing algorithms, we generate a new dataset, which includes various texts in diverse real-world scenarios; we also propose a protocol for performance evaluation. Experiments on benchmark datasets and the proposed dataset demonstrate that our algorithm compares favorably with the state-of-the-art algorithms when handling horizontal texts and achieves significantly enhanced performance on texts of arbitrary orientations in complex natural scenes.

To improve text detection and text recognition in natural scenes, it is important to improve legibility by removing the effects of illumination on the image. Therefore, in this study, we present a signal enhancement method for the dark regions in the image. In addition, we propose a procedure to reduce computational complexity of the bilateral filter that is used to estimate the illumination in our method. Since our main aim is to provide the preprocessing of text detection and recognition in natural scenes, we have proposed a simple processing in which only the signals of the dark regions in the image are enhanced. Experimental results show that our method is effective in conserving the naturalness of the image and improving the legibility of texts in natural scenes. Furthermore, by using our proposed procedure, bilateral filter computation loads can be reduced by about 30%.

We propose an end-to-end system for text detection and recognition in natural scenes and consumer videos. Maximally Stable Extremal Regions which are robust to illumination and viewpoint variations are selected as text candidates. Rich shape descriptors such as Histogram of Oriented Gradients, Gabor filter, corners and geometrical features are used to represent the candidates and classified using a support vector machine. Positively labeled candidates serve as anchor regions for word formation. We then group candidate regions based on geometric and color properties to form word boundaries. To speed up the system for practical applications, we use Partial Least Squares approach for dimensionality reduction. The detected words are binarized, filtered and passed to a hidden Markov model based Optical Character Recognition (OCR) system for recognition. We show significant improvement in text detection and recognition tasks over previous approaches on a large consumer video dataset. Furthermore, the event detection system built upon the OCR output of this approach outperformed multiple other OCR-only based submissions in the recently concluded NIST TRECVID 2013 multimedia event detection evaluations.

Detecting and recognizing text in natural scene videos and images has brought more attention to computer vision researchers due to applications like robotic navigation and traffic sign detection. In addition, Optical Character Recognition (OCR) technology is applied to detect and recognize text on the license plate. It will be used in various commercial applications such as finding stolen cars, calculating parking fees, invoicing tolls, or controlling access to safety zones and aids in detecting fraud and secure data transactions in the banking industry. Much effort is required when scene text videos are in low contrast and motion blur with arbitrary orientations. Presently, text detection and recognition approaches are limited to static images like horizontal or approximately horizontal text. Detecting and recognizing text in videos with data dynamicity is more challenging because of the presence of multiple blurs caused by defocusing, motion, illumination changes, arbitrarily shaped, and occlusion. Thus, we proposed a combined DeepEAST (Deep Efficient and Accurate Scene Text Detector) and Keras OCR model to overcome these challenges in the proffered DEFUSE (Deep Fused) work. This two-combined technique detects the text regions and then deciphers the result into a machine-readable format. The proposed method has experimented with three different video datasets such as ICDAR 2015, Road Text 1K, and own video Datasets. Our results proved to be more effective with precision, recall, and F1-Score.

In this paper, we investigate the issue of class imbalance in scene text detection. Class Balanced Cross Entropy (CBCE) loss is often adopted for addressing this imbalance problem. We find that CBCE excessively restrains the backward gradients of background. Negative samples own extremely small weights which are offered by CBCE during training of text detectors. These tiny weight values lead to insufficient learning of background. As a result, the CBCE-based text detection methods only can achieve sub-optimal performance.We propose a novel loss function, Strong-Background Restrained Cross Entropy (SBRCE), to deal with the disadvantage in CBCE. Specifically, SBRCE effectively down-weights the loss assigned to the strong background which means well-classified negative samples. Our SBRCE can make training focused on all positive samples and weak background(i.e., hard-classified negative samples). Moreover, it can prevent the enormous amount of strong background from overwhelming text detectors during training. Experimental results show that the proposed SBRCE can improve the performance of the efficient and accurate scene text detector (EAST) by F-score of 3.3% on ICDAR2015 dataset and 1.12% on MSRA-TD500 dataset, without sacrificing the training and testing speed of EAST.

Text recognition in natural scene images is a challenging problem in computer vision. Different than the optical character recognition (OCR), text recognition in natural scene images is more complex due to variations in text size, colors, fonts, orientations, complex backgrounds, occlusion, illuminations and uneven lighting conditions. In this paper, we propose a segmentation-free method based on a deep convolutional recurrent neural network to solve the problem of cursive text recognition, particularly focusing on Urdu text in natural scenes. Compared to the non-cursive scripts, Urdu text recognition is more complex due to variations in the writing styles, several shapes of the same character, connected text, ligature overlapping, stretched, diagonal and condensed text. The proposed model gets a whole word image as an input without pre-segmenting into individual characters, and then transforms into the sequence of the relevant features. Our model is based on three components: a deep convolutional neural network (CNN) with shortcut connections to extract and encode the features, a recurrent neural network (RNN) to decode the convolutional features, and a connectionist temporal classification (CTC) to map the predicted sequences into the target labels. To increase the text recognition accuracy further, we explore deeper CNN architectures like VGG-16, VGG-19, ResNet-18 and ResNet-34 to extract more appropriate Urdu text features, and compare the recognition results. To conduct the experiments, a new large-scale benchmark dataset of cropped Urdu word images in natural scenes is developed. The experimental results show that the proposed deep CRNN network with shortcut connections outperform than other network architectures. The dataset is publicly available and can be downloaded from <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://data.mendeley.com/datasets/k5fz57zd9z/1</uri> .

Deep neural network (DNN) models typically have many hyperparameters that can be configured to achieve optimal performance on a particular dataset. Practitioners usually tune the hyperparameters of their DNN models by training a number of trial models with different configurations of the hyperparameters, to find the optimal hyperparameter configuration that maximizes the training accuracy or minimizes the training loss. As such hyperparameter tuning usually focuses on the model accuracy or the loss function, it is not clear and remains under-explored how the process impacts other performance properties of DNN models, such as inference latency and model size. On the other hand, standard DNN models are often large in size and computing-intensive, prohibiting them from being directly deployed in resource-bounded environments such as mobile devices and Internet of Things (IoT) devices. To tackle this problem, various model optimization techniques (e.g., pruning or quantization) are proposed to make DNN models smaller and less computing-intensive so that they are better suited for resource-bounded environments. However, it is neither clear how the model optimization techniques impact other performance properties of DNN models such as inference latency and battery consumption, nor how the model optimization techniques impact the effect of hyperparameter tuning (i.e., the compounding effect). Therefore, in this paper, we perform a comprehensive study on four representative and widely-adopted DNN models, i.e., CNN image classification , Resnet-50 , CNN text classification , and LSTM sentiment classification , to investigate how different DNN model hyperparameters affect the standard DNN models, as well as how the hyperparameter tuning combined with model optimization affect the optimized DNN models, in terms of various performance properties (e.g., inference latency or battery consumption). Our empirical results indicate that tuning specific hyperparameters has heterogeneous impact on the performance of DNN models across different models and different performance properties. In particular, although the top tuned DNN models usually have very similar accuracy, they may have significantly different performance in terms of other aspects (e.g., inference latency). We also observe that model optimization has a confounding effect on the impact of hyperparameters on DNN model performance. For example, two sets of hyperparameters may result in standard models with similar performance but their performance may become significantly different after they are optimized and deployed on the mobile device. Our findings highlight that practitioners can benefit from paying attention to a variety of performance properties and the confounding effect of model optimization when tuning and optimizing their DNN models.

Person detection is an important prerequisite of social interaction, but is not well understood. Following suggestions that people in the visual field can capture a viewer's attention, this study examines the role of the face and the body for person detection in natural scenes. We observed that viewers tend first to look at the center of a scene, and only then to fixate on a person. When a person's face was rendered invisible in scenes, bodies were detected as quickly as faces without bodies, indicating that both are equally useful for person detection. Detection was optimized when face and body could be seen, but observers preferentially fixated faces, reinforcing the notion of a prominent role for the face in social perception. These findings have implications for claims of attention capture by faces in that they demonstrate a mediating influence of body cues and general scanning principles in natural scenes.