CPN: Complementary Proposal Network for Unconstrained 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.

With the development of deep learning, the use of neural network for text detection has been more in-depth research and more widely used. Based on this, this paper studies the Chinese text event detection technology based on improved neural network. In the research, this paper uses the flower pollination algorithm (FPA) to improve the traditional BP neural network algorithm. By optimizing the weights and thresholds of BP neural network, a Chinese text event detection method based on improved neural network is proposed. In order to verify the effect of the Chinese text event detection method based on improved neural network, this paper compares it with the natural scene text detection method, and compares the recall rate, accuracy rate and time-consuming. The results show that the accuracy rate of the natural scene text detection method is 88%, and the recall rate is 73%. The accuracy rate of the text detection method based on the improved neural network is 95% and the recall rate is 86%. The F value of the natural scene text detection method in the Chinese text event detection test is 0.79, which takes 4.56s The value of F in is 0.90, which takes 0.64s. Therefore, the Chinese text event detection method based on improved neural network has better performance.

Text detection and recognition in scene images and videos attract much attention in computer vision recently. However, most existing text detection and recognition methods only focus on static images. In this paper an end-to-end scene text recognition method based on multi frame tracking is proposed for text in videos, in which temporal information is employed to improve performance. First, an end-to-end text recognition method based on a unified deep neural network is used to detect and recognize text in each frame of the input video. Then, multi frame text tracking is employed through associations of texts in current frame and several previous frames to obtain final results. Experiments on ICDAR datasets demonstrate that the proposed method outperforms the state-of-the-art methods in end-to-end video text recognition.

Visually impaired people suffer daily from their disability to read textual information. One of the most anticipated blind-assistive devices is a system equipped with a wearable camera capable of finding the textual information in natural scenes and translating it into sound through a speech synthesizer. To avoid duplicate readings, the device should be able to recognize text areas with the same content, and group them to obtain a single result. Scene text detection and tracking methods attract a lot of interest for these purposes. However, this field is still challenging and methods of scene text detection and tracking are yet to be perfected. This paper proposes a scene text tracking system capable of finding text regions and tracking them in video frames captured by a wearable camera. By combining a text detection method with a feature point tracker, we obtain a robust text tracker which produces much less false positive text images at 2.9 times faster speed compared with the conventional method.

With the rapid development of industries such as nuclear power and shipbuilding, radiographic testing (RT) is widely used in these fields as an important means of weld inspection. It also produces a large number of radiographic films, which consume a great deal of manpower and material resources. It is therefore beneficial for the radiographic film to be digitised for storage and archiving. Text detection in RT weld images is an important prerequisite for the archiving of digitised films. This paper proposes a novel text detection method that employs mask convolution and frequency-domain filtering, which can detect text at different positions, with different fonts and of different sizes in RT weld images. The method is evaluated using 366 different images and shows significant efficacy for text detection in RT weld images, with the precision value reaching 96%. The method used in this paper is also compared with other methods that are commonly used in other fields and the results show that the proposed method gives improved results compared to state-of-the-art methods.

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.

Developing assisting system of handicapped persons become a challenging ask in research projects. Recently, a variety of tools are designed to help visually impaired or blind people object as a visual substitution system. The majority of these tools are based on the conversion of input information into auditory or tactile sensory information. Furthermore, object recognition and text retrieval are exploited in the visual substitution systems. Text detection and recognition provides the description of the surrounding environments, so that the blind person can readily recognize the scene. In this work, we aim to introduce a method for detecting and recognizing text in indoor scene. The process consists on the detection of the regions of interest that should contain the text using the connected component. Then, the text detection is provided by employing the images correlation. This component of an assistive blind person should be simple, so that the users are able to obtain the most informative feedback within the shortest time.

Buffer-text: Detecting arbitrary shaped text in natural scene image

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.

We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our proposed model is designed to perform noise reduction and text region enhancement as well as text detection. Moreover, we enrich the training data for the model with synthesized document images that are fully labeled for text detection and enhancement, thus overcome the insufficiency of labeled document image data. For the effective exploitation of the synthetic and real data, the training process is separated in two phases. The first phase is training only synthetic data in a fully-supervised manner. Then real data with only detection labels are added in the second phase. The enhancement task for the real data is weakly-supervised with information from their detection labels. Our methods are demonstrated in a real document dataset with performances exceeding those of other text detection methods. Moreover, ablations are conducted and the results confirm the effectiveness of the synthetic data, auxiliary task, and weak-supervision. Whereas the existing text detection studies mostly focus on the text in scenes, our proposed method is optimized to the applications for the text in scanned documents.

A coarse-to-fine scene text detection method based on Skeleton-cut detector and Binary-Tree-Search based rectification

Text detection in natural scene images is a challenging problem in computer vision. To robust detect various texts in complex scenes, a hierarchical recursive text detection method is proposed in this paper. Usually, texts in natural scenes are not alone and arranged into lines for easy reading. To find all possible text lines in an image, candidate text lines are obtained using text edge box and conventional neural network at first. Then, to accurately find out the true text lines in the image, these candidate text lines are analyzed in a hierarchical recursive architecture. For each of them, connected components segmentation and hierarchical random field based analysis are recursively employed until the detected text line no more changes. Now the detected text lines are output as the text detection result. Experiments on ICDAR 2003 dataset, ICDAR 2013 dataset and Street View Dataset show that the hierarchical recursive architecture can improve text detection performance and the proposed method achieves the state-of-art in scene text detection.

In this paper, we propose a new method for natural image text detection under a weakly supervised data set. Currently, most of the text detection models are based on bounding box label training data. However, the cost of the bounding box label training data is very high. In order to solve this problem, we propose an attention mechanism that can be trained on image-level labels data and roughly identifies text regions via an automatically learned attentional map based on a convolutional neural network. There are three main steps: firstly, a VGG model is trained using image-level labels data to score the likelihood that a text region exists in the picture; secondly, the region of interest is extracted by means of the attention mechanism and the extracted region is evaluated using the network trained in the first step to getting the text region and finally, the text line is extracted in the text region using the MSER algorithm. Trained with the weakly supervised data which is only with image-level labels, our model can generate bounding boxes for the text line in the image. The results of our model are very close to those of the models using bounding box label training data on the text detection benchmark sets of MSRA-TD500, ICDAR2013, and ICDAR2015.

A method of text detection in natural images, to be turned into an effective embedded software on a mobile device, shall be both efficient and lightweight. We observed that a simple method based on the morphological Laplace operator is very appropriate: we can construct in quasi-linear time a hierarchical image decomposition/simplification based on its 0-crossings, and search for some text in the resulting tree. Yet, for this decomposition to be sound, we need “0-crossings” to be Jordan curves, and to that aim, we rely on some discrete topology tools. Eventually, the hierarchical representation is the morphological tree of shapes of the Laplacian sign (ToSL). Moreover, we provide an algorithm with linear time complexity to compute this representation. We expect that the proposed hierarchical representation can be useful in some applications other than text detection.

To detect text from an image with a different background, an adaptive text detection method based on image complexity analysis is proposed. Before text detection, this approach adopts an image complexity analysis step to classify image complexity into three categories: low complexity, middle complexity and high complexity. Then images with different complexity adopt different methods to extract image edges. The proposed text detection method takes a coarse to fine detection strategy which combines the edge-based method, connected component based method and the texture based method into a framework. Experimental results demonstrate the performance of the proposed method.