Recognizing Text-Based Traffic Signs

License plate recognition is currently used in various situations, such as parking lot vehicle management and the tracking of wanted vehicles. These applications require recognition from all possible camera angles. Therefore, we propose a method for license plate recognition in images captured from various camera angles. First, the license plate area is detected from the input image using the YOLOv5 object detection method. The subsequent process can be performed in two manners: by rotating the license plate to the front using projective transformation and trapezoidal correction, or by using graph matching. The first method performs Hough transforms or linear approximations as preprocessing, and then calculates the rectangle surrounding the license plate from the YOLOv5 output. After performing trapezoidal correction, the maximally stable extremal regions (MSER) are used to detect character candidates, and characters are recognized using 3D rotated character recognition. The second method performs character candidate detection and recognition without trapezoidal correction, followed by graph matching. These methods are versatile because they do not depend on the layout of license plates, which varies among countries and regions. Two types of datasets were used: a set of images containing Japanese license plates collected by ourselves, and a set of publicly available images containing Taiwanese license plates. Two recognition rates were evaluated: the license plate character recognition rate and license plate recognition rate in which all characters in one plate are recognized. The license plate character recognition rates using graph matching were 91.9% for the Japanese license plates and 89.3% for the Taiwanese license plates. The license plate recognition rates were 84.0% and 84.5%, respectively.

The generation of text proposals (i.e. local candidate regions most likely containing textual components) is one critical and prerequisite step in scene text detection task. As one popular text proposal algorithm, the Maximally Stable Extremal Region (MSER), has been exploited by many successful text detection methods, while on the other hand has difficulties in handling complicated scene text involving touching characters and characters composed of multiple unconnected parts (e.g. Chinese characters and text in dot matrix fonts). In this paper, we propose a novel text proposal method for localizing text in natural images, which integrates the MSER algorithm with the multi-scale sliding window framework and efficiently extracts Windowed Maximally Stable Extremal Regions (WMSERs) as text proposals. We further present effective proposal filtering and grouping algorithms for exploiting WMSER-based proposals in text detection task. Experiments on public scene text datasets demonstrate the promising aspects of the proposed method in dealing with complicated scene text.

In this paper a novel robust algorithm that extracts text from signage images is proposed. Existing methods are constructed to work on certain limitations, as detecting text under perfect lightning conditions. Maximally Stable Extremal Regions (MSER) detector is used to extract text areas because it shows better performance to lightning conditions. To enhance the MSER regions, novel enhancement technique is used by combining edge detection algorithm. Enhance edge image is then put to the stroke width detection algorithm. Based on stroke width information, connected components are obtained. Afterwards connected components are filtered to remove non text pixels. Text recognition is not touched by this algorithm and resulted binary image can be used on any text recognition algorithm. This algorithm shows best performance on light effected text images and noisy images.

As an important information carrier, texts play significant roles in many applications. However, text detection in unconstrained scenes is a challenging problem due to cluttered backgrounds, various appearances, uneven illumination, etc.. In this paper, an approach based on multi-channel information and local context is proposed to detect texts in natural scenes. According to character candidate detection plays a vital role in text detection system, Maximally Stable Extremal Regions(MSERs) and Graph-cut based method are integrated to obtain the character candidates by leveraging the multi-channel image information. A cascaded false positive elimination mechanism are constructed from the perspective of the character and the text line respectively. Since the local context information is very valuable for us, these information is utilized to retrieve the missing characters for boosting the text detection performance. Experimental results on two benchmark datasets, i.e., the ICDAR 2011 dataset and the ICDAR 2013 dataset, demonstrate that the proposed method have achieved the state-of-the-art performance.

Multimedia files such as images and videos contain most of the textual information, which is an important route for people to obtain information. Therefore, the automatic detection and recognition of text has been becoming more and more popular topic in computer vision and document analysis. Aiming at the problem of scene text detection and recognition, this paper introduces a variety of text detection methods. It focusses on the use of machine learning for text detection and compares these methods. Then, there is a brief introduction for text recognition and some standard datasets. Finally, some valuable research topics in this field are proposed and summarized.

This paper presents the method to classify the speed limit traffic sign using multiple features, namely histogram of oriented gradient (HOG) and maximally stable extremal regions (MSER) features. The classification process is divided into the outer circular ring matching and the inner part matching. The HOG feature is employed to match the outer circular ring of the sign, while MSER feature is employed to extract the digit number in the inner part of the sign. Both features are extracted from the grayscale image. The algorithm detects the rotation angle of the sign by analyzing the blobs which is extracted using MSER. In the matching process, tested images are matched with the standard reference images by calculating the Euclidean distance. The experimental results show that the proposed method for matching the outer circular ring works properly to recognize the circular sign. Further, the digit number matching achieves the high classification rate of 93.67% for classifying the normal and rotated speed limit signs. The total execution time for classifying six types of speed limit sign is 10.75 ms.

Food object recognition has gained popularity in recent years. This can perhaps be attributed to its potential applications in fields such as nutrition and fitness. Recognizing food images however is a challenging task since various foods come in many shapes and sizes. Besides having unexpected deformities and texture, food images are also captured in differing lighting conditions and camera viewpoints. From a computer vision perspective, using global image features to train a supervised classifier might be unsuitable due to the complex nature of the food images. Local features on the other hand seem the better alternative since they are able to capture minute intricacies such as interest points and other intricate information. In this paper, two local features namely SURF (Speeded- Up Robust Feature) and MSER (Maximally Stable Extremal Regions) are investigated for food object recognition. Both features are computationally inexpensive and have shown to be effective local descriptors for complex images. Specifically, each feature is firstly evaluated separately. This is followed by feature fusion to observe whether a combined representation could better represent food images. Experimental evaluations using a Support Vector Machine classifier shows that feature fusion generates better recognition accuracy at 86.6%.

The article presents a method of recognizing alphanumeric characters located in the image, based on a previously created database of patterns using neural networks. For this purpose the convolutional networks were used, which independently search for features that allow to distinguish characters in the image. A larger number of convolution layers allows us to recognize a greater number of features and thus to increase the probability of correctly recognized characters. The main purpose of the paper is to present software that recognizes the alphanumeric characters in images and to investigate the impact of the size of this database on the program's speed and character recognition efficiency. This software can also be used in more complex structures, such as automatic translators or as a computer reader. The calculation of the first program that recognizes single character and the second program that reads all the text from the image have been made in the MATLAB environment. The paper describes the components of this software, such as the learning subsystem and the character recognition subsystem. The results of the program were presented in the form of screenshots showing the results of the learning process and character recognition process. The speed of the software and the effectiveness of recognizing alphanumeric characters using the artificial neural networks and maximally stable extremal regions (MSER) algorithm are presented in the table and figures. Attention was also paid to the impact of the size of the database used to learn the network on the speed of calculations and recognition efficiency.

Robust text detection via multi-degree of sharpening and blurring

Nowadays most of the information is stored in images and there is a need to convert this information into an editable format. The objective of this paper includes the development of a user-friendly tool to extract text from the video or to recognize well-written handwriting in a scanned document to an editable form. The proposed methodology is robust and can provide high-grade performance with layout distortion. The explication utilizes modalities like Optical Character Recognition (OCR), Artificial Neural Networks (ANN), Deep Learning and Maximally Stable Extremal Regions (MSER) techniques for text detection. The video extraction can be attained by using video to frame conversion and then to use the Structural Similarity Index Measure (SSIM). The prototype is developed using MATLAB and provided with a GUI, which is deployable on a workstation. The generated GUI is employed to define Region of Interest (ROI), specify the required text layout, highlighting the specific portions of the image, select the appropriate language and also export the text to a word document or notepad applications where it can be edited.

Could scene context be beneficial for scene text detection?

info:eu-repo/semantics/published

One of the intelligent transportation system's critical tasks is to understand traffic signs and convey traffic information to humans. However, most related works are focused on the detection and recognition of traffic sign texts or symbols, which is not sufficient for understanding. Besides, there has been no public dataset for traffic sign understanding research. Our work takes the first step towards addressing this problem. First, we propose a "CASIA-Tencent Chinese Traffic Sign Understanding Dataset" (CTSU Dataset), which contains 5000 images of traffic signs with rich semantic descriptions. Second, we introduce a novel multi-task learning architecture that extracts text and symbol information from traffic signs, reasons the relationship between texts and symbols, classifies signs into different categories, and finally, composes the descriptions of the signs. Experiments show that the task of traffic sign understanding is achievable, and our architecture demonstrates state-of-the-art and superior performance. The CTSU Dataset is available at http://www.nlpr.ia.ac.cn/databases/CASIA-Tencent%20CTSU/index.html.

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.

Automatic detection and recognition of traffic sign has been a topic of great interest in advanced driver assistance system. It enhances vehicle and driver safety by providing the condition and state of the road to the drivers. However, visual occlusion and ambiguities in the real-world scenario make the traffic sign recognition a challenging task. This paper presents an Automatic Traffic Sign Detection and Recognition (ATSDR) system, involving three modules: segmentation, detection, and recognition. Region of Interest (ROI) is extracted using multiple thresholding schemes with a novel environmental selection strategy. Then, the traffic sign detection is carried out using correlation computation between log-polar mapped inner regions and the reference template. Finally, recognition is performed using Support Vector Machine (SVM) classifier. Our proposed system achieved a recognition accuracy of 98.3 % and the experimental results demonstrates the robustness of traffic sign detection and recognition in real-world scenario.