Stroke Width Transform Research Articles

River extraction from Gaofen-1 Satellite images combined with relative total variation and stroke width transform

Extraction of rivers from remote sensing images is crucial for understanding the utilization of water resources. Because rivers have similar and consistent widths in a consistent range of remote sensing images, the stroke width transform (SWT) algorithm has a good effect on river extraction. However, the algorithm is susceptible to the influence of features around the river. A river extraction method combining relative total variation (RTV) and SWT was proposed to obtain river area information with high accuracy. First, the near-infrared channel of the image was selected as the input and the RTV model was used for texture smoothing and edge enhancement. Thereafter, the image edge map calculateds by the Canny operator was used as the input of the SWT to obtain the stroke width map. Subsequently, the connectivity components were labeled, and a specific filter was constructed according to the geometric characteristics of the river to filter out nonriver noise. The retained connected components were filled with holes, and a highly accurate river basin map was generated. In this study, six images of rivers flowing through four different landforms, including woodland, urban, mountainous, and cultivated land, were captured by the Gaofen-1 satellite for validation and comparison analysis. The experimental results demonstrated that the method’s completeness, accuracy, and extraction quality in this study could be maintained above 95%. Compared with the mainstream methods of the Otsu method, normalized difference water index, U-Net, and direct use of the SWT algorithm, the method in this study is significantly better in terms of extraction effect and algorithm stability. This can effectively improve the accuracy of river segmentation.

A Text Location Method for Sign Based on Pixel-level Gradient Ray Images and Edge Contour Mapping

Compared with deep learning methods, traditional image processing methods have lower computational costs and have advantages for typical problems such as sign text, this paper proposes a sign text location method based on pixel-level gradient ray map and edge contour mapping. First, based on image pre-processing, the pixel-level gradient ray map is obtained by using the Stroke Width Transform. Then, using the Maximally Stable Extremal Region method to locate the irregular text candidate area in the ray map. At the same time, add a mask layer to filter the irregular candidate area, and then regularize the candidate area and perform Non-Maximum Suppression processing. Finally, the background non-text candidate area is processed by extracting the mapping of the closed edge contour of the image, and the remaining text area positioning candidate frame coordinates are mapped back to the original picture. The experimental results show that the method is simple and clear, the effect is remarkable, and it has good robustness to the sign of different sizes.

Analysis of Text Identification Techniques Using Scene Text and Optical Character Recognition

In today's era, data in digitalized form is needed for faster processing and performing of all tasks. The best way to digitalize the documents is by extracting the text from them. This work of text extraction can be performed by various text identification tasks such as scene text recognition, optical character recognition, handwriting recognition, and much more. This paper presents, reviews, and analyses recent research expansion in the area of optical character recognition and scene text recognition based on various existing models such as convolutional neural network, long short-term memory, cognitive reading for image processing, maximally stable extreme regions, stroke width transformation, and achieved remarkable results up to 90.34% of F-score with benchmark datasets such as ICDAR 2013, ICDAR 2019, IIIT5k. The researchers have done outstanding work in the text recognition field. Yet, improvement in text detection in low-quality image performance is required, as text identification should not be limited to the input quality of the image.

Text Region Identification in Indian Street Scene Images Using Stroke Width Transform and Support Vector Machine

Text Region Identification in Indian Street Scene Images Using Stroke Width Transform and Support Vector Machine

An enhanced binarization framework for degraded historical document images

Binarization plays an important role in document analysis and recognition (DAR) systems. In this paper, we present our winning algorithm in ICFHR 2018 competition on handwritten document image binarization (H-DIBCO 2018), which is based on background estimation and energy minimization. First, we adopt mathematical morphological operations to estimate and compensate the document background. It uses a disk-shaped structuring element, whose radius is computed by the minimum entropy-based stroke width transform (SWT). Second, we perform Laplacian energy-based segmentation on the compensated document images. Finally, we implement post-processing to preserve text stroke connectivity and eliminate isolated noise. Experimental results indicate that the proposed method outperforms other state-of-the-art techniques on several public available benchmark datasets.

Multi-lingual scene text detection and language identification

Scene text analysis is a field of research that poses challenges to researchers owing to the background complexities, image quality, text orientation, text size, etc. The problem gets more complex when the image contains multi-lingual texts. Most scene text detection techniques approach the problem as either a feature-based or deep learning-based problem. In this work, an end-to-end system is proposed for scene text detection, localization and language identification to combine feature-based and deep learning-based approaches. The model uses Maximally Stable Extremal Regions and Stroke Width Transform for generating text proposals, followed by proposal refinement using Generative Adversarial Network. Finally, a Convolution Neural Network based model is used for language identification of the detected scene texts. Experiments have been conducted on standard datasets like KAIST, COCO, CTW1500, CVSI and ICDAR along with an in-house multi-lingual Indic scene text dataset for which the proposed model achieves satisfactory results.

Modified Sauvola binarization for degraded document images

The binarization of historical documents is a difficult job due to the presence of many degradations. Many existing local binarization techniques use certain manually adjusted parameters. The output of these techniques is much dependent on the value of these parameters. One of such parameters is window size which is kept fixed for the whole text image. The fixed window size will not be able to perform well for images having variable stroke widths and text sizes. The proposed binarization technique (Modified Sauvola) is the modification of state of art Sauvola’s binarization technique. It automatically computes window size dynamically across the image pixel to pixel using the stroke width transform (SWT). This led to reduction in number of manually adjusted parameters. The results are compared with the nine existing techniques using the quantitative measures: FM, PSNR, NRM, MPM, and DRD. The results show that the proposed method outperforms existing methods for images having variable stroke widths and text sizes.

SOLVING THE CLASSIFICATION PROBLEM OF CIRCULAR METAL OBJECTS WITH ENGRAVED CHARACTERS BY IMAGE PROCESSING METHODS

In this study, two different solution ways have been developed for the problem of classification of industrial small circular metal objects on the surfaces of engraved metal. It is the first proposed solution to perform the pattern matching with XOR operator by extract the character region of the circular metal objects as a pre-process, making the model of the Daugman’s Rubber Sheet Model (DRSM) and performing feature extraction. As a result, obtained that average processing time is 69,72 milliseconds and 0,9398 accuracy rate in the first proposed solution. The second solution is the optical character recognition (OCR) on the circular metal objects that to be realized character region detection and character segmentation as a result of the Maximal Stabil Extremal Region (MSER) and Stroke Width Transform (SWT) algorithms. Character recognition realized by using the model of Convolutional Neural Network (CNN) class which is a deep machine learning approach of artificial intelligence. The character recognition problem of the circular metal objects provided at the same time solved the problem of object classification. As a result, obtained that average processing time is 1,596 second and 0,9719 accuracy rate in the second proposed solution.

A ROAD EXTRACTION METHOD BASED ON HIGH RESOLUTION REMOTE SENSING IMAGE

Abstract. Aiming at the road extraction in high-resolution remote sensing images, the stroke width transformation algorithm is greatly affected by surrounding objects, and it is impossible to directly obtain high-precision road information. A new road extraction method combining stroke width transformation and mean drift is proposed. In order to reduce road holes and discontinuities, and preserve better edge information, the algorithm first performs denoising preprocessing by means of median filtering to the pre-processed image. Then, the mean shift algorithm is used for image segmentation. The adjacent parts of the image with similar texture and spectrum are treated as the same class, and then the fine areas less than the maximum stroke width are reduced. On the basis , the road information is extracted by the stroke width transformation algorithm, and the information also contains a small amount of interference information such as spots (non-road). In order to further improve road extraction accuracy and reduce speckle and non-road area interference, the basic operations and combinations in mathematical morphology are used to optimize it. The experimental results show that the proposed algorithm can accurately extract the roads on high-resolution remote sensing images, and the better the road features, the better the extraction effect. However, the applicability of the algorithm is greatly affected by the surrounding objects.

Application on character recognition system on road sign for visually impaired: case study approach and future

Many visually impaired people worldwide are unable to travel safely and autonomously because they are physically unable to perceive effective visual information during their daily lives. In this research, we study how to extract the character information of the road sign and transmit it to the visually impaired effectively, so they can understand easier. Experimental method is to apply the Maximally Stable External Region and Stroke Width Transform method in Phase I so that the visually impaired person can recognize the letters on the road signs. It is to convey text information to the disabled. The result of Phase I using samples of simple road signs was to extract the sign information after dividing the exact character area, but the accuracy was not good for the Hangul (Korean characters) information. The initial experimental results in the Phase II succeeded in transmitting the text information on Phase I to the visually impaired. In the future, it will be required to develop a wearable character recognition system that can be attached to the visually impaired. In order to perform this task, we need to develop and verify a miniaturized and wearable character recognition system. In this paper, we examined the method of recognizing road sign characters on the road and presented a possibility that may be applicable to our final development.

Multi-Oriented Text Detection in Natural Scene Images Based on the Intersection of MSER With the Locally Binarized Image

Abstract The problem of text extraction is an interesting area of research in computer vision domain. In the recent years, emergence of various applications on smart hand-held devices such as translation of text from one language to another in real time, computerized aid for visually impaired, user navigation & traffic monitoring and driving assistance systems, has stimulated the renewed research interest in this domain. Retrieving text directly from natural scene images or videos is a challenging task due to variant patterns and orientations of scene text. Although various research investigations are available on horizontal oriented text detection in natural scene images, a little number of studies exist on text detection of multiple orientations. In this article, a robust method has been proposed for scene text detection having multiple orientations. The text in the images are horizontally, non-horizontally and curve oriented. The proposed method contains two main stages—maximally stable extremal region (MSER) computation and stroke width transformation (SWT). MSERs have been used to detect maximally stable extremal regions in the images. It is followed by implementing Canny edge detector for enhancement of edges in the images. To remove the non-text regions in the images, the combination of SWT image and geometric information has been used. The performance of the proposed method has been assessed on the IITR text datasets and it produces very encouraging results.

An Advanced Road Structure Image Segmentation Method using Swt in Cnn

In this paper, the design of advanced road structure image segmentation approach using stroke width transformation (SWT) in convolution neural network (CNN) is proposed. The main intent of the proposed system is to acquire the aerial images for the vehicle. Basically, this image segmentation performs its operation in two forms they are operating phase and learning phase. Here the aerial image has enhanced by using the SWT transformation. Hence the main advantage of this proposes system is that it processes the entire operation in simple way with high speed. The SWT will capture the images of road areas in effective way. Hence the propose system has various features which will determine the color, width and many other.

Detection, Localization of Text in Images by Mser and Enhanced Swt

The number digital images and digital videos has raised highly. The text shows in the images is major thing for fully understanding the images. So it is very signifigant to recognize the text. First step of text recognization system is known as text detection. But detecting text from images is very challenging and it is receiving high amount of concentration. Text detection is improved by pre-procssing techniques like noise removal, contrast changes and etc. Recently MSER (Maximally Stable Edge Region) and SWT (Stroke Width Transformation) methods are used seperately or combined with each other for detecting and localizing text. This paper analyzes and compares technical challenges and performance of above methods and take in new and fast method for text detection and localization. The proposed method comprises an enhanced technique based on SWT which combined with MSER. The proposed method detect wording which is located in differnt directions, different angle and combined letters. Performance of exisisting and proposed methods on road signal images depicted in experimental results.

Text Detection in Natural Image By Connected Component Labeling

The process of detect the text from the natural image is complex and difficult process because the variance by the devises that take the images and different the texts that found in images in the orientation, size and style. Given the importance the texts in images in the several of application of computer vision. In this paper dependent on the spatial natural images and on the spatial data set for the street sign that include the texts by the different size and different orientation. In this paper detected the texts in images by using robust method by using several algorithms, at the first stage making preprocessing for the image to blur the image and reduce the nose on it by Gaussian blur, second stage making processing that include canny edge detection to detect the edges and dilation, third stage applying connected component to filling all objects in image then applying stroke width transform(SWT) to detect the letter candidate and applying the system on the several images that include different types of texts.

An Enhanced MSER Pruning Algorithm for Detection and Localization of Bangla Texts from Scene Images

Text detection and localization have great importance for content based image analysis and text based image indexing. The efficiency of text recognition depends on the efficiency of text localization. So, the main goal of the proposed method is to detect and localize text regions with high accuracy. To achieve this goal, a new and efficient method has been introduced for localization of Bangla text from scene images. In order to improve precision and recall as well as f-measure, Maximally Stable Extremal Region (MSER) based method along with double filtering techniques have been used. As MSER algorithm generates many false positives, we have introduced double filtering method for removing these false positives to increase the f-measure to a great extent. Our proposed method works at three basic levels. Firstly, MSER regions are generated from the input color image by converting it into gray scale image. Secondly, some heuristic features are used to filter out most of the false positives or non-text regions. Lastly, Stroke Width Transform (SWT) based filtering method is used to filter out remaining non-text regions. Remaining components are then grouped into candidate text regions marked by bounding box over each region. As there is no benchmark database for Bangla text, the proposed method is implemented on our own prepared database consisting of 200 scene images of Bangla texts and has got prominent performance. To evaluate the performance of our proposed approach, we have also tested the proposed method on International Conference on Document Analysis and Recognition( ICDAR) 2013 benchmark database and have got a better result than the related existing methods.

Multi-Lingual Scene Text Detection Using One-Class Classifier

The main purpose of scene text recognition is to detect texts in a given image. The problem of text detection and recognition in such images has gained great attention in recent years due to rising demand of several applications like visual based applications, multimedia and content-based retrieval. Due to low accuracies of existing scene text detection methods, an improved pipeline is developed for text localizing task. First, candidate text regions are generated using Maximally Stable Extremal Region and Stroke Width Transform methods that capture true positives along with many false positives. A One Class Classifier is trained to label the candidate regions obtained, as text or non-text, which in this case is suitable as non-text class cannot be adequately represented to train a binary classifier. The one class classifier is trained with some popular feature descriptors like Histogram of Oriented Gradients, Grey Level Co-Occurrence Matrix, Discrete Cosine Transform and Gabor filter. Experimental results show high recall for text containing regions and reducing false positives.

Text detection in natural scene images based on color prior guided MSER

Abstract In this paper, we focus on text detection in natural scene images which is conducive to content-based wild image analysis and understanding. This task is still an open problem and usually includes two key issues: text candidate extraction and verification. For text candidate extraction, we introduce a color prior to guide the character candidate extraction by Maximally Stable Extremal Region (MSER). The principle of color prior acquirement is to obtain stroke-like textures with modified Stroke Width Transform (SWT), which is based on segmented edges. For text verification, the ideology of deep learning is adopted to distinguish text/non-text candidates. To improve classification accuracy, the results of specific task CNNs are fused. The proposed framework is evaluated on the ICDAR 2013 Robust Reading Competition database. It achieves F-score at 85.87%, which are superior over several state-of-the-art text detection methods.

Visual substitution system for room labels identification based on text detection and recognition

Vision is an essential human sense which is playing the most important role in human perception about surrounding environment. However such information is generally inaccessible for blind people. In order to enable these persons to overcome such incapability, we propose a system for identifying the neighbouring scene. In fact, the environment is labelled as a first step and then we present a personalised and adaptive method for labels detection and recognition. The automatic analysis involves the detection of personalised markers employed to extract the region of interest followed by the perspectives rectification based on homography estimation. We use the stroke width transform (SWT) to extract the text from the detected label and crop it into words and letters. The extracted text is identified using images correlation. Finally, as a substitution for visual modality, a vocal transformation of the recognised text is performed.

Deteksi Teks Secara Otomatis Pada Natural Image Berbasis Superpixel Menggunakan Maximally Stable Extremal Regions dan Stroke Width Transform

Text detection in natural image is something to do before performing character recognition. The process of text detection plays an important role in the acquisition of information in an image. This research aims to detect text automatically in natural image based on superpixels with Maximally Stable Extremal Regions (MSER) and Stroke Width Transform (SWT). The superpixel method used is Simple Linear Iterative Clustering (SLIC). The SLIC method is used for segmenting text images into superpixel spaces. Image segmentation to superpixel aims to group pixels into homogeneous regions that capture redundant images. SLIC is a technique that effectively divides images into homogeneous regions (superpixels). Furthermore MSER is used as a feature to locate the text candidate region in a segmented image with superpixel. Then edge detection is done to validate the text area that has been found. Next, the SWT method is used to distinguish both text and non-text image regions. The dataset used is ICDAR 2003. Based on test result, MSER with superpixel is able to detect region of text in natural image. SWT is also able to recover the region which is the candidate of the text in natural image.

On Detecting Road Regions in a Single UAV Image

Automatic detection of road regions in aerial images remains a challenging research topic. Most existing approaches work well on the requirement of users to provide some seedlike points/strokes in the road area as the initial location of road regions, or detecting particular roads such as well-paved roads or straight roads. This paper presents a fully automatic approach that can detect generic roads from a single unmanned aerial vehicles (UAV) image. The proposed method consists of two major components: automatic generation of road/nonroad seeds and seeded segmentation of road areas. To know where roads probably are (i.e., road seeds), a distinct road feature is proposed based on the stroke width transformation (SWT) of road image. To the best of our knowledge, it is the first time to introduce SWT as road features, which show the effectiveness on capturing road areas in images in our experiments. Different road features, including the SWT-based geometry information, colors, and width, are then combined to classify road candidates. Based on the candidates, a Gaussian mixture model is built to produce road seeds and background seeds. Finally, starting from these road and background seeds, a convex active contour model segmentation is proposed to extract whole road regions. Experimental results on varieties of UAV images demonstrate the effectiveness of the proposed method. Comparison with existing techniques shows the robustness and accuracy of our method to different roads.