Non-text Regions Research Articles

Hybrid method for enhancement of low-resolution ancient Kannada Stone Inscription images

In this paper, we proposed the hybrid-based method for the enhancement of low-resolution Kannada Stone Inscription images. To test the performance of the proposed method, a total of 110 low-resolution samples of Kannada stone inscription images were collected from internet sources for the experimental setup due to the non-availability of the standard datasets for the Kannada stone inscriptions. The collected data set samples from the internet were complex in nature to read the contents present on stone images. The experimental workflow of the proposed method is to separate the text and non-text regions from the stone inscription images using a proposed technique for setting the coordinates. Then, the preprocessing process starts to filter out the noises and other unwanted regions found in the image foreground region using the median filtering composition method. Finally, the hybrid approach is implemented using a Fuzzy adaptive thresholding technique for the elimination of the background region of the input image and smooth enhancement of Kannada stone inscription images due to enormous challenges related to perspective distortion, diverse lighting conditions, the minimal disparity between the foreground and background, a lack of standardized text size and shape, reduced perceptible colour contrast, and associated noises. Hence, we obtained an enhancement accuracy of 78.18% using a hybrid method. The obtained accuracy is more acceptable compared to existing methods found in the global literature and is also carried out during the experimental study. The novelty of the paper is working on low-resolution ancient Kannada stone inscription images and a hybrid approach to enhance the quality of the original input image.

Utilization of relative context for text non-text region classification in offline documents using multi-scale dilated convolutional neural network

Utilization of relative context for text non-text region classification in offline documents using multi-scale dilated convolutional neural network

Complex Text Detection Algorithm Based on Edge Attention Mechanism

In computer vision, automatically identifying and locating text in images or videos is an important task. Traditional text detection methods are not effective in detecting complex scenes in irregular rectangular areas such as text bending, spacing, and special shapes, which are mainly reflected in the fragmentation of text detection areas. In this paper, a text detection method based on edge attention mechanism is proposed to better adapt to complex scenes. The proposed method takes Encoder–Decoder as the core idea. First of all, an edge attention module is designed, including global attention and local attention. The global attention module is used to perceive the features of text regions and nontext regions, while the local attention module is used to learn the information of text boundaries. Then a multi-scale feature fusion process is designed, which can strengthen the edge information and key information of text regions. Finally, the model outputs probability maps and threshold maps, and generates high-precision binary maps of text regions. After experimental verification, the proposed method on the public data set significantly reduces the fragmentation of the detection area, improves the detection accuracy of the text area, and has better robustness for text detection scenes with unconventional rectangular areas.

Segmentation-Less Extraction of Text and Non-Text Regions From JPEG 2000 Compressed Document Images Through Partial and Intelligent Decompression

JPEG 2000 is a popular image compression technique that uses Discrete Wavelet Transform (DWT) for compression and subsequently provides many rich features for efficient storage and decompression. Though compressed images are preferred for archival and communication purposes, their processing becomes difficult due to the overhead of decompression and re-compression operations which are needed as many times the data needs to operate. Therefore in this research paper, the novel idea of direct operation over the JPEG 2000 compressed documents is proposed for extracting text and non-text regions without using any segmentation algorithm. The technique avoids full decompression of the compressed document in contrast to the conventional methods, where they fully decompress and then process. Moreover, JPEG 2000 features are explored in this research work to partially and intelligently decompress only the selected regions of interest at different resolutions and bitdepths to accomplish segmentation-less extraction of text and non-text regions. Finally Maximally Stable Extremal Regions (MSER) algorithm is used to extract the layout of segmented text and non-text regions for further analysis. Experiments have been carried out on the standard PRImA Layout Analysis Dataset leading to promising results and saving computational resources.

An Effective Method for Detection and Recognition of Uyghur Texts in Images with Backgrounds

Uyghur text detection and recognition in images with simple backgrounds is still a challenging task for Uyghur image content analysis. In this paper, we propose a new effective Uyghur text detection method based on channel-enhanced MSERs and the CNN classification model. In order to extract more complete text components, a new text candidate region extraction algorithm is put forward, which is based on the channel-enhanced MSERs according to the characteristics of Uyghur text. In order to effectively prune the non-text regions, we design a CNN classification network according to the LeNet-5, which gains the description characteristics automatically and avoids the tedious and low efficiency artificial characteristic extraction work. For Uyghur text recognition in images, we improved the traditional CRNN network, and to verify its effectiveness, the networks trained on a synthetic dataset and evaluated on the text recognition datasets. The experimental results indicated that the Uyghur text detection method in this paper is robust and applicable, and the recognition result by improvedCRNN was better than the original CRNN network.

Deep features based convolutional neural network model for text and non-text region segmentation from document images

A deep convolutional neural network model is presented here which uses deep learning features for text and non-text region segmentation from document images. The key objective is to extract text regions from the complex layout document images without any prior knowledge of segmentation. In a real-world scenario, a document or magazine images contain various text information along with non-text regions such as symbols, logos, pictures, and graphics. Extraction of text regions from non-text regions is challenging. To mitigate these issues, an efficient and robust segmentation technique has been proposed in this paper. The implementation of the proposed model is divided into three phases: (a) a method for pre-processing of document images using different patch sizes is employed to handle the situations for variants of text fonts and sizes in mage; (b) a deep convolutional neural network model is proposed to predict the text or non-text or ambiguous region within the image; (c) a method for post-processing of document image is proposed to handle the situation where the image has complex ambiguous regions by utilizing the recursive partitioning of those regions into their proper classes (i.e. text or non-text) and then the system accumulates the responses of those predictive patches with varying resolutions for handling the situation of text fonts variations within the image. Extensive computer simulations have been conducted using a collection of complex layout magazine images from Google sites and the ICDAR 2015 database. Results are collected and compared with state-of-the-art methods. It reveals that the proposed model is robust and more effective as compared to state-of-the-art methods.

Urdu text in natural scene images: a new dataset and preliminary text detection.

Text detection in natural scene images for content analysis is an interesting task. The research community has seen some great developments for English/Mandarin text detection. However, Urdu text extraction in natural scene images is a task not well addressed. In this work, firstly, a new dataset is introduced for Urdu text in natural scene images. The dataset comprises of 500 standalone images acquired from real scenes. Secondly, the channel enhanced Maximally Stable Extremal Region (MSER) method is applied to extract Urdu text regions as candidates in an image. Two-stage filtering mechanism is applied to eliminate non-candidate regions. In the first stage, text and noise are classified based on their geometric properties. In the second stage, a support vector machine classifier is trained to discard non-text candidate regions. After this, text candidate regions are linked using centroid-based vertical and horizontal distances. Text lines are further analyzed by a different classifier based on HOG features to remove non-text regions. Extensive experimentation is performed on the locally developed dataset to evaluate the performance. The experimental results show good performance on test set images. The dataset will be made available for research use. To the best of our knowledge, the work is the first of its kind for the Urdu language and would provide a good dataset for free research use and serve as a baseline performance on the task of Urdu text extraction.

Text and metadata extraction from scanned Arabic documents using support vector machines

Text information in scanned documents becomes accessible only when extracted and interpreted by a text recognizer. For a recognizer to work successfully, it must have detailed location information about the regions of the document images that it is asked to analyse. It will need focus on page regions with text skipping non-text regions that include illustrations or photographs. However, text recognizers do not work as logical analyzers. Logical layout analysis automatically determines the function of a document text region, that is, it labels each region as a title, paragraph, or caption, and so on, and thus is an essential part of a document understanding system. In the past, rule-based algorithms have been used to conduct logical layout analysis, using limited size data sets. We here instead focus on supervised learning methods for logical layout analysis. We describe LABA, a system based on multiple support vector machines to perform logical Layout Analysis of scanned Books pages in Arabic. The system detects the function of a text region based on the analysis of various images features and a voting mechanism. For a baseline comparison, we implemented an older but state-of-the-art neural network method. We evaluated LABA using a data set of scanned pages from illustrated Arabic books and obtained high recall and precision values. We also found that the F-measure of LABA is higher for five of the tested six classes compared to the state-of-the-art method.

Scene Text Detection with Polygon Offsetting and Border Augmentation

Scene text localization is a very crucial step in the issue of scene text recognition. The major challenges—such as how there are various sizes, shapes, unpredictable orientations, a wide range of colors and styles, occlusion, and local and global illumination variations—make the problem different from generic object detection. Unlike existing scene text localization methods, here we present a segmentation-based text detector which can detect an arbitrary shaped scene text by using polygon offsetting, combined with the border augmentation. This technique better distinguishes contiguous and arbitrary shaped text instances from nearby non-text regions. The quantitative experimental results on public benchmarks, ICDAR2015, ICDAR2017-MLT, ICDAR2019-MLT, and Total-Text datasets demonstrate the performance and robustness of our proposed method, compared to previous approaches which have been proposed.

Directional Coherence-Based Scrolling-Text Detection for Frame Rate Up-Conversion

This article proposes a new scrolling-text detection method that uses directional coherence for frame rate up-conversion (FRUC). Most previous methods use either gradient information or motion vector (MV) distribution of the frame for scrolling-text detection. Edges can be generated by non-text components and the number of MVs to determine the scrolling-text decreases in each row of the frame. Thus, they incorrectly detect the non-text regions as scrolling-text and cannot accurately detect the start or end of text scrolling at the frame boundary. The proposed method overcomes these problems using coherence values of edge directions for each pixel and scrolling-text-aware refinement processes. The key idea of the proposed method is to use the directional coherence of edge directions and use texture patterns analysis-based refinement to improve the accuracy of the scrolling-text detection. For refinement processes, the proposed method extracts texture patterns as bit codes. Then, it computes the diversity of the texture patterns around the detected text edges. In addition, the proposed method extracts the representative value of the MV for the detected region to correct the regions falsely detected as the scrolling-text. With these refinement processes, the proposed method can also accurately detect the start or end of text scrolling at the frame boundary. In the experimental results, the proposed method increased the average F1 score to 0.504 (a 131.25% improvement) compared with previous methods. The average computation time per pixel of the proposed method also decreased to $18.571~\mu \text{s}$ (an 80.80% reduction) compared with previous methods.

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.

Realtime multi-scale scene text detection with scale-based region proposal network

Multi-scale approaches have been widely used for achieving high accuracy for scene text detection, but they usually slow down the speed of the whole system. In this paper, we propose a two-stage framework for realtime multi-scale scene text detection. The first stage employs a novel Scale-based Region Proposal Network (SRPN) which can localize text of wide scale range and estimate text scale efficiently. Based on SRPN, non-text regions are filtered out, and text region proposals are generated. Moreover, based on text scale estimation by SRPN, small or big texts in region proposals are resized into a unified normal scale range. The second stage then adopts a Fully Convolutional Network based scene text detector to localize text words from proposals of the first stage. Text detector in the second stage detects texts of narrow scale range but accurately. Since most non-text regions are eliminated through SRPN efficiently, and texts in proposals are properly scaled to avoid multi-scale pyramid processing, the whole system is quite fast. We evaluate both performance and speed of the proposed method on datasets ICDAR2015, ICDAR2013, and MSRA-TD500. On ICDAR2015, our system can reach the state-of-the-art F-measure score of 85.40% at 16.5 fps (frame per second), and competitive performance of 79.66% at 35.1 fps, either of which is more than 5 times faster than previous best methods. On ICDAR2013 and MSRA-TD500, we also achieve remarkable speedup by keeping competitive performance. Ablation experiments are also provided to demonstrate the reasonableness of our method.

Multi-level Fuzzy Based Renyi Entropy for Linguistic Classification of Texts in Natural Scene Images

This paper focuses on linguistic classification of scene texts in natural scene images. In this paper, an attempt is made to localize texts based on multi-level thresholding by fuzzy-based Renyi entropy. Complex natural scene images with diversified challenges are considered. A set of heuristic rules comprising geometric filters and stroke width transform govern the process of locating potential text regions. The scene images may contain more than one language, where text recognition by optical character recognition system becomes challenging. Manual intervention is needed to specify the language of each text. To overcome this hurdle, linguistic classification of text regions is suggested in this paper. The proposed method is validated using publicly available dataset—MSRA-TD500. Results show that fuzzy-based Renyi entropy thresholding is able to segment the foreground text from complex natural scene images. Geometric filters could capture the inherent uniformity of the text. Stroke width transform eliminates the non-text regions. The performance measures such as precision, recall and F-measures are 78%, 77% and 76%, respectively. This shows the ability of the algorithm to extract the text from the scenes. The geometric feature such as area and corner shows better variation in discriminating the linguistic texts. Further, the first three Hu moment features also contribute remarkable role in analyzing the shape of extracted text regions. The classifier based on support vector machine (SVM) yields classification accuracy of 85.45% in discriminating English and Chinese alphabets. Area under the ROC curve (AUC) is 0.851 for SVM classifier. The proposed methodology has proved its robustness against common degradations, such as uneven illumination, varying font characteristics and blurring effects. Experimental results show that our method achieves better performance in linguistic classification.

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-script text versus non-text classification of regions in scene images

Text versus non-text region classification is an essential but difficult step in scene-image analysis due to the considerable shape complexity of text and background patterns. There exists a high probability of confusion between background elements and letter parts. This paper proposes a feature-based classification of image blocks using the color autocorrelation histogram (CAH) and the scale-invariant feature transform (SIFT) algorithm, yielding a combined scale and color-invariant feature suitable for scene-text classification. For the evaluation, features were extracted from different color spaces, applying color-histogram autocorrelation. The color features are adjoined with a SIFT descriptor. Parameter tuning is performed and evaluated. For the classification, a standard nearest-neighbor (1NN) and a support-vector machine (SVM) were compared. The proposed method appears to perform robustly and is especially suitable for Asian scripts such as Kannada and Thai, where urban scene-text fonts are characterized by a high curvature and salient color variations.

Pseudo Zernike moments-based approach for text detection and localisation from lecture videos

Scene text presents challenging characteristics mainly related to acquisition circumstances and environmental changes resulting in low quality videos. In this paper, we present a scene text detection algorithm based on pseudo Zernike moments (PZMs) and stroke features from low resolution lecture videos. Algorithm mainly consists of three steps: slide detection, text detection and segmentation and non-text filtering. In lecture videos, slide region is a key object carrying almost all important information; hence slide region has to be extracted and segmented from other scene objects considered as background for later processing. Slide region detection and segmentation is done by applying pseudo Zernike moment's based on RGB frames. Text detection and extraction is performed using PZMs segmentation over V channel of HSV colour space, and then stroke feature is used to filter out non-text region and to remove false positives. The algorithm is robust to illumination, low resolution and uneven luminance from compressed videos. Effectiveness of PZM description leads to very few false positives comparing to other approached. Moreover resulting images can be used directly by OCR engines and no more processing is needed.

Study on the extraction of the text region from natural scene images by an analysis of the edge-oriented pattern

Background/Objectives: In this paper, we propose a hybrid scene-detection method using an edge and textural analysis in natural scene images, and finally, we detect the text regions by removing the non-text regions through a pattern analysis of each region.Methods/Statistical analysis: The proposed algorithm is divided into the pre-processing stage and the extraction processing stage to perform the text detection. The lost texts that are improved through a histogram equalization for the minimization of the loss of the text parts that is due to light exposure are detected before the edge detection. After that, the edge is detected using the Canny operator. The detected edge is obtained in the step of applying the SWT algorithm to detect the text candidate regions. The extraction processing step is the step of removing the noise region that is detected by the pixel analysis of the SWT algorithm, and it analyzes the pattern of the text regions and then removes the non-text regions to finally detect the text regions. For the quantitative comparison of the proposed algorithm, our results are compared with the ground-truth image using the precision, recall, and F-measure.Findings: One of the existing text-detection algorithms, the edge-based method, is problematic, as, in addition to the text, the complex backgrounds and textures are detected as the edges in natural scene images. The connected component-based method is also problematic, as the non-text region is included in the text region in the process of finding the connection component.Improvements/Applications: The proposed method shows an effective text-detection result regardless of the light exposure in natural scene images compared with the conventional text-detection algorithm.

Artificial Urdu Text Detection and Localization from Individual Video Frames

In current era of technology, information acquisition from images and videos become most important task due to the rapid development of data mining and machine learning.The information can be either textual, visual, or combination of these. Text appearing in images or videos is a significant source of information and plays a vital role to perceive it. Developing a unified method to detect the text is hard, as textual properties (i.e. font, size, color, illumination, orientation, etc.) may vary with the complex background. So far, multimedia and computer vision community unable yet to standardize any ideal approach to extract the text smoothly. In this paper, a novel method is proposed to detect and localize artificial Urdu text in individual video frames. Firstly, Sobel and Canny edge detection operators are applied to input frame and are merged with MSER (Maximally Stable Extremal Region) detected regions. Next, geometric constraints are applied to eliminate obvious non-text regions with large and small variations. Further refining of non-text regions is achieved by stroke width transform. SVM (Support Vector Machine) classifier is trained to classify text and non-text objects. Finally, bounding boxes are used to localize the text.Experimental results show that the proposed method is robust and efficient than state-of-the-art methods.

A Heuristic Approach to Detect and Localize Text on Arabic News Video

Automatic text detection in video sequences remains a challenging problem due to the variety of sizes, colors and the presence of complex background. In this paper, we attempt to solve this problem by proposing a robust detection–validation schema for text localization in Arabic news video. Candidate text regions are first detected by using a hybrid method which combines MSER detector and edge information. Then, these regions are grouped using morphological operators. Finally, a verification process is applied to remove noisy non-text regions including specific features for Arabic text. Performance and efficacy of the proposed text detection approach have been tested By using Arabic-Text-in-Video database (AcTiV-DB).

Improved Line Segmentation Framework for Sundanese Old Manuscripts

Line segmentation can be a useful process for further text segmentation. There are some certain line segmentation framework that use binarization method as an initial step. But binarization process is still facing a major challenge, especially on old document palm-leaf manuscripts. As the quality of the image has varying degrees of noises in the non-text region. Seam Carving method, one of line segmentation methods that uses binarization-free approach, can be an alternative solution. However, this method can separate the incorrect text line on small element text located at the bottom or at the top of a main character contour. Therefore, an improvement on line segmentation framework is proposed by using hybrid binarization and its implemented on the smallest energy function to separate out the text-lines. The proposed framework have been evaluated on 44 Sundanese old manuscript images that consist of true color and binary images. The evaluation matrix shows that this framework can improve Niblack binarization process up to 50%. In addition, our framework does not only generate the number of text-lines to come near to the number of target lines, but it also can separate the text-lines well on small element text. Overall, the expected result can in the end be produced from the proposed line segmentation framework.