Non-text Regions Research Articles

Textline detection in degraded historical document images

This paper presents a textline detection method for degraded historical documents. Our method follows a conventional two-step procedure that the binarization is first performed and then the textlines are extracted from the binary image. In order to address the challenges in historical documents such as document degradation, structure noise, and skews, we develop new methods for the binarization and textline extraction. First, we improve the performance of binarization by detecting the non-text regions and processing only text regions. We also improve the textline detection method by extracting main textblock and compensating the skew angle and writing style. Experimental results show that the proposed method yields the state-of-the-art performance for several datasets.

Image based book cover recognition and retrieval

In this we are developing a graphical user interface using MATLAB for the users to check the information related to books in real time. We are taking the photos of the book cover using GUI, then by using MSER algorithm it will automatically detect all the features from the input image, after this it will filter bifurcate non-text features which will be based on morphological difference between text and non-text regions. We implemented a text character alignment algorithm which will improve the accuracy of the original text detection. We will also have a look upon the built in MATLAB OCR recognition algorithm and an open source OCR which is commonly used to perform better detection results, post detection algorithm is implemented and natural language processing to perform word correction and false detection inhibition. Finally, the detection result will be linked to internet to perform online matching. More than 86% accuracy can be obtained by this algorithm.

Scene text detection via extremal region based double threshold convolutional network classification.

In this paper, we present a robust text detection approach in natural images which is based on region proposal mechanism. A powerful low-level detector named saliency enhanced-MSER extended from the widely-used MSER is proposed by incorporating saliency detection methods, which ensures a high recall rate. Given a natural image, character candidates are extracted from three channels in a perception-based illumination invariant color space by saliency-enhanced MSER algorithm. A discriminative convolutional neural network (CNN) is jointly trained with multi-level information including pixel-level and character-level information as character candidate classifier. Each image patch is classified as strong text, weak text and non-text by double threshold filtering instead of conventional one-step classification, leveraging confident scores obtained via CNN. To further prune non-text regions, we develop a recursive neighborhood search algorithm to track credible texts from weak text set. Finally, characters are grouped into text lines using heuristic features such as spatial location, size, color, and stroke width. We compare our approach with several state-of-the-art methods, and experiments show that our method achieves competitive performance on public datasets ICDAR 2011 and ICDAR 2013.

Accurate segmentation of complex document image using digital shearlet transform with neutrosophic set as uncertainty handling tool

In any image segmentation problem, there exist uncertainties. These uncertainties occur from gray level and spatial ambiguities in an image. As a result, accurate segmentation of text regions from non-text regions (graphics/images) in mixed and complex documents is a fairly difficult problem. In this paper, we propose a novel text region segmentation method based on digital shearlet transform (DST). The method is capable of handling the uncertainties arising in the segmentation process. To capture the anisotropic features of the text regions, the proposed method uses the DST coefficients as input features to a segmentation process block. This block is designed using the neutrosophic set (NS) for management of the uncertainty in the process. The proposed method is experimentally verified extensively and the performance is compared with that of some state-of-the-art techniques both quantitatively and qualitatively using benchmark dataset.

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.

Automatic video superimposed text detection based on Nonsubsampled Contourlet Transform

Compared with other video semantic clues, such as gestures, motions etc., video text generally provides highly useful and fairly precise semantic information, the analysis of which can to a great extent facilitate video and scene understanding. It can be observed that the video texts show stronger edges. The Nonsubsampled Contourlet Transform (NSCT) is a fully shift-invariant, multi-scale, and multi-direction expansion, which can preserve the edge/silhouette of the text characters well. Therefore, in this paper, a new approach has been proposed to detect video text based on NSCT. First of all, the 8 directional coefficients of NSCT are combined to build the directional edge map (DEM), which can keep the horizontal, vertical and diagonal edge features and suppress other directional edge features. Then various directional pixels of DEM are integrated into a whole binary image (BE). Based on the BE, text frame classification is carried out to determine whether the video frames contain the text lines. Finally, text detection based on the BE is performed on consecutive frames to discriminate the video text from non-text regions. Experimental evaluations based on our collected TV videos data set demonstrate that our method significantly outperforms the other 3 video text detection algorithms in both detection speed and accuracy, especially when there are challenges such as video text with various sizes, languages, colors, fonts, short or long text lines.

A cascaded method for text detection in natural scene images

In this paper, a novel image operator is proposed to detect and locate text in scene images. To achieve a high recall of character detection, extremal regions are detected as character candidates. Two classifiers are trained to identify characters, and a recursive local search algorithm is proposed to extract characters that are wrongly identified by the classifiers. An efficient pruning method, which combines component trees and recognition results, is proposed to prune repeating components. A cascaded method combines text line entropy with a Convolutional Neural Network model. It is used to verify text candidates, which reduces the number of non-text regions. The proposed technique is test on three public datasets, i.e. ICDAR2011 dataset, ICDAR2013 dataset and ICDAR2015 dataset. The experimental results show that our approach achieves state-of-the-art performance.

Fast Image Embedded Chinese Text Extracting by Homogeneous Space Mapping

Text-embedded images are popular in the mobile Internet to spread malicious information. A fast text-embedded image Chinese text extracting algorithm based on homogeneous space mapping is proposed. Image enhancement functions are used to highlight edge and texture features of images. Sobel operator is used to extract the edge feature and wavelet packet is used to extract the 24-dimensional texture feature vectors in the enhanced images. The texture features and edge features are used to describe the homogeneity of an image, which construct the homogeneous feature map of the image. The differences between the non-text and the text region homogeneity are used to distinguish them and reduce non-text region further. Thus the text regions are highlighted. Then, homogeneous text samples are used to train the text region detector, which greatly reduces the computational complexity. Finally, the characters are segmented and recognized. Some experiments to verify the validity and practicability of the proposed algorithm have been conducted. The recognition rate achieves 86%, which is higher than that of other methods in industry. The algorithm is verified on the operator's malicious information monitoring system, which provides secure malicious filtering performance.

Wavelet transform based technique for text image localization

In this paper, a robust technique based on discrete wavelet transform, edge detection, and morphology operation for scene text detection is proposed. There are several stages in the proposed method. In the first stage, a single wavelet decomposition LH, HL and HH subbands are applied for detecting edges in original scene text image. The projection technique is applied in the second stage to preliminary detect text and non-text pixels. In third stage, 4-connected components are applied, and then area geometric feature is used as threshold to remove non-text region. At last stage, morphological operations are applied to connect isolated text components and to remove non-text regions. The proposed method is applied on a various images such as images of low contrast, complex background images and images of different fonts and size of text. The experimental results show that the proposed method can detect regions of the text perfectly.

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.

A New Approach to Extract Text from Images based on DWT and K-means Clustering

AbstractText present in image provides important information for automatic annotation, indexing and retrieval. Therefore, its extraction is a well known research area in computer vision. However, variations of text due to differences in orientation, alignment, font, size, low image contrast and complex background make the problem of text extraction extremely challenging. In this paper, we propose a texture-based text extraction method using DWT with K-means clustering. First, the edges are detected from image by using DWT. Then, a small size overlapped sliding window is used to scan high frequency component sub-bands from which texture features of text and non-text regions are extracted. Based on these features, K-means clustering is employed to classify the image into text, simple background and complex background clusters. Finally, voting decision process and area based filtering are used to locate text regions exactly. Experimentation is carried out using public dataset ICDAR 2013 and our own dataset f...

An automatic video text detection method based on BP-adaboost

Video text usually provides us a lot of useful information that is important for video analysis, indexing and retrieval. However, it is still a challenging work to detect text from video images due to variation of text patterns and complexity of background. In this paper, an automatic video text detection method is proposed. Firstly, K-means is utilized to classify pixels in gradient images into text and non-text regions. Subsequently, morphological operations are performed on text regions to form connected candidate text components, followed by projection profile boundary refinement. Finally, the detection results are verified by geometry and BP-Adaboost identifications. The experimental results on our manually selected dataset and the publicly available Microsoft Asia dataset show the effectiveness and feasibility of the proposed method.

An Effective Edge and Texture Based Approach towards Curved Videotext Detection and Extraction

In present day video text greatly helps video indexing and retrieval system as they often carry significant semantic information. Video text analysis is challenging due to varying background, multiple orientations and low contrast between text and non-text regions. Proposed approach explores a new framework for curved video text detection and recognition where from the observation that curve text regions can be well defined by edges size and uniform texture, Probable curved text edge detection is accomplished by processing wavelet sub bands followed by text localization by utilizing fast texture descriptor LU-transform. Binarization is achieved by maximal H-transform. A Connected Component filtering method followed by B-Spline curve fitting on centroid of each character vertically aligns each oriented character. The aligned text string is recognized by optical character recognition (OCR). Experiments on various curved video frames shows that proposed method is efficacious and robust in detecting and recognizing curved videotext.

Fast Text Processing for Interlaced Sports or News Videos

Interlaced scanning has been widely used as a trade-off solution between picture quality and transmission bandwidth since the invention of television. During the past decades, various interlaced-to-progressive conversion algorithms have been proposed to improve subjective quality or coding efficiency. However, almost all the researchers concentrate on general cases, without making full use of specific application scenarios. Based on extensive investigations, eliminating visual artifacts in areas of subtitles and station captions for interlaced sports and news videos is still an unsolved problem, which will be addressed in this paper. Firstly, motion estimation is performed between field pictures. Secondly, text edge detection is proposed for sports and news videos. Finally, different processing strategies are applied to text regions and non-text regions. Experimental results show that the proposed method can generate much better text content than existing algorithms. In addition, it is quite stable for non-text parts.

Robust Video Text Detection with Morphological Filtering Enhanced MSER

Video text detection is a challenging problem, since video image background is generally complex and its subtitles often have the problems of color bleeding, fuzzy boundaries and low contrast due to video lossy compression and low resolution. In this paper, we propose a robust framework to solve these problems. Firstly, we exploit gradient amplitude map (GAM) to enhance the edge of an input image, which can overcome the problems of color bleeding and fuzzy boundaries. Secondly, a two-direction morphological filtering is developed to filter background noise and enhance the contrast between background and text. Thirdly, maximally stable extremal region (MSER) is applied to detect text regions with two extreme colors, and we use the mean intensity of the regions as the graph cuts’ label set, and the Euclidean distance of three channels in HSI color space as the graph cuts smooth term, to get optimal segmentations. Finally, we group them into text lines using the geometric characteristics of the text, and then corner detection, multi-frame verification, and some heuristic rules are used to eliminate non-text regions. We test our scheme with some challenging videos, and the results prove that our text detection framework is more robust than previous methods.

English

The textual pieces in scene images might often provide vital semantic data for visual content understanding, indexing and analysis; as a result, text extraction had become a significant research area in image processing and computer vision. In this paper, we propose a new hybrid multilevel algorithm to extract text in various scene images. The algorithm converts the Red – Green –Blue (RGB) image into grayscale for color reduction. Next, it applies edge detection and mathematical morphological operations to extract edges in the image preprocessing phase. The resultant binary image passes through three subsequent levels in a multi layer behavior. Connected components labeling and text candidates' selection take place in each level through different criteria analysis. We used the structural features of connected components as basis criteria for selecting candidate texts, those features include: area, width, length and condense intensity mean of connected components. Afterwards, Horizontal projection profile analysis is used to further refine the candidate text areas and to eliminate non-text regions. The proposed algorithm is evaluated on a set of fifty images chosen from a well known text locating test dataset: KAIST. Extensive experiments show high robustness under different environments such as indoor, outdoor, shadow, night and light, and for different text properties such as various font size, style and complexities of backgrounds and textures. The algorithm effectively extracts textual contents from scenes images with high average of Precision, Recall, and F-Score which are 90.1, 99, and 94.3%, respectively.    Key words: Multilevel text extraction, hybrid text extraction, edge detection, connected components, text candidates, morphological operations, horizontal projection profile. &nbsp

Text Detection in Scene Images Based on Interest Points

Text in images is one of the most important cues for understanding a scene. In this paper, we propose a novel approach based on interest points to localize text in natural scene images. The main ideas of this approach are as follows: first we used interest point detection techniques, which extract the corner points of characters and center points of edge connected components, to select candidate regions. Second, these candidate regions were verified by using tensor voting, which is capable of extracting perceptual structures from noisy data. Finally, area, orientation, and aspect ratio were used to filter out non-text regions. The proposed method was tested on the ICDAR 2003 dataset and images of wine labels. The experiment results show the validity of this approach.

Caption Region Detection in Video Images by Improved Corner Detector

Caption region detection is significant for text segmentation and recognition in video images. In this paper, caption region detection includes the following three steps: text corner detection, candidate text region generation, non-text region elimination. Firstly, an improved Harris corner detection algorithm based on second difference, called sHarris, is proposed to detect text corners. sHarris detector is effective to detect text corners existing in video image. Secondly, morphologic operations are utilized to generate candidate text regions after text corner points are detected. Finally, non-text regions are eliminated from candidate text regions by some validation rules. In the end of this paper, experiments are used to analyze and evaluate the detection results of caption regions, which indicate the effectiveness of the proposed method.

A method for text line detection in natural images

Text information in natural images is very important to cross-media retrieval, index and understanding. However, its detection is challenging due to varying backgrounds, low contrast between text and non-text regions, perspective distortion and other disturbing factors. In this paper, we propose a novel text line detection method which can detect text line aligned with a straight line in any direction. It is mainly composed of three steps. In the first step, we use the maximal stable extremal region detector with dam line constraint to detect candidate text regions, we then define a similarity measurement between two regions which combines sizes, absolute distance, relative distance, contextual information and color histograms. In the second step, we propose a text line identification algorithm based on the defined similarity measurement. The algorithm firstly searches three regions as the seeds of a line, and then expands to obtain all regions in the line. In the last step, we develop a filter to remove non-text lines. The filter uses a sparse classifier based on two dictionaries which are learned from feature vectors extracted from morphological skeletons of those candidate text lines. A comparative study using two datasets shows the excellent performance of the proposed method for accurate text line detection with horizontal or arbitrary consistent orientation.

Systematic Approach for Detecting Text in Images Using Supervised Learning

Locating text data in images automatically has been a challenging task. In this approach, we build a three stage system for text detection purpose. This system utilizes tensor voting and Completed Local Binary Pattern (CLBP) to classify text and non-text regions. While tensor voting generates the text line information, which is very useful for localizing candidate text regions, the Nearest Neighbor classifier trained on discriminative features obtained by the CLBP-based operator is used to refine the results. The whole algorithm is implemented in MATLAB and applied to all images of ICDAR 2011 Robust Reading Competition data set. Experiments show the promising performance of this method.