Computer Vision Based Automatic Margin Computation Model for Digital Document Images

Now days reading words from an unconstrained and noisy image is not easy. Text localization and recognition in an image is a research area which takes efforts to develop a computer system with an ability to automatically read the text from images. The objective of this study is to propose a new method for text localization and recognition in natural scene images with complex background. In this paper, a hybrid methodology is suggested which extracts text from natural scene image with chaotic backgrounds. The proposed approach involves embedded system. This combines software with hardware. First, superimposed text regions in an image are extracted based on character descriptors features like Area, Bounding box, Perimeter, Euler number, Horizontal crossings. In the second step, superimposed text regions are tested for text content or non-text using character descriptors and SVM classifier. In the third step, detection of multiple lines in localized superimposed text regions is made and line segmentation is performed using horizontal profiles. In the final step, using vertical profiles each character of the segmented line is extracted. In the system ARM7 (LPC2138) is interface with Personal Computer. The GPS and GSM are also interface with the ARM7 (LPC2138). The extracted English text from an image is given to the ARM7 (LPC2138). This will be displayed on LCD. The GPS will obtain location coordinates of an image. The GSM will send SMS to the local tourist guide company like (e.g. Just Dial) to update information of natural scene image like (e.g. shop names, hotel names etc.). The workout has been done using images drawn from ICDAR 2013 and SVT 2010 datasets. The extracted text and location results will be played with IC (APR33A3). This system will be helpful for tourist and visually impaired. The results demonstrate the effectiveness of the proposed method, which can be used as an efficient method for text localization and recognition in natural scene images.

The objective of this study is to propose a new method for text region localization and character extraction in natural scene images with complex background. In this paper, a hybrid methodology is suggested which extracts multilingual text from natural scene image with cluttered backgrounds. The proposed approach involves four steps. First, potential text regions in an image are extracted based on edge features using Contourlet transform. In the second step, potential text regions are tested for text content or non-text using GLCM features and SVM classifier. In the third step, detection of multiple lines in localized text regions is done and line segmentation is performed using horizontal profiles. In the last step, each character of the segmented line is extracted using vertical profiles. The experimentation has been done using images drawn from own dataset and ICDAR dataset. The performance is measured in terms of the precision and recall. The results demonstrate the effectiveness of the proposed method, which can be used as an efficient method for text recognition in natural scene images.

Universally, scene text in natural images is an expressive means of communication. Texts available in an image could provide important information which can enhance the interpretation of the image, for instance texts on product packages and road signs. Recently, scene texts detection has been recognized as an important research field in computer vision. However, texts detection in natural scene images has been challenging due to the complicated scene background involving varying fonts, sizes, image resolutions etc. As to date, different methods of detecting texts in natural scene images have been proposed for horizontal texts, arbitrarily-oriented texts and curved texts, but there is a lack of detection of vertically-oriented texts in the natural scene images. Hence, this research proposed a framework for detecting the top-to-bottom, bottom-to-top and horizontally-stacked vertical texts in natural scene images. In this paper, Multi-directional Text Detector (MTD) is modelled and developed to locate the vertically-oriented texts in natural scene images, and the Vertical Scene Texts Dataset-700 (VSTD-700) is developed. The preliminary testing shows that the success rate of detection of MTD is 87% on ICDAR 2013, 73% on ICDAR 2015, 71% on MSRA-TD500 and 87% on VSTD-700 datasets. Hence, the results showed that MTD is able to detect vertically-oriented texts on top of the horizontally-oriented and arbitrarily-oriented texts in natural scene images simultaneously.

Now days reading words from an unconstrained and noisy image is not easy. Text localization and recognition in an image is a research area which takes efforts to develop a computer system with an ability to automatically read the text from images. The Optical Character Recognition (OCR) tool gives good results obtained to read the text from an image. The objective of this study is to propose a new method for text localization and recognition in natural scene images with complex background. In this paper, a hybrid methodology is suggested which extracts text from natural scene image with chaotic backgrounds. The proposed approach involves four stages. First, superimposed text regions in an image are extracted based on character descriptors features like Area, Bounding box, Perimeter, Euler number, Horizontal crossings. In the second step, superimposed text regions are tested for text content or nontext using character descriptors and SVM classifier. In the third step, detection of multiple lines in localized text regions is done and line segmentation is performed using horizontal profiles. In the final step, using vertical profiles each character of the segmented line is extracted. The workout has been done using images drawn from ICDAR 2013 and SVT 2010 datasets. The results demonstrate the effectiveness of the proposed method, which can be used as an efficient method for text localization and recognition in natural scene images.

Textual matter present in a natural scene image provides indispensable information about it. The semantics and information present in the natural scene images can be perceived by extracting the text regions in them. Detection and localization of text from natural scene images is a challenging task for analysis of images due to various font size, font type, and illumination. In this paper, we propose a hybrid approach for text detection and localization based on text confidence score using three attributes namely stroke width dissimilarity, color dissimilarity and occupy rate convex area to discern text and non-text constituents. The aim of this paper is to achieve fast detection and localization of text regions in low resolution and blurred images. To accomplish this, the possible candidate regions are extracted using edge smoothing by fast guided filter followed by MSER. The text confidence score on these constituents is calculated using the Bayesian framework with the help of above mentioned three attributes. Experimental results on benchmark ICDAR 2013 testing dataset shows the efficacy of our method in the form of precision, recall, and f-measure.

Unified non-uniform scale adaptive sampling model for quality assessment of natural scene and screen content images

A Hybrid Approach to Localize Farsi Text in Natural Scene Images

A new text location method based on color reduction and Adaboost classifier is proposed in this paper, which is used in extracting the text region in natural scene images with complex background. Firstly, the images are segmented into several layers through adopting color reduction and mean shift image segmentation techniques. Then, in order to pick up the potential text region, each layer is processed using connected component analysis, text region identification and text region merging, etc. Finally, HOG (Histogram of Oriented Gradient) and LBP (Local Binary Pattern) features are extracted from the candidate text region, and an AdaBoost classifier is applied to classify text and non-text regions. A series of experiments on a natural scene images database have indicated that, our method can effectively improve the text location in natural scene images with complex background, showing the effectiveness of the proposed approach.

Text in camera captured images contains important and useful information. Text in images can be used for identification, indexing and retrieval. Detection and localization of text from camera captured images is still a challenging task due to high variability of text appearance. In this paper we propose an efficient algorithm, for detecting and localizing text in natural scene images. The method is based on texture feature extraction using first and second order statistics. The entire work is divided into two stages. Text regions are detected in the first stage using texture features. Discriminative functions are used to filter out non-text regions. In the second stage the detected text regions are merged and localized. An experimental results obtained shows that the proposed approach detects and localizes texts of various sizes, fonts, orientations and languages efficiently.

Detection and localization of texts from natural scene images is important and can provide a much truer form of content-based image analysis if it can be extracted and harnessed efficiently. This problem becomes challenging because of complex background, variations of text font, size and line orientation, non-uniform illumination. A new unsupervised text detection algorithm is proposed in this paper. In this approach scale space and morphological operations for the edge detection are utilized. The non-text components are efficiently filter out by using scale decomposition and 2D Gaussian low pass filter. They are extracted based on observation that the edge of a character can be extracted from the complex scenes by taking into consideration the high similarities in length and aspect ratio. The proposed method yielded high precision when experiments where evaluated in the ICDAR 2003 dataset.

Detecting text in natural scene images is a challenging task. In this paper, we propose a character-level end-to-end text detection algorithm in natural scene images. In general, text detection tasks are categorized into three parts: text localization, text segmentation, and text recognition. The proposed method aims not only to localize but also to recognize text. To do these tasks successfully, the proposed method consists of four steps: character candidate patch extraction, patch classification using ensemble of ResNets, non-character region elimination, and character region grouping via self-tuning spectral clustering. In the character candidate patch extraction step, character candidate patches are extracted from the image by using both edge information from multi-scale images and Maximally Stable Extremal Regions (MSERs). Then each patch is classified into either character patch or non-character patch by using the deep network that is composed of three ResNets with different hyper-parameters. Text regions are determined by filtering out non-character patches. In order to make further reduction of classification errors, character characteristics are employed to compensate classification results of the ensemble of ResNets. To evaluate the text detection performance, character regions are grouped via self-tuning spectral clustering. The proposed method shows competitive performance on the ICDAR 2013 dataset.

Text recognition plays an important role in recognizing texts presented in the images as they provide important information. Scene text recognition has been an active research topic with rapid growth of development to improve the performance of text recognition with better reliability and accuracy. However, scene text recognition is challenging due to images containing inconsistent lighting, low resolution and blurriness. In addition, scene texts are usually taken from outdoor signboards, signage and road signs, which contain various orientation and fancy font styles to attract attention. Various researchers have proposed methods for recognizing different orientations of scene texts, such as horizontal texts, curved texts and rotated texts. However, to data there is a lack of research in recognizing vertical texts in natural scene images. In this research, a model for effective automatic recognition of vertical texts in natural scene images has been proposed, consisting of two major processes which are text localization and segmentation and text recognition. This proposed model recognizes three different types of vertical scene texts, which are top-to-bottom vertical texts, bottom-to-top vertical texts and horizontal-stacked vertical texts.

With the rapid increase of multimedia data, textual content in an image has become a very important source of information for several applications like navigation, image search and retrieval, image understanding, captioning, machine translation and several others. Scene text localization is the first step towards such applications and most current methods focus on generating a small set of high precision detectors rather than obtaining large set of detections covering all text patches. In this work we propose a novel hybrid framework for text localization which uses character level recognition recursively in a feedback mechanism to refine text patches and reduce false positives. We use popular MSER algorithm at multiple scales as an initial region proposal algorithm and several filtering stages recursively to improve precision as well as maximize recall. We aim at achieving high recall rather than achieving higher precision since several robust word recognition systems are already available. The word recognition systems are mature enough to produce highly accurate results if provided with maximum amount of regions rather than providing small set of highly precise text patches and losing several other text regions. The main contribution of this paper is the use of character recognizer within a novel feedback mechanism to recursively search for text regions in the neighborhood of previously detected text patches. Using 3 publicly available benchmark datasets (ICDAR2011, MSRA TD-500 and OSTD), we demonstrate the efficacy of the proposed framework for text localization.

With the advancement of digital technology, use of various multimedia devices such as portable camera and mobile camera has grown at rapid pace. Now days, these portable devices are used to capture various scene images which usually contain text. The text part in the scene images sometimes contain useful information which needs to be recognized for various applications. But, text detection in natural scene images is very challenging process due to factors such as uneven illumination, arbitrary layouts, perspective distortion and warped text. In order to overcome these challenges, study is being done by various researchers to detect text from the natural scene images. In this paper, author explains the various text detection techniques which have already been previously used for text detection in natural images. Apart from that, author has also described the new era of technology i.e. Deep Learning based techniques for text detection in natural scene images.

Saliency-induced reduced-reference quality index for natural scene and screen content images