Locating text in images using matched wavelets
31 Aug 2005-pp 595-599
TL;DR: A novel scheme for locating text regions in an image based on multiresolution wavelet analysis that does not require any a priori information about the font, font size, scripts, geometric transformation, distortion or background texture is proposed.
Abstract: In this paper we have proposed a novel scheme for locating text regions in an image. The method is based on multiresolution wavelet analysis. We used matched wavelets to capture textural characteristics of image regions. A clustering based approach has been proposed for estimating globally matched wavelets (GMWs) for a given collection of images. Using these GMWs, we generate feature vectors for segmentation and identification of text regions in an image. Our method, unlike most of the other methods, does not require any a priori information about the font, font size, scripts, geometric transformation, distortion or background texture. We have tested our method on various categories of images like license plates, posters, hand written documents and document images etc. The results show proposed method to be a robust, versatile and effective tool for text extraction from images.
Citations
More filters
TL;DR: A clustering-based technique has been devised for estimating globally matched wavelet filters using a collection of groundtruth images and a text extraction scheme for the segmentation of document images into text, background, and picture components is extended.
Abstract: In this paper, we have proposed a novel scheme for the extraction of textual areas of an image using globally matched wavelet filters. A clustering-based technique has been devised for estimating globally matched wavelet filters using a collection of groundtruth images. We have extended our text extraction scheme for the segmentation of document images into text, background, and picture components (which include graphics and continuous tone images). Multiple, two-class Fisher classifiers have been used for this purpose. We also exploit contextual information by using a Markov random field formulation-based pixel labeling scheme for refinement of the segmentation results. Experimental results have established effectiveness of our approach.
159 citations
TL;DR: The results of experiments confirm the robustness of proposed method against severe imaging conditions and the ability to characterize the color information in plate using the MNS (multimodal neighborhood signature) method.
154 citations
TL;DR: A filtering method called ''region-based'' is proposed in order to smooth the uniform and background areas of an image, the Sobel operator and morphological filtering to extract the vertical edges and the candidate regions respectively, and the plate region is segmented by considering some geometrical features.
68 citations
Cites methods from "Locating text in images using match..."
...In fact the novelty and the strength of our license plate detection system is in applying the region-based filtering that decreases the run time and increases the accuracy in the two final stages: morphological filtering and using the geometrical features....
[...]
...In the following, these two methods are explained in detail....
[...]
TL;DR: Under the method, each construction site image is first divided into regions through image segmentation, and the visual features of each region are calculated and classified with a pre-trained classifier, determining whether the region is composed of concrete or not.
57 citations
23 Sep 2007
TL;DR: This paper develops a fast, simple, and effective algorithm to detect character strokes and analyzes the performance of the stroke detection algorithm on images collected for the robust-reading competitions at ICDAR 2003.
Abstract: In this paper, we present a new approach for analysis of images for text-localization and extraction. Our approach puts very few constraints on the font, size and color of text and is capable of handling both scene text and artificial text well. In this paper, we exploit two well-known features of text: approximately constant stroke width and local contrast, and develop a fast, simple, and effective algorithm to detect character strokes. We also show how these can be used for accurate extraction and motivate some advantages of using this approach for text localization over other color-space segmentation based approaches. We analyze the performance of our stroke detection algorithm on images collected for the robust-reading competitions at ICDAR 2003.
44 citations
Cites methods from "Locating text in images using match..."
...These low-level properties are computed for subset of pixels [2, 3] and used to train a classifier....
[...]
References
More filters
01 Dec 2001
TL;DR: Learning with Kernels provides an introduction to SVMs and related kernel methods that provide all of the concepts necessary to enable a reader equipped with some basic mathematical knowledge to enter the world of machine learning using theoretically well-founded yet easy-to-use kernel algorithms.
Abstract: From the Publisher:
In the 1990s, a new type of learning algorithm was developed, based on results from statistical learning theory: the Support Vector Machine (SVM). This gave rise to a new class of theoretically elegant learning machines that use a central concept of SVMs-kernels--for a number of learning tasks. Kernel machines provide a modular framework that can be adapted to different tasks and domains by the choice of the kernel function and the base algorithm. They are replacing neural networks in a variety of fields, including engineering, information retrieval, and bioinformatics.
Learning with Kernels provides an introduction to SVMs and related kernel methods. Although the book begins with the basics, it also includes the latest research. It provides all of the concepts necessary to enable a reader equipped with some basic mathematical knowledge to enter the world of machine learning using theoretically well-founded yet easy-to-use kernel algorithms and to understand and apply the powerful algorithms that have been developed over the last few years.
7,880 citations
TL;DR: A robust system is proposed to automatically detect and extract text in images from different sources, including video, newspapers, advertisements, stock certificates, photographs, and checks.
Abstract: A robust system is proposed to automatically detect and extract text in images from different sources, including video, newspapers, advertisements, stock certificates, photographs, and checks. Text is first detected using multiscale texture segmentation and spatial cohesion constraints, then cleaned up and extracted using a histogram-based binarization algorithm. An automatic performance evaluation scheme is also proposed.
446 citations
TL;DR: Two methods for automatically locating text in complex color images that computes the local spatial variation in the gray-scale image, and locates text in regions with high variance are presented.
362 citations
"Locating text in images using match..." refers background in this paper
...There has been attempts in the past for extraction of textual component of an image by analyzing the edges of candidate regions or homogeneous color/gray scale components that contain the characters [8],[9],[10]....
[...]
01 Jul 1992
TL;DR: In this paper, two-dimensional Gabor filters are used to extract texture features for each text region in a given document image, and the text in the document is considered as a textured region.
Abstract: There is a considerable interest in designing automatic systems that will scan a given paper document and store it on electronic media for easier storage, manipulation, and access. Most documents contain graphics and images in addition to text. Thus, the document image has to be segmented to identify the text regions, so that OCR techniques may be applied only to those regions. In this paper, we present a simple method for document image segmentation in which text regions in a given document image are automatically identified. The proposed segmentation method for document images is based on a multichannel filtering approach to texture segmentation. The text in the document is considered as a textured region. Nontext contents in the document, such as blank spaces, graphics, and pictures, are considered as regions with different textures. Thus, the problem of segmenting document images into text and nontext regions can be posed as a texture segmentation problem. Two-dimensional Gabor filters are used to extract texture features for each of these regions. These filters have been extensively used earlier for a variety of texture segmentation tasks. Here we apply the same filters to the document image segmentation problem. Our segmentation method does not assume any a priori knowledge about the content or font styles of the document, and is shown to work even for skewed images and handwritten text. Results of the proposed segmentation method are presented for several test images which demonstrate the robustness of this technique.
326 citations
Book•
01 Jan 1995
TL;DR: This paper presents a simple method for document image segmentation in which text regions in a given document image are automatically identified and is shown to work even for skewed images and handwritten text.
Abstract: There is a considerable interest in designing automatic systems that will scan a given paper document and store it on electronic media for easier storage, manipulation, and access. Most documents contain graphics and images in addition to text. Thus, the document image has to be segmented to identify the text regions, so that OCR techniques may be applied only to those regions. In this paper, we present a simple method for document image segmentation in which text regions in a given document image are automatically identified. The proposed segmentation method for document images is based on a multichannel filtering approach to texture segmentation. The text in the document is considered as a textured region. Nontext contents in the document, such as blank spaces, graphics, and pictures, are considered as regions with different textures. Thus, the problem of segmenting document images into text and nontext regions can be posed as a texture segmentation problem. Two-dimensional Gabor filters are used to extract texture features for each of these regions. These filters have been extensively used earlier for a variety of texture segmentation tasks. Here we apply the same filters to the document image segmentation problem. Our segmentation method does not assume any a priori knowledge about the content or font styles of the document, and is shown to work even for skewed images and handwritten text. Results of the proposed segmentation method are presented for several test images which demonstrate the robustness of this technique.
197 citations
"Locating text in images using match..." refers methods in this paper
...Compared to other existing methods [2], [5], [3] the dimensionality and so computation of the feature space is considerably reduced....
[...]