Raid Saabni

Segmentation-Free Online Arabic Handwriting Recognition

Arabic script is naturally cursive and unconstrained and, as a result, an automatic recognition of its handwriting is a challenging problem. The analysis of Arabic script is further complicated in comparison to Latin script due to obligatory dots/stokes that are placed above or below most letters. In this paper, we introduce a new approach that performs online Arabic word recognition on a continuous word-part level, while performing training on the letter level. In addition, we appropriately handle delayed strokes by first detecting them and then integrating them into the word-part body. Our current implementation is based on Hidden Markov Models (HMM) and correctly handles most of the Arabic script recognition difficulties. We have tested our implementation using various dictionaries and multiple writers and have achieved encouraging results for both writer-dependent and writer-independent recognition.

Text line extraction for historical document images

In this paper we present a language independent global method for automatic text line extraction. The proposed approach computes an energy map of a text image and determines the seams that pass across and between text lines. In this work we have developed two algorithms along this novel idea, one for binary images and the other for grayscale images. The first algorithm works on binary document images and assumes it is possible to extract the components along text lines. The seam passes on the middle and along the text line, l, and marks the components that make the letters and words of l. It then assigns the unmarked component to the closest text line. The second algorithm works directly on grayscale document images. It computes the distance transform directly from the grayscale images and generates two types of seams: medial seams and separating seams. The medial seams determine the text lines and the separating seams define the upper and lower boundaries of these text lines. Moreover, we present a new benchmark dataset of historical document images with various types of challenges. The dataset contains a groundtruth for text line extraction and it contains samples with different languages such as: Arabic, English and Spanish. A binary dataset is used to test the binary algorithm. We performed various experimental results using our two algorithms on the mentioned datasets and report segmentation accuracy. We also compare our algorithms with the state-of-the-art text line segmentation methods.

Language-Independent Text Lines Extraction Using Seam Carving

In this paper, we present a novel language-independent algorithm for extracting text-lines from handwritten document images. Our algorithm is based on the seam carving approach for content aware image resizing. We adopted the signed distance transform to generate the energy map, where extreme points indicate the layout of text-lines. Dynamic programming is then used to compute the minimum energy left-to-right paths (seams), which pass along the ``middle`` of the text-lines. Each path intersects a set of components, which determine the extracted text-line and estimate its hight. The estimated hight determines the text-lines region, which guides splitting touching components among consecutive lines. Unassigned components that fall within the region of a text-line are added to the components list of the line. The components between two consecutive lines are processed when the two lines are extracted and assigned to the closest text-line, based on the attributes of extracted lines, the sizes and positions of components. Our experimental results on Arabic, Chinese, and English historical documents show that our approach manage to separate multi-skew text blocks into lines at high success rates.

Hierarchical On-line Arabic Handwriting Recognition

In this paper, we present a multi-level recognizer for online Arabic handwriting. In Arabic script (handwritten and printed), cursive writing – is not a style – it is an inherent part of the script. In addition, the connection between letters is done with almost no ligatures, which complicates segmenting a word into individual letters. In this work, we have adopted the holistic approach and avoided segmenting words into individual letters. To reduce the search space, we apply a series of filters in a hierarchical manner. The earlier filters perform light processing on a large number of candidates, and the later filters perform heavy processing on a small number of candidates. In the first filter, global features and delayed strokes patterns are used to reduce candidate word-part models. In the second filter, local features are used to guide a dynamic time warping (DTW) classification. The resulting k top ranked candidates are sent for shape context based classifier, which determines the recognized word-part. In this work, we have modified the classic DTW to enable different costs for the different operations and control their behavior. We have performed several experimental tests and have received encouraging results.

Comprehensive synthetic Arabic database for on/off-line script recognition research

Developing and maintaining large comprehensive databases for script recognition that include different shapes for each word in the lexicon is expensive and difficult. In this paper, we present an efficient system that automatically generates prototypes for each word in a lexicon using multiple appearances of each letter. Large sets of different shapes are created for each letter in each position. These sets are then used to generate valid shapes for each word-part. The number of valid permutations for each word is large and prohibits practical training and searching for various tasks, such as script recognition and word spotting. We apply dimensionality reduction and clustering techniques to maintain compact representation of these databases, without affecting their ability to represent the wide variety of handwriting styles. In addition, a database for off-line script recognition is generated from the on-line strokes using a standard dilation technique, while making special efforts to resemble pen’s path. We also examined and used several layout techniques for producing words from the generated word-parts. Our experimental results show that the proposed system can automatically generate large databases, whose quality is at least as good as the manually generated ones.

Text line segmentation for gray scale historical document images

In this paper we present a new approach for text line segmentation that works directly on gray-scale document images. Our algorithm constructs distance transform directly on the gray-scale images, which is used to compute two types of seams: medial seams and separating seams. A medial seam is a chain of pixels that crosses the text area of a text line and a separating seam is a path that passes between two consecutive rows. The medial seam determines a text line and the separating seams define the upper and lower boundaries of the text line. The medial and separating seams propagate according to energy maps, which are defined based on the constructed distance transform. We have performed various experimental results on different datasets and received encouraging results.

Efficient Generation of Comprehensive Database for Online Arabic Script Recognition

The difficulties in segmenting cursive words into individual characters have shifted the focus of handwriting recognition research from segmentation-based approaches to segmentation-free (holistic) methods. However, maintaining and training large number of prototypes (models) that represent the words in the dictionary make the training process extremely expensive and difficult in computing resources. In this paper we present an efficient system that automatically generates prototypes for each word in a given dictionary using multiple appearance of each letter shape. Multiple appearance allows for many permutation of shapes for each word and thus complicates searching for the right prototype. To simplify the training, reduce the maintained prototypes, and avoid over fitting, we used dimensionality reduction followed by clustering techniques to reduce the size of these sets without affecting their ability to represent the wide variations of the handwriting styles. A set of generated fonts are created by professional writers imitating all handwriting styles for each character in each position. These Fonts are used to generate all shapes for writing each word-part in a comprehensive dictionary. Principal component analysis and k-means clustering techniques are performed to select the minimal number of shapes representing the wide variations of handwriting styles for a word-part. Experimental results using an online recognition system proves the credibility of this process compared to manually generated databases.

Fast Keyword Searching Using 'BoostMap' Based Embedding

Dynamic Time Warping (DTW), is a simple but efficient technique for matching sequences with rigid deformation. Therefore, it is frequently used for matching shapes in general, and shapes of handwritten words in Document Image Analysis tasks. As DTW is computationally expensive, efficient algorithms for fast computation are crucial. Retrieving images from large scale datasets using DTW, suffers from the constraint of linear searching of all sample in the datasets. Fast approximation algorithms for image retrieval are mostly based on normed spaces where the triangle inequality holds, which is unfortunately not the case with the DTW metric. In this paper we present a novel approach for fast search of handwritten words within large datasets of shapes. The presented approach is based on the Boost-Map [1] algorithm, for embedding the feature space with the DTW measurement to an euclidean space and use the Local Sensitivity Hashing algorithm (LSH) to rank the k-nearest neighbors of a query image. The algorithm, first, processes and embeds objects of the large data sets to a normed space. Fast approximation of k-nearest neighbors using LSH on the embedding space, generates the top kranked samples which are examined using the real DTW distance to give final accurate results. We demonstrate our method on a database of 45; 800 images of word-parts extracted from the IFN/ENIT database [11] and images collected from 51 different writers. Our method achieves a speedup of 4 orders of magnitude over the exact method, at the cost of only a 2:2% reduction in accuracy.

Fast Key-Word Searching via Embedding and Active-DTW

In this paper we present a novel approach for fast search of handwritten Arabic word-parts within large lexicons. The algorithm runs through three steps to achieve the required results. First it warps multiple appearances of each word-part in the lexicon for embedding into the same euclidean space. The embedding is done based on the warping path produced by the Dynamic Time Warping (DTW) process while calculating the similarity distance. In the next step, all samples of different word-parts are resampled uniformly to the same size. The

Efficient Word Image Retrieval Using Earth Movers Distance Embedded to Wavelets Coefficients Domain

kd