A New Arabic Printed Text Image Database and Evaluation Protocols

Slimane, Fouad; Ingold, Rolf; Kanoun, Slim; Alimi, Adel M.; Hennebert, Jean

doi:10.1109/icdar.2009.155

Cited by 121 publications

(63 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As indicated above, experiments were carried out on the public part of the APTI database [10]. As the public part of APTI does not include set 6 , we could not rerun exactly the experiments carried out at the ICDAR 2011 competition.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Arabic Printed Word Recognition Using Windowed Bernoulli HMMs

Khoury

Giménez

Juan

et al. 2013

Image Analysis and Processing – ICIAP 2013

View full text Add to dashboard Cite

Abstract. Hidden Markov Models (HMMs) are now widely used for off-line text recognition in many languages and, in particular, Arabic. In previous work, we proposed to directly use columns of raw, binary image pixels, which are directly fed into embedded Bernoulli (mixture) HMMs, that is, embedded HMMs in which the emission probabilities are modeled with Bernoulli mixtures. The idea was to by-pass feature extraction and to ensure that no discriminative information is filtered out during feature extraction, which in some sense is integrated into the recognition model. More recently, we extended the column bit vectors by means of a sliding window of adequate width to better capture image context at each horizontal position of the word image. However, these models might have limited capability to properly model vertical image distortions. In this paper, we have considered three methods of window repositioning after window extraction to overcome this limitation. Each sliding window is translated (repositioned) to align its center to the center of mass. Using this approach, state-of-art results are reported on the Arabic Printed Text Recognition (APTI) database.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The Arabic Printed Text Image (APTI) database is freely available for noncommercial research [10]. It is a multi-font, multi-size and multi-style database.…”

Section: Apti Databasementioning

confidence: 99%

Arabic Printed Word Recognition Using Windowed Bernoulli HMMs

Khoury

Giménez

Juan

et al. 2013

Image Analysis and Processing – ICIAP 2013

View full text Add to dashboard Cite

show abstract

“…then, in Sect. 3.3, we describe how the APTI benchmark was constructed [12] and provide some initial tests results we did on parts of the dataset.…”

Section: Scanning For Initial and A Final Letter Or An Isolated Lettermentioning

confidence: 99%

“…The Arabic printed text image database (APTI) [12], was created to address the challenges of optical character recognition of printed Arabic text of multiple fonts, multiple font sizes and multiple font styles. APTI is designed for the evaluation of screen-based OCR systems.…”

Section: Apti Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Arabic Character Recognition

Dershowitz

Rosenberg

2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Although optical character recognition of printed texts has been a focus of research for the last few decades, Arabic printed text, being cursive, still poses a challenge. The challenge is twofold: segmenting words into letters and identifying individual letters. We describe a method that combines the two tasks, using multiple grids of SIFT descriptors as features. To construct a classifier, we do not use a large training set of images with corresponding ground truth, a process usually done to construct a classifier, but, rather, an image containing all possible symbols is created and a classifier is constructed by extracting the features of each symbol. To recognize the text inside an image, the image is split into "pieces of Arabic words", and each piece is scanned with increasing window sizes. Segmentation points are set where the classifier achieves maximal confidence. Using the fact that Arabic has four forms of letters (isolated, initial, medial and final), we narrow the search space based on the location inside the piece. The performance of the proposed method, when applied to printed texts and computer fonts of different sizes, was evaluated on two independent benchmarks, PATS and APTI. Our algorithm outperformed that of the creator of PATS on five out of eight fonts, achieving character correctness of 98.87%-100%. On the APTI dataset, ours was competitive or better that the competition.

show abstract