Case Study in Hebrew Character Searching

Rabaev, Irina; Biller, Ofer; El-Sana, Jihad; Kedem, Klara; Dinstein, I.

doi:10.1109/icdar.2011.218

Cited by 8 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future we plan to use a dictionary to improve the recognition rate of these letters. An examination of the unrecognized characters, reveals that 68.26% of the unrecognized characters failed to be recognized in the preliminary recognition [17]. That is, none of the 5 candidate characters suggested was the ground truth character.…”

Section: Nsd =mentioning

confidence: 93%

“…That is, none of the 5 candidate characters suggested was the ground truth character. For an analysis of the possible reasons for that we refer the reader to [17]. Figure 5 illustrates the results of our algorithm on a text line, and Figure 4 depicts the computation of the NSD on two different Hebrew characters.…”

Section: Nsd =mentioning

confidence: 98%

“…The recognition of a partially occluded character, c, is performed by computing the distance between each of the models and c. The closest k models are selected as potential candidates for c. The score of matching the partially occluded character, c, and a candidate model, m, is computed by the GSC method in [12,17],which employs normalized features and flexible window sizes. …”

Section: Preliminary Recognitionmentioning

confidence: 99%

“…In this work, we assume that the input consists of segmented Arabic text (the overlaid layer) and partially occluded Hebrew text (the underlaid layer). We apply our text recognition algorithm [17] to find a constant number, k, of candidate letters that match best the fragments of the Hebrew letters. We then complete the broken Hebrew characters using a 2-phase active contour for occluded text (more in Section 3) with the k candidates as shape priors.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Occluded Character Restoration Using Active Contour with Shape Priors

Cohen

Kedem

Dinstein

et al. 2012

2012 International Conference on Frontiers in Handwriting Recognition

Self Cite

View full text Add to dashboard Cite

Broken or partially visible characters is common phenomenon in historical documents. It stems from various factors, such as overlaid text or degradation. Restoring such characters is necessary for document analysis applications. This paper presents a new approach for restoring underlaying Hebrew broken characters that were partially occluded by Arabic text in a palimpsest. We apply text recognition on the fragments of the Hebrew letters and select the k candidate letters that match best the fragments of the Hebrew letters. We then complete the broken Hebrew characters using active contour with the k candidates as shape priors. We use a modified geodesic active contour, which we tailored to occluded text restoration. It is initialized on the fragments of the Hebrew text, then it undergoes an expansion phase and a contraction phase via the occluding Arabic text to form the restored Hebrew character. We measure the distance between the completed character and its corresponding priors and choose the shape with the minimal distance as the reconstructed character. Experimental results are presented. On average 68% of the characters were correctly reconstructed.

show abstract

Section: Nsd =mentioning

confidence: 93%

Section: Nsd =mentioning

confidence: 98%

Section: Preliminary Recognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Occluded Character Restoration Using Active Contour with Shape Priors

Cohen

Kedem

Dinstein

et al. 2012

2012 International Conference on Frontiers in Handwriting Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, two word-matching technologies were used to recognize George Washington's manuscripts [Rath et al 2004], and to identify the historical Hebrew manuscripts [Yosef et al 2004]. Rabaev et al [2011] presented a retrieval approach for the Hebrew manuscripts. Japanese and Korean researchers also developed specific sensibilities and styles of calligraphies, and applied to specific scripts.…”

Section: Retrieval Of Historical Manuscript Imagesmentioning

confidence: 99%

Efficient Personalized Probabilistic Retrieval of Chinese Calligraphic Manuscript Images in Mobile Cloud Environment

Zhuang

Chiu

et al. 2014

ACM Transactions on Asian Language Information Processing

View full text Add to dashboard Cite

Ancient language manuscripts constitute a key part of the cultural heritage of mankind. As one of the most important languages, Chinese historical calligraphy work has contributed to not only the Chinese cultural heritage but also the world civilization at large, especially for Asia. To support deeper and more convenient appreciation of Chinese calligraphy works, based on our previous work on the probabilistic retrieval of historical Chinese calligraphic character manuscripts repositories, we propose a system framework of the multi-feature-based Chinese calligraphic character images probabilistic retrieval in the mobile cloud network environment, which is called the DPRC. To ensure retrieval efficiency, we further propose four enabling techniques: (1) DRL-based probability propagation, (2) optimal data placement scheme, (3) adaptive data robust transmission algorithm, and (4) index support filtering scheme. Comprehensive experiments are conducted to testify the effectiveness and efficiency of our proposed DPRC method.

show abstract