Achraf Othman

Publications


Filter by type

  • Show All
  • Journals
  • Workshop
  • Conferences

Filter by year

  • Show All
  • 2013
  • 2012
  • 2011
  • 2010

Filter by theme

  • Show All
  • Accessibility for Deafs
  • Computer Graphics

Sort Controls

  • Descending
  • Ascending
  • Default
  • 16 Achraf Othman and Raouia Hamdoun. “Toward a new Transcription Model in XML for Sign Language Processing based on Gloss Notation System”. Fourth International Conference On Information and Communication Technology and Accessibility ICTA'13, October 24-26, 2013, Hammamet, Tunisia.

    Abstract - Representation of Sign Language (SL) in written form is required for the generation via avatar or any other tools of synthesis. Although, this problem can be solved by developing a new transcription system based on one of existing annotation like gloss. In this context, we present a new transcription system for the American Sign Language (ASL) based on gloss annotation system. Initially, a descriptive study of glosses will be detailed to clarify the transcription system. In a second step, we describe our system following an XML format, to facilitate the interpretation of coded data that we assign. Finally, we propose our API in Java to build an annotation gloss as XML to create corpus or to manipulate a virtual signer as an intermediate language. Also, the new transcription system can be useful for any Sign Language Processing tool like machine translation or building n-gram models.
    Conference link :

  • 15 Achraf Othman and Zouhour Tmar. “English-ASL Gloss Parallel Corpus 2012: ASLG-PC12, The Second Release”. Fourth International Conference On Information and Communication Technology and Accessibility ICTA'13, October 24-26, 2013, Hammamet, Tunisia.

    Abstract - A serious problem facing the Community for researchers in the field of sign language is the absence of a large parallel corpus for signs language. The ASLG-PC12 project proposes a rule-based approach for building big parallel corpus between English written texts and American Sign Language Gloss. We present a novel algorithm which transforms an English part-of-speech sentence to ASL gloss. This project was started in the beginning of 2010, a part of the project WebSign, and it offers today a corpus containing more than one hundred million pairs of sentences between English and ASL gloss. It is available online for free in order to develop and design new algorithms and theories for American Sign Language processing, for example statistical machine translation and any related fields. In this paper, we present tasks for generating ASL sentences from the corpus Gutenberg Project that contains only English written texts.
    Conference link :

  • 14 Mohamed Jemni, Sameer Semreen, Achraf Othman, Zouhour Tmar and Nadia Aouiti. “Toward the creation of an Arab GLOSS for Arabic Sign Language Notation”. Fourth International Conference On Information and Communication Technology and Accessibility ICTA'13, October 24-26, 2013, Hammamet, Tunisia.

    Abstract - Representation of Sign Language (SL) in written form is required for the generation via avatar or any other tools of synthesis specially for Arabic Sign Language (Unified or not) noted ArSL. Although, this problem can be solved by developing a new transcription system based on one of existing annotation like gloss or any other writing system that respect properties of ArSL. In this context, we present a new initiative toward the creation of an Arab Gloss writing system for this sign language based on gloss annotation system like American Sign Language. Initially, a descriptive study of motivation and issues will be detailed to clarify the need of a transcription system. In a second step, we describe some solution for writing system following some guidelines inspired from others writing annotation system, to facilitate the interpretation of coded data that we assign. Finally, we propose some conventions. Also, the new transcription system can be useful for any Sign Language Processing tool like machine translation or building n-gram models.
    Conference link :

  • 13 Achraf Othman, Oussama El Ghoul. “A Novel Approach for 3D Head Segmentation and Facial Feature Points Extraction”. International Conference on Electrical Engineering and Software Applications ICEESA , March 21-23, 2013, Hammamet, Tunisia.

    Abstract - This work presents a novel approach for 3D head segmentation as well as for extraction of facial features vertices. These tasks are the preliminary task for retrieval, recognition, classification and tracking processes. 3D head regions are detected from a cloud of points using the ratio of geodesic to Euclidean distances between pairs of vertices that combine neighbor coordinates and position information of the point. In this paper, we propose a new algorithm to extract automatically feature points inside the facial region based on the topology of 3D face. Furthermore, in order to validate our approach, we have run experimentations on several types of full 3D head that differ in number of points and surfaces, gender and ethnic. Also, to approve its robustness, we apply our approach on a benchmark of scanned faces containing 67 models.
    | IEEE

  • 12 Zouhour Tmar, Achraf Othman, Mohamed Jemni. “A Rule-Based Approach for Building an Artificial English-ASL Corpus”. International Conference on Electrical Engineering and Software Applications ICEESA, March 21-23, 2013, Hammamet, Tunisia.

    Abstract - A serious problem facing the Community for researchers in the field of sign language is the absence of a large parallel corpus for signs language. The ASLG-PC12 project, proposes a rule-based approach for building big parallel corpus between English written texts and American Sign Language Gloss. We present a novel algorithm which transforms an English part-of-speech sentence to ASL gloss. This project was started in the beginning of 2010, a part of the project WebSign, and it offers today a corpus containing more than one hundred million pairs of sentences between English and ASL gloss. It is available online for free in order to develop and design new algorithms and theories for American Sign Language processing, for example statistical machine translation and any related fields. In this paper, we present tasks for generating ASL sentences from the corpus Gutenberg Project that contains only English written, texts.
    | IEEE

  • 11 Mohamed Jemni, Sameer Semreen, Oussama El ghoul, Achraf Othman, “المعالجة الآلية للغة الاشارة و برمجيات التواصل مع الصم”. Special Issue in the Communications of Arab Society, Vol 5, No 2, 2012

    Abstract - ...

  • 10 Mohamed Jemni, Sameer Semreen, Oussama El ghoul, Achraf Othman, “المعالجة الآلية للغة الاشارة و برمجيات التواصل مع الصم”. ورشة العمل الافتراضية الخامسة حول نظم الحوسبة الذكية وتطبيقاتھا, 10-11 سبتمبر 2012

    Abstract - ...

  • 9 Achraf Othman, Mohamed Jemni.A probabilistic model for Sign Language Translation Memory”. The 1st International Symposium on Intelligent Informatics, ISI’12, August, Chennai, India, 4-5, 2012.

    Abstract - In this paper, we present an approach for building translation memory for American Sign Language (ASL) from parallel corpora between English and ASL, by identifying new alignment combinations of words from existing texts. Our primary contribution is the application of several models of alignments for Sign Language. The model represents probabilistic relationships between properties of words, and relates them to learned underlying causes of structural variability within the domain. We developed a statistical machine translation based on generated translation memory. The model was evaluated on a big parallel corpus containing more than 800 millions of words. IBM Models have been applied to align Sign Language Corpora then we have run experimentation on a big collection of paired data between English and American Sign Language. The result is useful to build a Statistical Machine Language or any related field.
    Springer | Google Books

  • 8 Achraf Othman, Zouhour Tmar, Mohamed Jemni. “Toward developing a very big Sign Language Parallel Corpus”. The 13th International Conference on Computers Helping People with Special Needs ‘ICCHP’, Lecture Note in Computer Science LNCS Springer, July 11-13, 2012, University of Linz, Austria.

    Abstract - The Community for researchers in the field of sign language is facing a serious problem which is the absence of a large parallel corpus for signs language. The ASLG-PC12 project, conducted in our laboratory, proposes a rule-based approach for building big parallel corpus between English written texts and American Sign Language Gloss. In this paper, we present a new algorithm to transform a part of English-speech sentence to ASL gloss. This project was started in the beginning of 2011 and it offers today a corpus containing more than one hundred million pairs of sentences between English and ASL gloss. It is available online for free in order to develop and design new algorithms and theories for Sign Language processing, for instance, statistical machine translation and any related fields. We present, in particular, the tasks for generating ASL sentences from the corpus Gutenberg Project that contains only English written texts.
    Springer | ACM

  • 7 Mohamed Jemni, Sameer Samreen, Achraf Othman,. “دور التكنولوجيات الحديثة في تطوير لغة الاشارة و تسهيل التواصل مع الصم”. المؤتمر العلمي الثاني للصم و ضعاف السمع، 1-3 مايو 2012، الدوحة، قطر.

    Abstract - .

  • 6 Achraf Othman, Mohamed Jemni. “English-ASL Gloss Parallel Corpus 2012: ASLG-PC12”. LREC 2012, 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon, May 51-27, 2012, Istanbul Turkey.

    Abstract - .

  • 5 Achraf Othman, Mohamed Jemni, “La traduction automatique à base de statistiques au service de la langue des signes”. 4ème édition du colloque INFOL@NGUES 2012, April 5-7, 2012, Béjà, Tunisia.

    Abstract - .

  • 4 Achraf Othman, Oussama El Ghoul, Mohamed Jemni. “An automatic approach for facial feature points extraction from 3D head”. International Conference on Computer Graphics Theory and Applications GRAPP’12, February 24-26, 2012, Rome, Italy.

    Abstract - This work presents a novel approach for 3D head segmentation as well as for extraction of facial features vertices. These tasks are the preliminary task for retrieval, recognition, classification and tracking processes. 3D head regions are detected from a cloud of points using the ratio of geodesic to Euclidean distances between pairs of vertices that combine neighbor coordinates and position information of the point. In this paper, we propose a new algorithm to extract automatically feature points inside the facial region based on the topology of 3D face. Furthermore, in order to validate our approach, we have run experimentations on several types of full 3D head that differ in number of points and surfaces, gender and ethnic. Also, to approve its robustness, we apply our approach on a benchmark of scanned faces containing 67 models.

  • 3 Achraf Othman, Mohamed Jemni. “Statistical Sign Language Machine Translation: from English written text to American Sign Language Gloss”. International Journal of Computer Science Issues, Vol 8, Issue 5, September 30, pp. 65-73.

    Abstract - This works aims to design a statistical machine translation from English text to American Sign Language (ASL). The system is based on Moses tool with some modifications and the results are synthesized through a 3D avatar for interpretation. First, we translate the input text to gloss, a written form of ASL. Second, we pass the output to the WebSign Plug-in to play the sign. Contributions of this work are the use of a new couple of language English/ASL and an improvement of statistical machine translation based on string matching thanks to Jaro-distance.

  • 2 Achraf Othman, Heithem Abbes, Mohamed Jemni. “Gridification of facial feature vertices extractionfrom 3D head”. The EUMEDGRID-Support User Forum Workshop / The EGI Technical Forum 2011. September 19-23, 2011, Lyon, France.

    Abstract - the extraction of Facial features vertices from 3D faces is a beforehand task for retrieval, recognition, classification and tracking processes. Facial regions are detected from the cloud of points using the ratio of geodesic to Euclidean distances between pairs of vertices that combine neighbor coordinates and position information of the vertex. Many facial feature points among those specified by the MPEG-4 Standard are extracted automatically inside the facial region based on the topology of 3D face. The extracted feature points can be used to define the visual aspect of the face and to provide an MPEG-4 compliant face model. In addition, the displacement of these points allows the MPEG-4 decoder to deform the shape and to ensure the animation of the face. 3D faces are composed of vertices and surfaces. Since the number of vertices and surfaces is important, the sequential computation time is great. Therefore, we present a gridification of a novel algorithm for extracting facial feature vertices from 3D mesh. This allowed running important experimentations based on large inputs data to optimize the 3D processing chain. Experimentations on EumedGrid platform show the contribution of the gridification in improving obtained results.

  • 1 Achraf Othman, Oussama El Ghoul, Mohamed Jemni. “Sport Sign: A new service to make sports news accessible for deaf persons”. The 12th International Conference on Computers Helping People with Special Needs ‘ICCHP’, Lecture Note in Computer Science LNCS Springer, pp.169-176, vol. 6190, July 14-16, 2010, Vienna, Austria.

    Abstract - Sports are important in the life of deaf, as well as hearing persons, on physical, social and mental levels. However, despite that there exist many deaf sports organization in the world, the announcement of sports’ results and actualities is still done by written or vocal languages. In this context, we propose a Web based application to edit and diffuse sports news in sign languages. The system uses the technology of avatar and it is based on WebSign kernel developed by our research Laboratory of Technologies of Information and Communication (UTIC). Information is broadcasted using MMS containing video on sign languages and also published in SportSign’s Web site.
    Springer | ACM