المؤلفون: Philipp Werner, Frerk Saxen, Zaher Al Aghbari, Sebastian Handrich, Ayoub Al-Hamadi, Laslo Dinges

المصدر: Journal of Ambient Intelligence and Humanized Computing. 12:57-73

مصطلحات موضوعية: 0209 industrial biotechnology, Facial expression, General Computer Science, Computer science, Computational intelligence, 02 engineering and technology, Measure (mathematics), Arousal, 020901 industrial engineering & automation, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Valence (psychology), Valence arousal, Cognitive psychology

الوصف: We address the problem of facial expression analysis. The proposed approach predicts both basic emotion and valence/arousal values as a continuous measure for the emotional state. Experimental results including cross-database evaluation on the AffectNet, Aff-Wild, and AFEW dataset shows that our approach predicts emotion categories and valence/arousal values with high accuracies and that the simultaneous learning of discrete categories and continuous values improves the prediction of both. In addition, we use our approach to measure the emotional states of users in an Human-Robot-Collaboration scenario (HRC), show how these emotional states are affected by multiple difficulties that arise for the test subjects, and examine how different feedback mechanisms counteract negative emotions users experience while interacting with a robot system.

الوصول الحر: https://explore.openaire.eu/search/publication?articleId=doi_________::1a2e9d5ab325b40a73055fc428a00976Test
https://doi.org/10.1007/s12652-020-02851-wTest

المؤلفون: Thorsten, Hempel, Marc-Andre, Fiedler, Aly, Khalifa, Ayoub, Al-Hamadi, Laslo, Dinges

المساهمون: Federal Ministry of Education and Research of Germany (BMBF)

المصدر: 2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA)

الإتاحة: https://doi.org/10.1109/ispa52656.2021.9552148Test
http://xplorestaging.ieee.org/ielx7/9552029/9552037/09552148.pdf?arnumber=9552148Test

المؤلفون: Laslo Dinges, Ayoub Al-Hamadi, Moftah Elzobi, Sherif El-etriby

المصدر: Sensors; Volume 16; Issue 3; Pages: 346

مصطلحات موضوعية: Arabic handwritings, optical character recognition (OCR), handwriting synthesis, digital pens, word segmentation, feature extraction and analysis, Active Shape Model, recognition and interpretation, intelligent systems

الوصف: Document analysis tasks such as pattern recognition, word spotting or segmentation, require comprehensive databases for training and validation. Not only variations in writing style but also the used list of words is of importance in the case that training samples should reflect the input of a specific area of application. However, generation of training samples is expensive in the sense of manpower and time, particularly if complete text pages including complex ground truth are required. This is why there is a lack of such databases, especially for Arabic, the second most popular language. However, Arabic handwriting recognition involves different preprocessing, segmentation and recognition methods. Each requires particular ground truth or samples to enable optimal training and validation, which are often not covered by the currently available databases. To overcome this issue, we propose a system that synthesizes Arabic handwritten words and text pages and generates corresponding detailed ground truth. We use these syntheses to validate a new, segmentation based system that recognizes handwritten Arabic words. We found that a modification of an Active Shape Model based character classifiers—that we proposed earlier—improves the word recognition accuracy. Further improvements are achieved, by using a vocabulary of the 50,000 most common Arabic words for error correction.

وصف الملف: application/pdf

العلاقة: Physical Sensors; https://dx.doi.org/10.3390/s16030346Test

الإتاحة: https://doi.org/10.3390/s16030346Test

المؤلفون: Zaher Al Aghbari, Ayoub Al-Hamadi, Laslo Dinges, Philipp Werner, Sebastian Handrich

المصدر: ANT/EDI40

مصطلحات موضوعية: Facial expression, Computer science, Speech recognition, 0202 electrical engineering, electronic engineering, information engineering, General Earth and Planetary Sciences, 020206 networking & telecommunications, 020201 artificial intelligence & image processing, 02 engineering and technology, Valence (psychology), Valence arousal, General Environmental Science, Arousal

الوصف: We address the problem of emotional state detection from facial expressions. Our proposed approach simultaneously detects faces and predicts both discrete emotion categories and continuous valence/arousal values from raw input images. We train and evaluate our approach on 3 different datasets, compare our approach to other state-of-the-art approaches and perform a cross-database evaluation. In this way, we found, that our approach generalizes well and is suitable for real-time applications.

الوصول الحر: https://explore.openaire.eu/search/publication?articleId=doi_________::99289f4da3184120d7db565388101637Test
https://doi.org/10.1016/j.procs.2020.03.134Test

المؤلفون: Laslo Dinges, Ayoub Al-Hamadi, Zaher Al Aghbari, Thorsten Hempel

المصدر: ISPA

مصطلحات موضوعية: Facial expression recognition, User perception, Action recognition, Context (language use), Valence (psychology), Psychology, Facial recognition system, Task (project management), Arousal, Cognitive psychology

الوصف: Human-Robot Collaboration (HRC) in the context of industrial workflows becomes more and more important. However, cooperation with powerful industrial robots might be problematic for human workers, who could suffer from fear or irritation. In this paper, we use automatically facial expression recognition, which was trained and evaluated on the AffectNet database, to predict the valence and arousal of 48 subjects during an HRC scenario. This covers an assembly task under regular and three kinds of aggravated conditions. The subjects are divided into two groups: The feedback group that gets automatically information according to the new situation and the no-feedback group that does not. We found that while arousal levels remained unaffected, the no-feedback group showed lower valence under aggravated conditions. This effect was compensated in the feedback group.

الوصول الحر: https://explore.openaire.eu/search/publication?articleId=doi_________::02a6fa7f7cd69037fadc45bef80e0aa6Test
https://doi.org/10.1109/ispa52656.2021.9552079Test

المؤلفون: Laslo Dinges, Ayoub Al-Hamadi, Moftah Elzobi, Sherif El-etriby, Ahmed Ghoneim

المصدر: The Scientific World Journal, Vol 2015 (2015)

مصطلحات موضوعية: Technology, Medicine, Science

الوصف: Document analysis tasks, as text recognition, word spotting, or segmentation, are highly dependent on comprehensive and suitable databases for training and validation. However their generation is expensive in sense of labor and time. As a matter of fact, there is a lack of such databases, which complicates research and development. This is especially true for the case of Arabic handwriting recognition, that involves different preprocessing, segmentation, and recognition methods, which have individual demands on samples and ground truth. To bypass this problem, we present an efficient system that automatically turns Arabic Unicode text into synthetic images of handwritten documents and detailed ground truth. Active Shape Models (ASMs) based on 28046 online samples were used for character synthesis and statistical properties were extracted from the IESK-arDB database to simulate baselines and word slant or skew. In the synthesis step ASM based representations are composed to words and text pages, smoothed by B-Spline interpolation and rendered considering writing speed and pen characteristics. Finally, we use the synthetic data to validate a segmentation method. An experimental comparison with the IESK-arDB database encourages to train and test document analysis related methods on synthetic samples, whenever no sufficient natural ground truthed data is available.

وصف الملف: electronic resource

العلاقة: https://doaj.org/toc/2356-6140Test; https://doaj.org/toc/1537-744XTest

الوصول الحر: https://doaj.org/article/e8e05ee9f1724abfb3c68c9f62f40532Test

المؤلفون: Laslo Dinges, Ayoub Al-Hamadi, Moftah Elzobi, Sherif El-etriby, Ahmed Ghoneim

مصطلحات موضوعية: Handwriting Recognition and Text Detection, Computer Vision and Pattern Recognition, Computer Science, Physical Sciences, Automated Reconstruction of Fragmented Objects, Shape Matching and Object Recognition, Handwriting Recognition, Document Image Analysis, Text Detection, Shape Matching, Document Reconstruction, Computer science, Natural language processing, Artificial intelligence, Preprocessor, Ground truth, Segmentation, Unicode, Word group theory, Text segmentation, Handwriting, Skew, Speech recognition, Pattern recognition psychology, Information retrieval, Telecommunications, Philosophy, FOS Philosophy, ethics and religion, Linguistics, FOS Languages and literature

الوصف: Document analysis tasks, as text recognition, word spotting, or segmentation, are highly dependent on comprehensive and suitable databases for training and validation. However their generation is expensive in sense of labor and time. As a matter of fact, there is a lack of such databases, which complicates research and development. This is especially true for the case of Arabic handwriting recognition, that involves different preprocessing, segmentation, and recognition methods, which have individual demands on samples and ground truth. To bypass this problem, we present an efficient system that automatically turns Arabic Unicode text into synthetic images of handwritten documents and detailed ground truth. Active Shape Models (ASMs) based on 28046 online samples were used for character synthesis and statistical properties were extracted from the IESK-arDB database to simulate baselines and word slant or skew. In the synthesis step ASM based representations are composed to words and text pages, smoothed by ... : تعتمد مهام تحليل المستندات، مثل التعرف على النص أو اكتشاف الكلمات أو التجزئة، اعتمادًا كبيرًا على قواعد بيانات شاملة ومناسبة للتدريب والتحقق من الصحة. ومع ذلك، فإن جيلهم مكلف من حيث العمل والوقت. في الواقع، هناك نقص في قواعد البيانات هذه، مما يعقد البحث والتطوير. وينطبق هذا بشكل خاص على حالة التعرف على خط اليد العربي، والذي يتضمن طرقًا مختلفة للمعالجة المسبقة والتجزئة والتعرف، والتي لها مطالب فردية على العينات والحقيقة الأرضية. لتجاوز هذه المشكلة، نقدم نظامًا فعالًا يحول نص يونيكود العربي تلقائيًا إلى صور اصطناعية للوثائق المكتوبة بخط اليد والحقيقة الأرضية التفصيلية. تم استخدام نماذج الشكل النشط (ASMs) بناءً على 28046 عينة عبر الإنترنت لتوليف الأحرف وتم استخراج الخصائص الإحصائية من قاعدة بيانات IESK - arDB لمحاكاة خطوط الأساس وميل الكلمات أو انحرافها. في خطوة التوليف، تتكون التمثيلات القائمة على ASM من الكلمات والصفحات النصية، ويتم تسهيلها من خلال استيفاء B - Spine ويتم تقديمها مع الأخذ في الاعتبار سرعة الكتابة وخصائص القلم. أخيرًا، نستخدم البيانات التركيبية للتحقق من صحة طريقة التقسيم. تشجع المقارنة ...

العلاقة: https://dx.doi.org/10.60692/0vaqx-mv274Test

الإتاحة: https://doi.org/10.60692/gr4nt-bdf0810.60692/0vaqx-mv274Test

المؤلفون: Laslo Dinges, Ayoub Al-Hamadi, Sebastian Handrich, Frerk Saxen, Sven Wachmuth

المصدر: ICSIPA

مصطلحات موضوعية: Facial expression, Computer science, business.industry, 05 social sciences, Pattern recognition, 02 engineering and technology, 050105 experimental psychology, Arousal, ComputingMethodologies_PATTERNRECOGNITION, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, 0501 psychology and cognitive sciences, Artificial intelligence, Valence (psychology), Valence arousal, business, ComputingMethodologies_COMPUTERGRAPHICS

الوصف: We address the problem of facial expression analysis. The proposed approach predicts both basic emotion labels and valence/arousal values as a continuous measure for the emotional state. We train our system on the AffectNet dataset, which shows a high variation of faces, facial expressions and other conditions like illumination and occlusions. Evaluation on the AffectNet dataset and cross-database evaluation on the Aff-Wild dataset shows that our approach predicts emotion categories and valence and arousal values with high accuracies.

الوصول الحر: https://explore.openaire.eu/search/publication?articleId=doi_________::75c3605bda5dbb1da9b30119a375c5a0Test
https://doi.org/10.1109/icsipa45851.2019.8977743Test

المؤلفون: Ehsan Othman, Laslo Dinges, Philipp Werner, Sebastian Handrich, Frerk Saxen, Ayoub Al-Hamadi

المصدر: ISPA

مصطلحات موضوعية: Simple (abstract algebra), Computer science, business.industry, Face (geometry), Preprocessor, Pattern recognition, Artificial intelligence, business, Convolutional neural network, Mobile device

الوصف: In this paper, we propose two simple yet effective methods to estimate facial attributes in unconstrained images. We use a straight forward and fast face alignment technique for preprocessing and estimate the face attributes using MobileNetV2 and Nasnet-Mobile, two lightweight CNN (Convolutional Neural Network) architectures. Both architectures perform similarly well in terms of accuracy and speed. A comparison with state-of-the-art methods with respect to processing time and accuracy shows that our proposed approach perform faster than the best state-of-the-art model and better than the fastest state-of-the-art model. Moreover, our approach is easy to use and capable of being deployed on mobile devices.

الوصول الحر: https://explore.openaire.eu/search/publication?articleId=doi_________::7b659f0e951eeb087a4027e1d3042ca1Test
https://doi.org/10.1109/ispa.2019.8868585Test

المؤلفون: Andreas Nürnberger, Ayoub Al-Hamadi, Moftah Elzobi, Laslo Dinges

المصدر: ICIP

مصطلحات موضوعية: Vocabulary, Arabic, Computer science, media_common.quotation_subject, Feature extraction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, computer.software_genre, Classifier (linguistics), 0202 electrical engineering, electronic engineering, information engineering, media_common, Character (computing), business.industry, 020207 software engineering, Image segmentation, language.human_language, Support vector machine, ComputingMethodologies_PATTERNRECOGNITION, Handwriting recognition, Word recognition, ComputingMethodologies_DOCUMENTANDTEXTPROCESSING, language, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, Natural language processing

الوصف: Comprehensive databases are vital for training and validation of word recognition systems. To overcome the lack of offline databases of Arabic handwritten words, especially regarding the generality of the underlying vocabulary, we used a synthesis system to generate a database of common Arabic handwritings. Subsequently, we validate a new word recognition system on these synthetic handwritings, to analyze the performance of its segmentation, character recognition, and error correction module. We found, that a dynamic character classifier, that is capable to adapted to the variations that are caused by the segmentation, clearly improves word recognition accuracy. For error detection and correction, n-grams as well as the Levenstein distance to a vocabulary of up to 50,000 valid words have been used.

الوصول الحر: https://explore.openaire.eu/search/publication?articleId=doi_________::a609de5afb5f5976e69d44baa7e40a69Test
https://doi.org/10.1109/icip.2017.8296958Test