Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231685
Jihene Tmamna, Emna Ben Ayed, Mounir Ben Ayed
In recent years, the internet of things is getting very popular where it arose in several areas such as education, and healthcare to enhance our live. This popularity has led to an increase number of IoT devices and thus generates massive volume of data. However, this data requires efficient methods of analysis to provide intelligent services. Recently, the deep learning can meet the requirements of IoT data analysis by providing techniques for large scale data analysis and meaningful feature extraction. The deep learning implementation is traditionally delivered to cloud computing due to its high compute resources provisioning. However, given the sheer volume of IoT data, the cloud computing fall to meet the IoT requirements, it presents many issues in term of time response, large data transmission, energy consumption, etc. To address this challenges the fog computing, new layer between cloud computing and internet of things devices, appears. So, moving the implementation of deep learning to fog computing can achieve the requirements of internet of things systems and enhance their performances. In this paper, we introduce deep learning for internet of things, next the application of deep learning in internet of things. We address fog computing for the internet of things. Finally, we present the deep learning in fog computing.
{"title":"Deep learning for internet of things in fog computing: Survey and Open Issues","authors":"Jihene Tmamna, Emna Ben Ayed, Mounir Ben Ayed","doi":"10.1109/ATSIP49331.2020.9231685","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231685","url":null,"abstract":"In recent years, the internet of things is getting very popular where it arose in several areas such as education, and healthcare to enhance our live. This popularity has led to an increase number of IoT devices and thus generates massive volume of data. However, this data requires efficient methods of analysis to provide intelligent services. Recently, the deep learning can meet the requirements of IoT data analysis by providing techniques for large scale data analysis and meaningful feature extraction. The deep learning implementation is traditionally delivered to cloud computing due to its high compute resources provisioning. However, given the sheer volume of IoT data, the cloud computing fall to meet the IoT requirements, it presents many issues in term of time response, large data transmission, energy consumption, etc. To address this challenges the fog computing, new layer between cloud computing and internet of things devices, appears. So, moving the implementation of deep learning to fog computing can achieve the requirements of internet of things systems and enhance their performances. In this paper, we introduce deep learning for internet of things, next the application of deep learning in internet of things. We address fog computing for the internet of things. Finally, we present the deep learning in fog computing.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"11 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132870272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231611
Nadia Smaoui Zghal, I. Kallel
Malignant melanoma is considered one of the terrible disorders causing death. The goal of the modern dermatology is the early screening of skin cancer, aiming at reducing the mortality rate with less extensive treatment. In this context, this work focuses on the problem of an automatic melanoma diagnosis. The proposed approach uses unsupervised robustness of deep learning to extract significant characteristics from pixels of the images. A preprocessing step is used to remove unwanted artifacts and to improve the contrast of the images. Then, features are extracted by a deep Sparse Auto-encoder. Finally, the classifier Support Vector Machine (SVM) is used to distinguish respectively between three populations which are Melanoma, suspicious cases, and non-melanoma. For evaluation, we test the proposed approach using images from the PH2 dataset. The results show remarkable performance in terms of specificity, sensitivity, and accuracy.
{"title":"An effective approach for the diagnosis of melanoma using the sparse auto-encoder for features detection and the SVM for classification","authors":"Nadia Smaoui Zghal, I. Kallel","doi":"10.1109/ATSIP49331.2020.9231611","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231611","url":null,"abstract":"Malignant melanoma is considered one of the terrible disorders causing death. The goal of the modern dermatology is the early screening of skin cancer, aiming at reducing the mortality rate with less extensive treatment. In this context, this work focuses on the problem of an automatic melanoma diagnosis. The proposed approach uses unsupervised robustness of deep learning to extract significant characteristics from pixels of the images. A preprocessing step is used to remove unwanted artifacts and to improve the contrast of the images. Then, features are extracted by a deep Sparse Auto-encoder. Finally, the classifier Support Vector Machine (SVM) is used to distinguish respectively between three populations which are Melanoma, suspicious cases, and non-melanoma. For evaluation, we test the proposed approach using images from the PH2 dataset. The results show remarkable performance in terms of specificity, sensitivity, and accuracy.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129429590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231723
Hana Ben Fredj, Souhir Sghaier, C. Souani
Face detection is a highly efficient component in diverse domains such as security surveillance. Especially, the Viola-Jones algorithm has achieved significant performances in the field of detection face. In the last years, graphics processors have fast become the mainstay to solve the problem of detection face applications and to accelerate data parallel computing. This is due to their flexibility, and in particular, to the single-instruction, multiple-data execution model exploited for streaming processors by a Graphics Processing Unit (GPU). Therefore, in this paper, the researchers develop a robust face detection implementation based on the GPU component. The implementation has been optimized by following up a strategy to use the different memory resources in GPU and the warp scheduler technique, so as to accelerate the access to the memory, with better exploitation of resources proved by GPU. The results display that the suggested method is very important and consumes less execution time compared with the standard implementation and sequential implementation.
{"title":"An Efficient Parallel Implementation of Face Detection System Using CUDA","authors":"Hana Ben Fredj, Souhir Sghaier, C. Souani","doi":"10.1109/ATSIP49331.2020.9231723","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231723","url":null,"abstract":"Face detection is a highly efficient component in diverse domains such as security surveillance. Especially, the Viola-Jones algorithm has achieved significant performances in the field of detection face. In the last years, graphics processors have fast become the mainstay to solve the problem of detection face applications and to accelerate data parallel computing. This is due to their flexibility, and in particular, to the single-instruction, multiple-data execution model exploited for streaming processors by a Graphics Processing Unit (GPU). Therefore, in this paper, the researchers develop a robust face detection implementation based on the GPU component. The implementation has been optimized by following up a strategy to use the different memory resources in GPU and the warp scheduler technique, so as to accelerate the access to the memory, with better exploitation of resources proved by GPU. The results display that the suggested method is very important and consumes less execution time compared with the standard implementation and sequential implementation.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130155942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231755
I. Chourib, G. Guillard, M. Mestiri, B. Solaiman, I. Farah
This article attempts to provide an overview of the basic concepts, structure and terms related to case-based reasoning, because we aim to work on an evolution of the CBR process which allows us to integrate the knowledge base, ensure the consistency of information, integrate the modes of reasoning: similarity, classification and hybrid. In addition, this article discusses the concept and issues related to similarity measure, which is very important in medical system and using it allows to reduce the risks of health error for patients. However, it seems very complex because the measure of similarity must take into account the diversity of the types of information (qualitative, textual, quantitative, etc.) for each patient. And at the end, we represent an evaluation of similarity measure which was applied in (GS.52).
{"title":"Case-Based Reasoning: Problems And Importance Of Similarity Measure","authors":"I. Chourib, G. Guillard, M. Mestiri, B. Solaiman, I. Farah","doi":"10.1109/ATSIP49331.2020.9231755","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231755","url":null,"abstract":"This article attempts to provide an overview of the basic concepts, structure and terms related to case-based reasoning, because we aim to work on an evolution of the CBR process which allows us to integrate the knowledge base, ensure the consistency of information, integrate the modes of reasoning: similarity, classification and hybrid. In addition, this article discusses the concept and issues related to similarity measure, which is very important in medical system and using it allows to reduce the risks of health error for patients. However, it seems very complex because the measure of similarity must take into account the diversity of the types of information (qualitative, textual, quantitative, etc.) for each patient. And at the end, we represent an evaluation of similarity measure which was applied in (GS.52).","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131047620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231880
Taissir Fekih Romdhane, R. Ouni, Mohamed Atri
An Electrocardiogram (ECG) records the electrical activity of the heart to locate the abnormalities. ECG signal processing is an emerging tool for the cardiologists in medical diagnosis for effective treatments. Many researches focus on how to improve preprocessing and processing algorithms in order to classify ECG signals with low cost and high accuracy. These algorithms consist of removing all types of noise that contaminate the ECG recording as well as extracting the most important features. In this paper, we present a useful Matlab GUI to analyze and classify ECG signal using efficient preprocessing and processing techniques. These techniques allow acquiring ECG recorders from various universal cardiac databases, filtering them using Butterworth low pass filter and IIR notch filter and extracting the most important cardiac features based on discrete wavelet transform db6.
{"title":"Multidatabase ECG signal processing","authors":"Taissir Fekih Romdhane, R. Ouni, Mohamed Atri","doi":"10.1109/ATSIP49331.2020.9231880","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231880","url":null,"abstract":"An Electrocardiogram (ECG) records the electrical activity of the heart to locate the abnormalities. ECG signal processing is an emerging tool for the cardiologists in medical diagnosis for effective treatments. Many researches focus on how to improve preprocessing and processing algorithms in order to classify ECG signals with low cost and high accuracy. These algorithms consist of removing all types of noise that contaminate the ECG recording as well as extracting the most important features. In this paper, we present a useful Matlab GUI to analyze and classify ECG signal using efficient preprocessing and processing techniques. These techniques allow acquiring ECG recorders from various universal cardiac databases, filtering them using Butterworth low pass filter and IIR notch filter and extracting the most important cardiac features based on discrete wavelet transform db6.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125866621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231719
Kawther Benharrath, B. Khaddoumi, M. Sayadi, H. Rix, Olivier Meste, J. Lebrun, S. Guetat, M. Magnié-Mauro
This paper deals with the diagnosis of intellectual precocity in gifted children (GC) cases. The P300 component is usually used for giftedness identification. By the use of empirical mode decomposition (EMD), a significant P300 detection is obtained through electroencephalogram signals (EEG). The novelty of the proposed work is to speed up the intellectual ability characterization based on statistical features extraction from P300 response. In order to get an optimized number of estimated information, a selection technique based on the characterization degree criterion (CD-J) is then introduced. This allows a considerably computing time decreasing and an excessive performance of the achieved results. Besides that, the proposed analysis method is applied on (GC) dataset, covering a parental relationship. Compared to the previous works, the proposed approach seems to be promising and useful for the characterization children and their diagnostic improvement.
{"title":"Feature Optimization for Gifted Children Diagnosis","authors":"Kawther Benharrath, B. Khaddoumi, M. Sayadi, H. Rix, Olivier Meste, J. Lebrun, S. Guetat, M. Magnié-Mauro","doi":"10.1109/ATSIP49331.2020.9231719","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231719","url":null,"abstract":"This paper deals with the diagnosis of intellectual precocity in gifted children (GC) cases. The P300 component is usually used for giftedness identification. By the use of empirical mode decomposition (EMD), a significant P300 detection is obtained through electroencephalogram signals (EEG). The novelty of the proposed work is to speed up the intellectual ability characterization based on statistical features extraction from P300 response. In order to get an optimized number of estimated information, a selection technique based on the characterization degree criterion (CD-J) is then introduced. This allows a considerably computing time decreasing and an excessive performance of the achieved results. Besides that, the proposed analysis method is applied on (GC) dataset, covering a parental relationship. Compared to the previous works, the proposed approach seems to be promising and useful for the characterization children and their diagnostic improvement.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122227745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231773
M. Yahia, Tarig Ali, M. Mortula
Speckle reduction in synthetic aperture radar (SAR) images and SAR polarimetry (PolSAR) is important for the extraction of important information for homogeneous extended areas. Finding good balance between spatial detail preservation and high equivalent number of looks is a challenge. In this paper, we validate the use of the infinite number of looks filter (INLP) method for the denoising of the multipolarization channels (i. e. hh, hv and vv) by representing their analogy with the eingenvalues of the coherency matrix. The denoised pixels obtained by a traditional filtering method served as inputs for the INLP method. Results demonstrated that the proposed method outperformed traditional filters i. e. boxcar and the refined sigma filter in terms of spatial detail preserving and speckle reduction.
{"title":"Speckle Denoising of the Multipolarization Images by Hybrid Filters","authors":"M. Yahia, Tarig Ali, M. Mortula","doi":"10.1109/ATSIP49331.2020.9231773","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231773","url":null,"abstract":"Speckle reduction in synthetic aperture radar (SAR) images and SAR polarimetry (PolSAR) is important for the extraction of important information for homogeneous extended areas. Finding good balance between spatial detail preservation and high equivalent number of looks is a challenge. In this paper, we validate the use of the infinite number of looks filter (INLP) method for the denoising of the multipolarization channels (i. e. hh, hv and vv) by representing their analogy with the eingenvalues of the coherency matrix. The denoised pixels obtained by a traditional filtering method served as inputs for the INLP method. Results demonstrated that the proposed method outperformed traditional filters i. e. boxcar and the refined sigma filter in terms of spatial detail preserving and speckle reduction.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114388842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231884
J. Gastellu-Etchegorry, Y. Wang, O. Regaieg, T. Yin, Z. Malenovský, Z. Zhen, X. Yang, Z. Tao, L. Landier, A. Al Bitar, Deschamps, N. Lauret, J. Guilleux, E. Chavanon, B. Cao, J. Qi, A. Kallel, Z. Mitraka, N. Chrysoulakis, B. Cook, D. Morton
Remote sensing (RS) dedicated to the study of land surfaces benefits from more and more advanced sensors. However, the interpretation of RS data is often is often inaccurate due to the complexity of the observed land surfaces. Therefore, RS models, in particular physical models, that simulate RS observations of the three-dimensional (3D) landscapes are critical to correctly interpret RS data. DART is one of the most comprehensive 3D models of Earthatmosphere optical radiative transfer (RT), from ultraviolet (UV) to thermal infrared (TIR). It simulates the optical signal of proximal, aerial and satellite imaging spectrometers and laser scanners, the 3D RB and solar-induced chlorophyll fluorescence (SIF) signal, for any urban or natural landscape and any experimental or instrument configuration. It is freely available for research and teaching activities (dart.omp.eu). After illustrating three significant sources of inaccuracy in RS interpretation, five recent DART advances are presented: RT in the atmosphere and topography, fast RS image simulation of large landscapes, SIF modelling, and satellite image inversion.
{"title":"Why To Model Remote Sensing Measurements In 3d? Recent Advances In Dart: Atmosphere, Topography, Large Landscape, Chlorophyll Fluorescence And Satellite Image Inversion","authors":"J. Gastellu-Etchegorry, Y. Wang, O. Regaieg, T. Yin, Z. Malenovský, Z. Zhen, X. Yang, Z. Tao, L. Landier, A. Al Bitar, Deschamps, N. Lauret, J. Guilleux, E. Chavanon, B. Cao, J. Qi, A. Kallel, Z. Mitraka, N. Chrysoulakis, B. Cook, D. Morton","doi":"10.1109/ATSIP49331.2020.9231884","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231884","url":null,"abstract":"Remote sensing (RS) dedicated to the study of land surfaces benefits from more and more advanced sensors. However, the interpretation of RS data is often is often inaccurate due to the complexity of the observed land surfaces. Therefore, RS models, in particular physical models, that simulate RS observations of the three-dimensional (3D) landscapes are critical to correctly interpret RS data. DART is one of the most comprehensive 3D models of Earthatmosphere optical radiative transfer (RT), from ultraviolet (UV) to thermal infrared (TIR). It simulates the optical signal of proximal, aerial and satellite imaging spectrometers and laser scanners, the 3D RB and solar-induced chlorophyll fluorescence (SIF) signal, for any urban or natural landscape and any experimental or instrument configuration. It is freely available for research and teaching activities (dart.omp.eu). After illustrating three significant sources of inaccuracy in RS interpretation, five recent DART advances are presented: RT in the atmosphere and topography, fast RS image simulation of large landscapes, SIF modelling, and satellite image inversion.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131885198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/atsip49331.2020.9231647
{"title":"ATSIP 2020 Cover Page","authors":"","doi":"10.1109/atsip49331.2020.9231647","DOIUrl":"https://doi.org/10.1109/atsip49331.2020.9231647","url":null,"abstract":"","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123208833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231801
A. Zaafouri, M. Sayadi
In this paper, a new automatic method for expiration code of medical products using convolutional neural network (CNN) is presented. The input image is enhanced using unsharp masking method. Then the image is binarized using local adaptive thresholding technique (LATT) and thinned using morphological operator. Also, characters of the image are extracted using bounding box technique. Finally, a set of characters (A-Z) and digits (0-9) is boiled. The dataset of characters feed an adopted architecture of CNN in order to recognize expiration code of the medication. The proposed approach is tested on large datasets of characters under various conditions of complexities. The experimental results demonstrate the robustness of our approach. The developed system achieves approximately 93% accuracy on character recognition.
{"title":"Medication Code Recognition using Convolutional Neural Network","authors":"A. Zaafouri, M. Sayadi","doi":"10.1109/ATSIP49331.2020.9231801","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231801","url":null,"abstract":"In this paper, a new automatic method for expiration code of medical products using convolutional neural network (CNN) is presented. The input image is enhanced using unsharp masking method. Then the image is binarized using local adaptive thresholding technique (LATT) and thinned using morphological operator. Also, characters of the image are extracted using bounding box technique. Finally, a set of characters (A-Z) and digits (0-9) is boiled. The dataset of characters feed an adopted architecture of CNN in order to recognize expiration code of the medication. The proposed approach is tested on large datasets of characters under various conditions of complexities. The experimental results demonstrate the robustness of our approach. The developed system achieves approximately 93% accuracy on character recognition.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121253379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：