2022 2nd International Conference on Image Processing and Robotics (ICIPRob)最新文献

{"title":"Converting high resolution multi-lingual printed document images in to editable text using image processing and artificial intelligence","authors":"H. Premachandra, A. Jayakody, H. Kawanaka","doi":"10.1109/ICIPRob54042.2022.9798739","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798739","url":null,"abstract":"The optical character recognition technique is used to convert information, mainly printed or handwritten text in paper materials, into an electronic format that the computers can edit. According to the literature, there are few competent OCR systems for recognizing multilingual characters in the form of Sinhala and English characters together. The lack of an appropriate technology to recognize multilingual text still remains as a problem that the current research community must address, and it has been designated as the key problem for this study. The main goal of this research is to develop a multilingual character recognition system that uses character image geometry features and Artificial Neural Networks to recognize printed Sinhala and English scripts together. It is intended that the solution would be improved to cover three Sri Lanka’s most commonly spoken languages, with the addition of Tamil as a later upgrade. The primary technologies for this study were character geometry features and Artificial Neural Networks. At the moment almost an 85% of success rate has been achieved with a database containing around 800 images, which are divided into 46 characters (20 Sinhala and 26 English), and each character is represented in 20 different forms of character images. Recognition of text from printed bi-lingual documents is experimented by extracting individual character data from such printed text documents and feeding them to the system.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125177145","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}

{"title":"Pulsar Candidate Selection Using Gaussian Hellinger Extremely Fast Decision Tree","authors":"Venoli Gamage, Mohamed Ayoob, Krishnakripa Jayakumar","doi":"10.1109/ICIPRob54042.2022.9798721","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798721","url":null,"abstract":"Radio wave data gathered by pulsar finding telescopes are required to be classified while being streamed. The reason for that is the practical constraints of traditional machine learning algorithms on streaming datasets. Traditional machine learning algorithms would take considerable compute power, memory and time to give pragmatic results.(recent surveys collect data at the rate of 0.5 – 1 terabyte per second) Stream classification algorithms are specifically developed to address the above limitations and can classify data streams without taking up a lot of memory or training time. They relate with characteristics of data streams such as concept drift and limited memory. Extremely Fast Decision Tree is one of the stream classification algorithms that can learn incrementally when it sees new data. However, data from pulsar detecting datastreams are highly imbalanced (there are less examples of pulsars in the data than non-pulsar objects). Learning incrementally from such a datastream would be a destructive interference for the model’s precision (of detecting pulsars). In this research, we introduce an improved version of the Extremely Fast Decision Tree, that is able to learn imbalanced data streams. Our approach is fast, accurate, and avoids the pitfalls of class imbalance and concept drift.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131273724","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}

{"title":"Theatrical Robotic Actor Developed Using the Interpersonal Communication Principles","authors":"U. Manawadu, J. Perera, D. A. A. Deepal, W.A.R. Fernando, P. R. D. De Silva","doi":"10.1109/ICIPRob54042.2022.9798455","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798455","url":null,"abstract":"Stage drama is a unique literary form because they are designed to be acted out on a stage before an audience. Among the key elements of a drama, acting is without a doubt the most important of the most essential element. For a drama to be more successful, it should consist of naturalism, realistic interactions, better coordination, and high engagement. Through the evolution of robots, a great milestone remarks the rise of robotic actors where robots have stepped the live theatre. In this study, it was identified that interpersonal communication principles are a major source to be utilized which unwittingly helps in building strong bonds between humans. This paper describes, developing a theatrical robotic actor using the principles of interpersonal communication which comprises the key behaviors of the robotic actor that are best suited in response to the human actor’s behaviors in a theatrical play that will result in human actor-like behavior in the live theatre. The experiment of the study was designed using three approaches. Through the results of this study, it was concluded that the robotic actor designed by following interpersonal communication key principles is capable of having better coordination and realistic interactions with the human actor and the play was more natural and realistic. In addition, this research has developed a novel concept of making theatrical robotic actors that emphasizes human actor-like behavior in live theater.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125238629","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}

{"title":"ANDTi Virtual Assistant","authors":"M. I. F. Nihla, Wr Arachchi, K.G. Dilini Subhani, D.K.G.M. Dissanayaka, W.T. Sanduni, W. Rankothge, P.N. Wariyapperuma, P. Kehelella","doi":"10.1109/ICIPRob54042.2022.9798736","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798736","url":null,"abstract":"Due of the current COVID-19 pandemic crises, there is a worldwide need for quick medical findings. Furthermore, due to a lack of medical facilities and medical practitioners’ hectic schedules, several examinations must now be performed by the general public. Also because of the high rate of transmissibility of COVID-19, even asymptomatic patients can readily transfer the virus to others, faster detection is critical during the initial phase of COVID-19, which is early identification. The earlier a patient is detected; the better the virus’s spread may be stopped and the patient can undergo proper treatment. As the nationwide vaccination process is in its later part, it is obvious that the government will uplift its regulations and the employees will have to return to their workplaces or offices. As a solution to this upcoming urgency the authors would like to propose a solution to identify COVID- 19 patients in advance at corporate level. As an IoT based solution a device is supposed to be setup on top of each employee’s desk, which in return will be used to monitor the oxygen level, temperature, and heartbeat rate of the employees.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129962599","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}

{"title":"Multiclass-Classification of Algae using Dc-GAN and Transfer Learning","authors":"Abdullah, Ziaullh Khan, W. Mumtaz, A. Mumtaz, Subrata Bhattacharjee, Hee-Cheol Kim","doi":"10.1109/ICIPRob54042.2022.9798730","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798730","url":null,"abstract":"The growth of algae is a natural process and highly increase in concentration has a bad impact on water bodies as well as other creatures. The monitoring and classification of algae by using the traditional method is a tedious and time-consuming task. The reliable and robust development of the alternative method is crucial to do these tasks, however, advanced machine learning, computer vision, and deep learning are excessively used to address this problem. In this paper, we have used the transfer learning technique, in which various pre-train models are used to train on our custom dataset. We conducted a series of experiments to classify genera of harmful algae bloom (HAB). Furthermore, we compare each pre-train architecture performance on our unique dataset. As the transfer learning model needs more data to train it, we used a direct generative adversarial network (Dc-GAN) to enhance the quantity of data. In this work the four popular pre-train models are used, namely, VGG-16, Alex Net, Google Net, and ResNet-18. Among these, the ResNet-18 model performed well with the highest accuracy of 97.10%. The transfer learning model approach would be an effective tool for rapid operational response to algae bloom events. The experimental results show that the transfer learning method is more effective and reliable to detect and classify algae.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123230905","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}

{"title":"Design and Implementation an IoT Based Smart Traffic System Using Renewable Energy Sources","authors":"Sakibur Rahman Kazemee, M. Mahmud, Yasin Rahman, Md Azmaeen Rahman Khan, B. B. Pathik, M. Kabiruzzaman","doi":"10.1109/ICIPRob54042.2022.9798731","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798731","url":null,"abstract":"Congestion in the streets is a big issue in many countries. Traffic congestion has been caused by signal failure, poor law enforcement, and inefficient traffic management. One of the biggest issues in many countries is that the existing infrastructure cannot be expanded further, leaving only better traffic management as an option. Overcrowding has a negative economic impact, on the environment, and on the general quality of life. As a result, it is past time to address the traffic congestion issue efficiently. For traffic control, visual data analysis, IR sensors, inductive loop detection, remote monitoring, and other methods are available. The problem of traffic congestion has had a significant impact on the country’s transportation system. This creates a slew of issues, particularly when there are emergency situations at traffic signal junctions, which are always congested. To address these issues, a traffic light controller system was created using renewable energy. When the system received a radio frequency (RF) transmission signal from an emergency vehicle, the speaker was triggered, and the traffic police were notified. The road was thereafter cleared by the traffic police. This technique will decrease accidents that occur frequently at traffic light crossings since other vehicles must congregate in order for an emergency vehicle to be given a unique route. This system was designed to run when it received a radio frequency (RF) transmission signal from an emergency vehicle, then the speaker was activated, also notifying the traffic police by the server. We include many features of a smart traffic system, such as voice announcement for ambulances with radio frequency, renewable energy source, extra power supply for residential areas, overspeed protection system, automatic street lights only for night time, pressure sensor traffic manual system, accident tracking and sending SMS with the accident location, local server, and global application/IoT base. Traffic congestion will be decreased as a result of the use of this innovative technology. Bottlenecks will be spotted early, allowing for early preventative steps to be performed, saving the driver time and money.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130090298","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}

{"title":"Deep Learning Models for Emotion Classification in Human Robot Interaction Platforms","authors":"Jose Balbuena, Cesar Beltran","doi":"10.1109/ICIPRob54042.2022.9798741","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798741","url":null,"abstract":"Human Robot Interaction (HRI) main purpose is to improve the communication between robots and people, in special the service robots which principal function is interacting with users. Service robots could be virtual or physical, such as a chatbot or humanoid robot. The increase of internet access and the use of online services have produced an exponentially use of chatbots. This situation generate people spending more time using this technology and trying to humanize it. Therefore, giving robots emotional capabilities have become an important issue in the field. For this reason, the purpose of this article is to analyzed and compared the performance of common deep learning techniques (CNN, RNN) that could be used as a emotion classifier for HRI platforms such a chatbots or humanoid robots. Two kind of input signals were evaluated: text and images of faces. In addition, different metrics were selected to evaluate the accuracy and time performance of the models.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128605924","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}

{"title":"ICIPRoB2022 Conference Program","authors":"","doi":"10.1109/iciprob54042.2022.9798454","DOIUrl":"https://doi.org/10.1109/iciprob54042.2022.9798454","url":null,"abstract":"","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"2012 22","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121007735","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}

{"title":"Border Control by Multi-biometric Identification using Face and Ear images","authors":"Susara S. Thenuwara, C. Premachandra, H. Kawanaka","doi":"10.1109/ICIPRob54042.2022.9798746","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798746","url":null,"abstract":"Biometrics are critical authorization method in border control areas such as airports. This study explores the usage of the ear and face biometric for verification at the physical appearance of the border points and indicates experimental results collected on a newly made database containing four hundred and twenty images. The images have been taken through a quality module for the purpose of reducing the False Rejection Rate. The approach that was used is The Principal Component Analysis (PCA) that is “eigen ear” for obtaining the recognition rate of 89.3%. After the ear was fused with face biometric, there was an improvement in the recognition. The fusion is done at the level of decision making, hitting a recognition of 97.1%, which is an improvement of 8.2%.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128451961","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}

{"title":"Machine learning based classification of ripening and decay stages of Mango (Mangifera indica L.) cv. Tom EJC","authors":"H. M. W. M. Hippola, Deepika Priyadarshani Wadumesthri, R. Rajakaruna, Lasith Yasakethu, M. Rajapaksha","doi":"10.1109/ICIPRob54042.2022.9798722","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798722","url":null,"abstract":"Tom EJC is a variety of Mango grown in tropical countries like Sri Lanka and India which has a very large demand and hence expensive. From the early stage of ripening, until the senescence stage, the process takes around 10–14 days. The fruit shows a yellowish color starting from the very early stage of ripening, throughout the period until it reaches the senescence stage. Unlike the other Mango varieties, it is difficult for a regular customer to determine the stage of ripening of the Tom EJC fruit, by observation. This paper focuses towards developing a vision-based classifier to rapidly identify ripening and decay stages of Tom EJC mango using surface image captures. A dataset of Tom EJC mango images was collated at different maturity levels. A Convolutional Neural Network (CNN) is proposed and tested using over 6000 Tom EJC images. The proposed model is shown to have a 76% testing accuracy in identifying four stages of maturity.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114815627","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}