|Degree Name||Group/Major Subject||Board/Institute||Country||Passing Year|
|No education information is found|
|Award Type||Award Title||Year||Country||Description|
|No award information is found|
|Building Extraction; Lidar Data; Machine Learning; Image Processing|
|Level of Study||Title||Supervisor||Co-Supervisor(s)||Name of Student(s)||Area of Research||Current Completion|
|Masters||Aspect extraction from bangla reviews using convolutional neural network||Emon Kumar Dey||Md. Atikur Rahman||
The extensive customer reviews on the web assist customers for purchase-decision-making as well as providers for business planning. Summarization of reviews is desirable as reading all reviews is not feasible to evaluate properly. To find aspect categories from reviews is a sub-task of summarization known as Aspect Based Sentiment Analysis (ABSA). In this paper, we present two Bangla datasets to perform ABSA task. We collected user comments on cricket game and annotated manually. The other dataset consists of consumer reviews of restaurants. A model to extract aspect categories based on Convolutional Neural Network (CNN) is presented. The model shows the convincing performance of the proposed datasets compared to the conventional classifiers.
|Masters||Bilateral Histogram Equalization for Contrast Enhancement||Emon Kumar Dey||Feroz Mahmud Amil||
As image enhancement is a well-discussed issue, various methods have already been proposed to date. Some of these methods perform well for specific applications but most of the techniques suffer from artifacts due to the over or under enhancement. To mitigate this problem a new technique namely Bilateral Histogram Equalization for contrast enhancement (BHE) which uses the Harmonic mean of the image to divide the histogram is introduced. BHE is evaluated in both qualitative and quantitative manner and the results show that BHE creates fewer artifacts on several standard images than other existing state-of-the-art image enhancement techniques.
|Masters||Garments Design Class Identification Using Deep Learning||Emon Kumar Dey||S M Sofiqul Islam||
Automatic garments design class identification for recommending the fashion trends is important nowadays because of the rapid growth of online shopping. By learning the properties of images efficiently, a machine can give better accuracy of classification. Several methods, based on Hand-Engineered feature coding exist for identifying garments design classes. But, most of the time, those methods do not help to achieve better results. Recently, Deep Convolutional Neural Networks (CNNs) have shown better performances for different object recognition. Deep CNN uses multiple levels of representation and abstraction that help a machine to understand the types of data (images, sound, and text) more accurately. In this paper, we have applied deep CNN for identifying garments design classes. To evaluate the performances, we used two well-known CNN models AlexNet and VGGNet on two different datasets. We also propose a new CNN model based on AlexNet and found better results than existing state-of-the-art by a significant margin
|Subject||Project Name||Source of Fund||From Date||To Date||Collaboration|
|No project/research work is found|
|No invited talk is found|
|SL||Collaboration & Membership Name||Type||Membership Year||Membership Expire Year|
|No Collaboration & Membership is found|
|Title||Organization||Location||From Date||To Date||Description|
|Assistant Professor||Institute of Information Technology, University of Dhaka||Dhaka, Bangladesh||18-09-2015||Currently Working||
At present on leave
Emon Kumar Dey, Fayez Tarsha Kurdi, Mohammad Awrangjeb and Bela Stantic : Effective Selection of Variable Point Neighbourhood for Feature Point Extraction from Aerial Building Point Cloud Data, Remote Sesnsing, (impact factor:4.509) vol.13, no.8 pp.1520, 2021 .
Emon Kumar Dey, Mohammad Awrangjeb and Bela Stantic : Outlier detection and robust plane fitting for building roof extraction from LiDAR data, International Journal of Remote Sensing, (impact factor:2.976) vol.41, pp.6325--6354, 2020 .
Emon Kumar Dey and Mohammad Awrangjeb : A Robust Performance Evaluation Metric for Extracted Building Boundaries From Remote Sensing Data, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, (impact factor:3.827) vol.13, pp.4030-4043, 2020 .
Emon Kumar Dey and Md Atikur Rahman : Datasets for aspect-based sentiment analysis in bangla and its baseline evaluation, Data, (impact factor:citescore 3.5) vol.3, pp.15, 2018 .
Emon Kumar Dey, S M Shofiqul Islam, Md Nurul Ahad Tawhid and B M Mainul Islam : A CNN Based Approach for Garments Texture Design Classification, Advances in Technology Innovation, vol.2, pp.119, 2017 .
Emon Kumar Dey, Feroz Mahmud Amil, Shanto Rahman and Md. Mostafijur Rahman : Bilateral Histogram Equalization for Contrast Enhancement, International Journal of Software Innovation, 2016 .
Emon Kumar Dey, Md Nurul Ahad Tawhid and Mohammad Shoyaib : An automated system for garment texture design class identification, Computers, (impact factor:Citescore 3.3) vol.4, no.3 pp.265--282, 2015 .
Emon Kumar Dey; Mohammad Awrangjeb; Bela Stantic "An Unsupervised Outlier Detection Method For 3D Point Cloud Data." IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2019. , pp. 2495--2498. Japan: IEEE, 2019 .
Emon Kumar Dey "Application of deep learning to computer vision: A comprehensive study." 5th international conference on informatics, electronics and vision (ICIEV , pp. 592--597. IEEE, 2016 .
Emon Kumar Dey "Chest X-ray analysis to detect mass tissue in lung." International Conference on Informatics, Electronics & Vision (ICIEV) 2014 .