Rahmatri Mardiko | University of Maryland, College Park (original) (raw)

Uploads

Papers by Rahmatri Mardiko

Research paper thumbnail of Evaluation of Singular Value Decomposition based Digital Image Watermarking with Dither Quantization and Edge Detection

Makara Seri Sains, 2010

Evaluation of Singular Value Decomposition based Digital Image Watermarking with Dither Quantizat... more Evaluation of Singular Value Decomposition based Digital Image Watermarking with Dither Quantization andEdge Detection. The use of singular value decomposition (SVD) in watermarking area has been developed by manyresearchers. In this paper, we describe our evaluation result against an SVD based watermarking scheme with Ditherquantization and edge detection proposed by Mohan et al. As an evaluation benchmark, we use StirMark to producemodified images by various image attacks. The extracted watermarks from these images were compared with theoriginal watermark by calculating its bit correlation ratio (BCR). The result shows that the scheme is robust againstJPEG compression, rotation, scaling, and PSNR attack. The scheme is also quite robust to some extents against removelineattack and cropping.

Research paper thumbnail of Resolving Occlusion in Multi-Object Tracking through Integrated Fuzzy Similarity Measure

Abstract-- In multi-object tracking, occlusion is a situation where part of an object is covered ... more Abstract-- In multi-object tracking, occlusion is a situation where part of an object is covered by another object or any structure in the video scene. It is a very common problem in multi-object tracking for real world video scenes and is a cause for poor tracking performance. Considering its significance and inevitability, this problem has been a subject of numerous papers about multi-object tracking. In this paper, a method for occlusion handling based on fuzzy approach is proposed. Fuzzy techniques are used here as they can deal with uncertainty and imprecision which are inherent in image/video processing. The method consists of feature extraction, fuzzy feature representation, merge-split event detection, and track resolution. The main contribution of this paper is in the use of fuzzy similarity measure together with fuzzy integral for resolving object tracks after occlusion. The similarity measure is performed separately on color, texture, and shape after representing them as ...

Research paper thumbnail of Resolving Occlusion in Multi-Object Tracking through Integrated Fuzzy Similarity Measure

In multi-object tracking, occlusion is a situation where part of an object is covered by another ... more In multi-object tracking, occlusion is a situation where part of an object is covered by another object or any structure in the video scene. It is a very common problem in multi-object tracking for real world video scenes and is a cause for poor tracking performance. Considering its significance and inevitability, this problem has been a subject of numerous papers about multi-object tracking. In this paper, a method for occlusion handling based on fuzzy approach is proposed. Fuzzy techniques are used here as they can deal with uncertainty and imprecision which are inherent in image/video processing. The method consists of feature extraction, fuzzy feature representation, merge-split event detection, and track resolution. The main contribution of this paper is in the use of fuzzy similarity measure together with fuzzy integral for resolving object tracks after occlusion. The similarity measure is performed separately on color, texture, and shape after representing them as fuzzy featu...

Research paper thumbnail of Protagoras: A Service for Tagging E-Commerce Products at Scale

2018 International Conference on Advanced Computer Science and Information Systems (ICACSIS), 2018

Despite widespread adoption of machine learning to solve real world problems, the implementation ... more Despite widespread adoption of machine learning to solve real world problems, the implementation of ML solutions in production environment is more complicated than it seems. It is quite straightforward to write machine learning codes these days but they are not designed to be deployed in production scale where millions of requests per day is a norm. In this paper, we describe our implementation of a ML service for large scale product tagging in e-commerce called Protagoras. The problem of tagging products can be seen as multi-label classification where the labels are product tags. By performing the classification within each product category, the precision can be increased and the inference can be performed faster. Protagoras combined the scalability and speed of microservice implementation in Golang and robust machine learning implementation in Python. We present the architecture of the system with all its components including API endpoints, job queue, database, and monitoring. The...

Research paper thumbnail of Watermarking pada Video : Robustness , Impercetibility dan Pendekatan untuk Domain Terkompresi

ABSTRAK Meningkatnya penggunaan dokumen digital khususnya multimedia (citra, audio, video) dan ke... more ABSTRAK Meningkatnya penggunaan dokumen digital khususnya multimedia (citra, audio, video) dan kemudahan transmisi data melalui Internet meningkatkan kebutuhan terhadap keamanan data terhadap pelanggaran hak cipta. Watermarking merupakan pendekatan yang telah banyak digunakan dan merupakan bagian dari Digital Right Management (DRM) yang dibuat untuk memenuhi kebutuhan tersebut. Khusus untuk video, teknik watermarking harus mampu mengatasi beberapa karakteristik yang membedakan dengan citra statis untuk mengoptimalkan properti watermarking terutama robustness dan imperceptibility. Watermarking pada domain video terkompresi juga perlu ditinjau karena kebanyakan video disimpan dan ditransmisikan dalam bentuk terkompresi. Diperlukan teknik-teknik khusus agar watermark dan kompresi bisa dioptimalkan. Makalah ini mengulas bagaimana ketiga isu tersebut (robustness, imperceptibility, kompresi) diatasi dengan melihat penelitian-penelitian terkini di bidang watermarking video.

Research paper thumbnail of Predicting users' first impressions of website aesthetics with a quantification of perceived visual complexity and colorfulness

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems - CHI '13, 2013

Research paper thumbnail of Evaluasi Skema Watermarking Citra Berbasis Singular Value Decomposition, Kuantisasi Dither, Dan Deteksi Sisi

MAKARA of Science Series, 2011

Research paper thumbnail of Evaluasi Skema Watermarking Citra Berbasis Singular Value Decomposition, Kuantisasi Dither, Dan Deteksi Sisi

MAKARA of Science Series, 2011

Research paper thumbnail of 132305-9090-IJVIPNS-IJENS

In multi-object tracking, occlusion is a situation where part of an object is covered by another ... more In multi-object tracking, occlusion is a situation where part of an object is covered by another object or any structure in the video scene. It is a very common problem in multi-object tracking for real world video scenes and is a cause for poor tracking performance. Considering its significance and inevitability, this problem has been a subject of numerous papers about multi-object tracking. In this paper, a method for occlusion handling based on fuzzy approach is proposed. Fuzzy techniques are used here as they can deal with uncertainty and imprecision which are inherent in image/video processing. The method consists of feature extraction, fuzzy feature representation, merge-split event detection, and track resolution. The main contribution of this paper is in the use of fuzzy similarity measure together with fuzzy integral for resolving object tracks after occlusion. The similarity measure is performed separately on color, texture, and shape after representing them as fuzzy features. Then, fuzzy integral combines them to calculate the overall similarity value. Experimental result shows that with moderately fast computational time, the proposed method can resolve occluded tracks accurately even in difficult situations. This result also shows the promising applicability of fuzzy approach for future automated video surveillance research.

Research paper thumbnail of Evaluation of Singular Value Decomposition based Digital Image Watermarking with Dither Quantization and Edge Detection

Makara Seri Sains, 2010

Evaluation of Singular Value Decomposition based Digital Image Watermarking with Dither Quantizat... more Evaluation of Singular Value Decomposition based Digital Image Watermarking with Dither Quantization andEdge Detection. The use of singular value decomposition (SVD) in watermarking area has been developed by manyresearchers. In this paper, we describe our evaluation result against an SVD based watermarking scheme with Ditherquantization and edge detection proposed by Mohan et al. As an evaluation benchmark, we use StirMark to producemodified images by various image attacks. The extracted watermarks from these images were compared with theoriginal watermark by calculating its bit correlation ratio (BCR). The result shows that the scheme is robust againstJPEG compression, rotation, scaling, and PSNR attack. The scheme is also quite robust to some extents against removelineattack and cropping.

Research paper thumbnail of Resolving Occlusion in Multi-Object Tracking through Integrated Fuzzy Similarity Measure

Abstract-- In multi-object tracking, occlusion is a situation where part of an object is covered ... more Abstract-- In multi-object tracking, occlusion is a situation where part of an object is covered by another object or any structure in the video scene. It is a very common problem in multi-object tracking for real world video scenes and is a cause for poor tracking performance. Considering its significance and inevitability, this problem has been a subject of numerous papers about multi-object tracking. In this paper, a method for occlusion handling based on fuzzy approach is proposed. Fuzzy techniques are used here as they can deal with uncertainty and imprecision which are inherent in image/video processing. The method consists of feature extraction, fuzzy feature representation, merge-split event detection, and track resolution. The main contribution of this paper is in the use of fuzzy similarity measure together with fuzzy integral for resolving object tracks after occlusion. The similarity measure is performed separately on color, texture, and shape after representing them as ...

Research paper thumbnail of Resolving Occlusion in Multi-Object Tracking through Integrated Fuzzy Similarity Measure

In multi-object tracking, occlusion is a situation where part of an object is covered by another ... more In multi-object tracking, occlusion is a situation where part of an object is covered by another object or any structure in the video scene. It is a very common problem in multi-object tracking for real world video scenes and is a cause for poor tracking performance. Considering its significance and inevitability, this problem has been a subject of numerous papers about multi-object tracking. In this paper, a method for occlusion handling based on fuzzy approach is proposed. Fuzzy techniques are used here as they can deal with uncertainty and imprecision which are inherent in image/video processing. The method consists of feature extraction, fuzzy feature representation, merge-split event detection, and track resolution. The main contribution of this paper is in the use of fuzzy similarity measure together with fuzzy integral for resolving object tracks after occlusion. The similarity measure is performed separately on color, texture, and shape after representing them as fuzzy featu...

Research paper thumbnail of Protagoras: A Service for Tagging E-Commerce Products at Scale

2018 International Conference on Advanced Computer Science and Information Systems (ICACSIS), 2018

Despite widespread adoption of machine learning to solve real world problems, the implementation ... more Despite widespread adoption of machine learning to solve real world problems, the implementation of ML solutions in production environment is more complicated than it seems. It is quite straightforward to write machine learning codes these days but they are not designed to be deployed in production scale where millions of requests per day is a norm. In this paper, we describe our implementation of a ML service for large scale product tagging in e-commerce called Protagoras. The problem of tagging products can be seen as multi-label classification where the labels are product tags. By performing the classification within each product category, the precision can be increased and the inference can be performed faster. Protagoras combined the scalability and speed of microservice implementation in Golang and robust machine learning implementation in Python. We present the architecture of the system with all its components including API endpoints, job queue, database, and monitoring. The...

Research paper thumbnail of Watermarking pada Video : Robustness , Impercetibility dan Pendekatan untuk Domain Terkompresi

ABSTRAK Meningkatnya penggunaan dokumen digital khususnya multimedia (citra, audio, video) dan ke... more ABSTRAK Meningkatnya penggunaan dokumen digital khususnya multimedia (citra, audio, video) dan kemudahan transmisi data melalui Internet meningkatkan kebutuhan terhadap keamanan data terhadap pelanggaran hak cipta. Watermarking merupakan pendekatan yang telah banyak digunakan dan merupakan bagian dari Digital Right Management (DRM) yang dibuat untuk memenuhi kebutuhan tersebut. Khusus untuk video, teknik watermarking harus mampu mengatasi beberapa karakteristik yang membedakan dengan citra statis untuk mengoptimalkan properti watermarking terutama robustness dan imperceptibility. Watermarking pada domain video terkompresi juga perlu ditinjau karena kebanyakan video disimpan dan ditransmisikan dalam bentuk terkompresi. Diperlukan teknik-teknik khusus agar watermark dan kompresi bisa dioptimalkan. Makalah ini mengulas bagaimana ketiga isu tersebut (robustness, imperceptibility, kompresi) diatasi dengan melihat penelitian-penelitian terkini di bidang watermarking video.

Research paper thumbnail of Predicting users' first impressions of website aesthetics with a quantification of perceived visual complexity and colorfulness

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems - CHI '13, 2013

Research paper thumbnail of Evaluasi Skema Watermarking Citra Berbasis Singular Value Decomposition, Kuantisasi Dither, Dan Deteksi Sisi

MAKARA of Science Series, 2011

Research paper thumbnail of Evaluasi Skema Watermarking Citra Berbasis Singular Value Decomposition, Kuantisasi Dither, Dan Deteksi Sisi

MAKARA of Science Series, 2011

Research paper thumbnail of 132305-9090-IJVIPNS-IJENS

In multi-object tracking, occlusion is a situation where part of an object is covered by another ... more In multi-object tracking, occlusion is a situation where part of an object is covered by another object or any structure in the video scene. It is a very common problem in multi-object tracking for real world video scenes and is a cause for poor tracking performance. Considering its significance and inevitability, this problem has been a subject of numerous papers about multi-object tracking. In this paper, a method for occlusion handling based on fuzzy approach is proposed. Fuzzy techniques are used here as they can deal with uncertainty and imprecision which are inherent in image/video processing. The method consists of feature extraction, fuzzy feature representation, merge-split event detection, and track resolution. The main contribution of this paper is in the use of fuzzy similarity measure together with fuzzy integral for resolving object tracks after occlusion. The similarity measure is performed separately on color, texture, and shape after representing them as fuzzy features. Then, fuzzy integral combines them to calculate the overall similarity value. Experimental result shows that with moderately fast computational time, the proposed method can resolve occluded tracks accurately even in difficult situations. This result also shows the promising applicability of fuzzy approach for future automated video surveillance research.