Uniform Detection in Social Image Streams

Social media mining from Internet has been an emerging research topic. The problem is challenging because of massive data contents from various sources, especially image data from user upload. In recent years, dictionary learning based image classification has been widely studied and gained significant success. In this paper, we propose a framework for automatic detection of interested uniforms in image streams from social networks. The systems is composed of a powerful feature extraction module based on dense SIFT feature and a state-of-the-art discriminative dictionary learning approach. Beside that, a parallel implementation of feature extraction is deployed to make the system work real time. An extensive set of experiments has been conducted on four real-life datasets. The experimental results show that we can obtain the detection rate up to 100% on some datasets. We also get real time performance with a speed of image stream of about 40 images per second. The framework can be applied to emerging applications such as uniform detection, automated image tagging, content base image retrieval or online advertisement based on image content.
Title: Uniform Detection in Social Image Streams
Authors: Manh, N.Q.
Tuan, N.D.
Sang, D.V.
Binh, H.T.T.
Thuy, N.T.
Keywords: Dictionary Learning, Image Classification, Max Pooling;Social Image Mining
Issue Date: 2016
Publisher: Institute of Electrical and Electronics Engineers Inc.
Citation: Scopus
Abstract: Social media mining from Internet has been an emerging research topic. The problem is challenging because of massive data contents from various sources, especially image data from user upload. In recent years, dictionary learning based image classification has been widely studied and gained significant success. In this paper, we propose a framework for automatic detection of interested uniforms in image streams from social networks. The systems is composed of a powerful feature extraction module based on dense SIFT feature and a state-of-the-art discriminative dictionary learning approach. Beside that, a parallel implementation of feature extraction is deployed to make the system work real time. An extensive set of experiments has been conducted on four real-life datasets. The experimental results show that we can obtain the detection rate up to 100% on some datasets. We also get real time performance with a speed of image stream of about 40 images per second. The framework can be applied to emerging applications such as uniform detection, automated image tagging, content base image retrieval or online advertisement based on image content.
Description: Proceedings - 2015 IEEE International Conference on Knowledge and Systems Engineering, KSE 2015 4 January 2016, Article number 7371779, Pages 180-185
URI: http://repository.vnu.edu.vn/handle/VNU_123/34102
ISBN: 978-146738013-3
Appears in Collections:Bài báo của ĐHQGHN trong Scopus

Nhận xét

Bài đăng phổ biến từ blog này

Di tích kiến trúc Hội An trong tiến trình lịch sử : Luận án TS. Lịch sử: 62 22 54 01

Hoàn thiện mô hình dự án liên kết giữa nhà trường và doanh nghiệp nhằm nâng cao chất lượng đào tạo nhân lực công nghệ cho doanh nghiệp (Nghiên cứu trường hợp Trường Đại học FPT và Công ty TNHH Phần mềm FPT)

Phát hiện gián tiếp đột biến gen EGFR trong ung thư biểu mô tuyến của phổi bằng kỹ thuật hóa mô miễn dịch: Luận văn ThS. Công nghệ nano sinh học (chuyên ngành đào tạo thí điểm)