Robust image features for classification and zero-shot tasks by merging visual and semantic attributes

For many applications in graphics, design, and human computer interaction, it is essential to understand where humans look in a scene with a particular task. Models of saliency can be used to predict fixation locations, but a large body of previous saliency models focused on free-viewing task. They are based on bottom-up computation that does not consider task-oriented image semantics and often does not match actual eye movements. To address this problem, we collected eye tracking data of 11 subjects when they performed some particular search task in 1307 images and annotation data of 2,511 segmented objects with fine contours and 8 semantic attributes. Using this database as training and testing examples, we learn a model of saliency based on bottom-up image features and target position feature. Experimental results demonstrate the importance of the target information in the prediction of task-oriented visual attention.

Download Full-text

Color restoration for objects of interest using robust image features

2008 IEEE 10th Workshop on Multimedia Signal Processing ◽

10.1109/mmsp.2008.4665136 ◽

2008 ◽

Cited By ~ 1

Author(s):

David Chen ◽

Vijay Chandrasekhar ◽

Gabriel Takacs ◽

Jatinder Singh ◽

Bernd Girod

Keyword(s):

Image Features ◽

Color Restoration ◽

Robust Image

Download Full-text

High quality machine-robust image features: Identification in nonsmall cell lung cancer computed tomography images

Medical Physics ◽

10.1118/1.4829514 ◽

2013 ◽

Vol 40 (12) ◽

pp. 121916 ◽

Cited By ~ 54

Author(s):

Luke A. Hunter ◽

Shane Krafft ◽

Francesco Stingo ◽

Haesun Choi ◽

Mary K. Martel ◽

...

Keyword(s):

Computed Tomography ◽

Lung Cancer ◽

Cell Lung Cancer ◽

Nonsmall Cell Lung Cancer ◽

Image Features ◽

High Quality ◽

Computed Tomography Images ◽

Robust Image

Download Full-text

A high performance parallel computing architecture for robust image features

International Journal of Electronics ◽

10.1080/00207217.2013.780306 ◽

2013 ◽

Vol 101 (3) ◽

pp. 391-404 ◽

Cited By ~ 1

Author(s):

Renyan Zhou ◽

Leibo Liu ◽

Shaojun Wei

Keyword(s):

Parallel Computing ◽

High Performance ◽

Image Features ◽

Computing Architecture ◽

Robust Image

Download Full-text

Performance Analysis of Robust Image Features Detection Algorithms

Information Technologies and Control ◽

10.2478/itc-2013-0011 ◽

2014 ◽

Vol 11 (3) ◽

pp. 2-15 ◽

Cited By ~ 1

Author(s):

I. Nikolova

Keyword(s):

Performance Analysis ◽

Feature Detection ◽

Image Features ◽

Detection Algorithms ◽

Digital Still Camera ◽

Robust Image

Abstract This paper deals with the challenging task of acquiring stable image features in a sequence of images of the same scene taken under different viewing positions by a digital still camera. Two popular contemporary algorithms for discrete feature detection: SIFT and SURF are regarded. The results of the timing performance analysis of their sequential implementations are presented and discussed. The performance speedup analysis and scalability tests with multi-threading and GPU-based implementations are analyzed

Download Full-text

Robust Image Hashing With Singular Values Of Quaternion SVD

The Computer Journal ◽

10.1093/comjnl/bxz127 ◽

2019 ◽

Cited By ~ 4

Author(s):

Zhenjun Tang ◽

Mengzhu Yu ◽

Heng Yao ◽

Hanyun Zhang ◽

Chunqiang Yu ◽

...

Keyword(s):

Euclidean Distance ◽

Characteristic Curve ◽

Singular Values ◽

Image Authentication ◽

Image Features ◽

Multimedia Systems ◽

Image Hashing ◽

Copy Detection ◽

Robust Image ◽

Robust Image Hashing

Abstract Image hashing is an efficient technique of many multimedia systems, such as image retrieval, image authentication and image copy detection. Classification between robustness and discrimination is one of the most important performances of image hashing. In this paper, we propose a robust image hashing with singular values of quaternion singular value decomposition (QSVD). The key contribution is the innovative use of QSVD, which can extract stable and discriminative image features from CIE L*a*b* color space. In addition, image features of a block are viewed as a point in the Cartesian coordinates and compressed by calculating the Euclidean distance between its point and a reference point. As the Euclidean distance requires smaller storage than the original block features, this technique helps to make a discriminative and compact hash. Experiments with three open image databases are conducted to validate efficiency of our image hashing. The results demonstrate that our image hashing can resist many digital operations and reaches a good discrimination. Receiver operating characteristic curve comparisons illustrate that our image hashing outperforms some state-of-the-art algorithms in classification performance.

Download Full-text