Images as sets of locally weighted features
نویسندگان
چکیده
This paper presents a generic framework in which images are modelled as orderless sets of weighted visual features. Each visual feature is associated with a weight factor that may inform its relevance. This framework can be applied to various bag-of-patches approaches such as the bag-of-visual-word or the Fisher kernel representations. We suggest that if dense sampling is used, different schemes to weight local features can be evaluated, leading to results that are often better than the combination of multiple sampling schemes, at a much lower computational cost, because the features are extracted only once. This allows our framework to be a test-bed for saliency estimation methods in image categorisation tasks. We explored two main possibilities for the estimation of local feature relevance. The first one is based on the use of saliency maps obtained from human feedback, either by gaze tracking or by mouse clicks. The method is able to profit from such maps, leading to a significant improvement in categorisation performance. The second possibility is based on automatic saliency estimation methods, including Itti&Koch’s method and the SIFT’s DoG. We evaluated the proposed framework and saliency estimation methods using an in house dataset and the PASCAL VOC 2008/2007 dataset, showing that some of the saliency estimation methods lead to a significant performance improvement in comparison to the standard unweighted representation.
منابع مشابه
Measurement of the correlation coefficients between extracted features from CT and MR images
Introduction: Nowadays applying computer in image processing is being improved revolutionary for solving medical images deficiencies. Image features that are analysis in image processing show image information. The aim of the present study was to find correlation between CT- scan and MRI images' features. Materials and Methods: After data acquisition, applying...
متن کاملA hybrid filter-based feature selection method via hesitant fuzzy and rough sets concepts
High dimensional microarray datasets are difficult to classify since they have many features with small number ofinstances and imbalanced distribution of classes. This paper proposes a filter-based feature selection method to improvethe classification performance of microarray datasets by selecting the significant features. Combining the concepts ofrough sets, weighted rough set, fuzzy rough se...
متن کاملSome Generalizations of Locally Closed Sets
Arenas et al. [1] introduced the notion of lambda-closed sets as a generalization of locally closed sets. In this paper, we introduce the notions of lambda-locally closed sets, Lambda_lambda-closed sets and lambda_g-closed sets and obtain some decompositions of closed sets and continuity in topological spaces.
متن کاملFuzzy $bigwedge_{e}$ Sets and Continuity in Fuzzy Topological spaces
We introduce a new class of fuzzy open sets called fuzzy $bigwedge_e$ sets which includes the class of fuzzy $e$-open sets. We also define a weaker form of fuzzy $bigwedge_e$ sets termed as fuzzy locally $bigwedge_e$ sets. By means of these new sets, we present the notions of fuzzy $bigwedge_e$ continuity and fuzzy locally $bigwedge_e$ continuity which are weaker than fuzzy $e$-continuity and f...
متن کاملEvaluation of Similarity Measures for Template Matching
Image matching is a critical process in various photogrammetry, computer vision and remote sensing applications such as image registration, 3D model reconstruction, change detection, image fusion, pattern recognition, autonomous navigation, and digital elevation model (DEM) generation and orientation. The primary goal of the image matching process is to establish the correspondence between two ...
متن کاملVisibility-Weighted Saliency for Volume Visualization
Volume visualization has been widely used to depict complicated 3D structures in volume data sets. However, obtaining clear visualization of the features of interest in a volume is still a major challenge. The clarity of features depends on the transfer function, the viewpoint and the spatial distribution of features in the volume data set. In this paper, we propose visibility-weighted saliency...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Computer Vision and Image Understanding
دوره 116 شماره
صفحات -
تاریخ انتشار 2012