Results 281 to 290 of about 141,408 (322)

Fast image segmentation for local feature descriptors

2017 25th Signal Processing and Communications Applications Conference (SIU), 2017
Local feature descriptors are the most frequently used feature representation in many Computer Vision problems. In particular, high level semantic information extraction from low-level features in classification and retrieval is also quite successful. Region based approaches to classification and retrieval have become very popular.
BİLGE, HASAN ŞAKİR, Celik, Ceyhun
openaire   +2 more sources

A novel feature descriptor based on microscopy image statistics

2015 IEEE International Conference on Image Processing (ICIP), 2015
In this paper, we propose a novel feature description algorithm based on image statistics. The pipeline first performs independent component analysis on training image patches to obtain basis vectors (filters) for a lower dimensional representation. Then for a given image, a set of filter responses at each pixel is computed.
Bayramoglu, N, Kannala, J, Akerfelt, M, Kaakinen, M, Eklund, L, Nees, M, Heikkila, J   +6 more
openaire   +2 more sources

Local feature descriptor using entropy rate

Neurocomputing, 2016
Over the past decades, an increasing number of local feature descriptors have been proposed in the community of computer vision and pattern recognition. Although they have achieved impressive results in many applications, how to find a balance between accuracy and computational efficiency is still an open issue.
Pu Yan, Dong Liang, Jun Tang, Ming Zhu
openaire   +1 more source

Texture descriptors for representing feature vectors

Expert Systems with Applications, 2019
Abstract Pattern representation affects classification performance. Although discovering “universal” features that work for many classification problems is ideal, most representations are problem specific. In this paper, we improve the classification performance of a classifier system by transforming a one-dimensional input descriptor into a two ...
Loris Nanni, Sheryl Brahnam, Alessandra Lumini   +2 more
openaire   +1 more source

Feature Identities, Descriptors, and Handles

1999
Finding the “right” geographic feature is a common source of interoperability difficulties. This paper reviews the issues and discusses how persistent feature identifiers can be used to support relationships and incremental updating in dispersed inter-operating information systems. Using such identifiers requires common definitions for concepts such as
openaire   +1 more source

Using affine features for an efficient binary feature descriptor

2014 Southwest Symposium on Image Analysis and Interpretation, 2014
A feature descriptor that is robust to a number of image deformations is a basic requirement for vision based applications. Most feature descriptors work well in image deformations such as compression artifacts, illumination changes, and blurring. To develop a feature descriptor that works well apart from these image deformations like transformations ...
Alok Desai, Dah-Jye Lee, Craig Wilson
openaire   +1 more source

Feature Selection and Heterogeneous Descriptors

2012
While the focus in Chap. 5 was on descriptors that were made up of homogeneous features, the focus in this chapter is on descriptors that are composed of features of different types. Heterogeneous descriptors are created from a combination of various types of features as described in Chap. 4.
openaire   +1 more source

Matching Affine Features with the SYBA Feature Descriptor

2014
Many vision-based applications require a robust feature descriptor that works well with image deformations such as compression, illumination, and blurring. It remains a challenge for a feature descriptor to work well with image deformation caused by viewpoint change.
Alok Desai, Dah-Jye Lee, Dan Ventura
openaire   +1 more source

Shape of Gaussians as feature descriptors

2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009
This paper introduces a feature descriptor called shape of Gaussian (SOG), which is based on a general feature descriptor design framework called shape of signal probability density function (SOSPDF). SOSPDF takes the shape of a signal's probability density function (pdf) as its feature.
null Liyu Gong, null Tianjiang Wang, null Fang Liu   +2 more
openaire   +1 more source

Active Descriptor Learning for Feature Matching

2019
Feature descriptor extraction lies at the core of many computer vision tasks including image retrieval and registration. In this paper, we present an active learning method for extracting efficient features to be used in matching image patches. We train a Siamese deep neural network by optimizing a triplet loss function. We develop a more efficient and
Aziz Koçanaoğulları, Esra Ataer-Cansızoğlu   +1 more
openaire   +1 more source