Fast explicit diffusion for accelerated features in nonlinear scale spaces
Reads0
Chats0
TLDR
A novel and fast multiscale feature detection and description approach that exploits the benefits of nonlinear scale spaces and introduces a Modified-Local Difference Binary (M-LDB) descriptor that is highly efficient, exploits gradient information from the non linear scale space, is scale and rotation invariant and has low storage requirements.Abstract:
We propose a novel and fast multiscale feature detection and description approach that exploits the benefits of nonlinear scale spaces. Previous attempts to detect and describe features in nonlinear scale spaces such as KAZE [1] and BFSIFT [6] are highly time consuming due to the computational burden of creating the nonlinear scale space. In this paper we propose to use recent numerical schemes called Fast Explicit Diffusion (FED) [3, 4] embedded in a pyramidal framework to dramatically speed-up feature detection in nonlinear scale spaces. In addition, we introduce a Modified-Local Difference Binary (M-LDB) descriptor that is highly efficient, exploits gradient information from the nonlinear scale space, is scale and rotation invariant and has low storage requirements. Our features are called Accelerated-KAZE (A-KAZE) due to the dramatic speed-up introduced by FED schemes embedded in a pyramidal framework.read more
Citations
More filters
Journal ArticleDOI
Learning visual representations with optimum-path forest and its applications to Barrett’s esophagus and adenocarcinoma diagnosis
Luis Antonio De Souza,Luis Claudio Sugi Afonso,Alanna Ebigbo,Andreas Probst,Helmut Messmann,Robert Mendel,Christian Hook,Christoph Palm,João Paulo Papa +8 more
TL;DR: This work introduces the unsupervised Optimum-Path Forest (OPF) classifier for learning visual dictionaries in the context of Barrett’s esophagus (BE) and automatic adenocarcinoma diagnosis and proposed a new BE and adenOCarcinomas description using the A-KAZE features, not yet applied in the literature.
Proceedings ArticleDOI
A Multi-modal Neural Embeddings Approach for Detecting Mobile Counterfeit Apps
Jathushan Rajasegaran,Naveen Karunanayake,Ashanie Gunathillake,Suranga Seneviratne,Guillaume Jourjon +4 more
TL;DR: An analysis of approximately 1.2 million apps from Google Play Store is presented and a novel approach of combining content embeddings and styleembeddings generated from pre-trained convolutional neural networks to detect counterfeit apps is proposed.
Posted Content
Improving Sonar Image Patch Matching via Deep Learning
TL;DR: In this paper, the authors used CNN to learn a matching function that can be trained from labeled sonar data, after pre-processing to generate matching and non-matching pairs.
Posted Content
Interest point detectors stability evaluation on ApolloScape dataset
TL;DR: This paper evaluates stability of a number of hand crafted and recent, learning-based interest point detectors on the street-level view ApolloScape dataset to verify if the recent, deep-learning based interest point detector have the advantage over the traditional, hand-crafted keypoint detectors.
Journal ArticleDOI
Keypoint Detection Using Higher Order Laplacian of Gaussian
Yongju Cho,Dojin Kim,Saleh Saeed,Muhammad Umer Kakli,Soon-Heung Jung,Jeongil Seo,Unsang Park +6 more
TL;DR: The proposed H LoG method provides comparable performance to HDoG and the combination of HLoG and H doG provides significant improvements in various keypoint-related computer vision problems.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images that can then be used to reliably match objects in diering images.
Book ChapterDOI
SURF: speeded up robust features
TL;DR: A novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
Journal ArticleDOI
Scale-space and edge detection using anisotropic diffusion
Pietro Perona,Jitendra Malik +1 more
TL;DR: A new definition of scale-space is suggested, and a class of algorithms used to realize a diffusion process is introduced, chosen to vary spatially in such a way as to encourage intra Region smoothing rather than interregion smoothing.
Proceedings ArticleDOI
ORB: An efficient alternative to SIFT or SURF
TL;DR: This paper proposes a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise, and demonstrates through experiments how ORB is at two orders of magnitude faster than SIFT, while performing as well in many situations.