Search results for "Feature extraction"
showing 10 items of 275 documents
Approximate 3D Partial Symmetry Detection Using Co-occurrence Analysis
2015
This paper addresses approximate partial symmetry detection in 3D point clouds, a classical and foundational tool for analyzing geometry. We present a novel, fully unsupervised method that detects partial symmetry under significant geometric variability, and without constraints on the number and arrangement of instances. The core idea is a matching scheme that finds consistent co-occurrence patterns in a frame-invariant way. We obtain a canonical partition of the input shape into building blocks and can handle ambiguous data by aggregating co-occurrence information across both all building block instances and the area they cover. We evaluate our method on several benchmark data sets and dem…
Signal-to-noise ratio in reproducing kernel Hilbert spaces
2018
This paper introduces the kernel signal-to-noise ratio (kSNR) for different machine learning and signal processing applications}. The kSNR seeks to maximize the signal variance while minimizing the estimated noise variance explicitly in a reproducing kernel Hilbert space (rkHs). The kSNR gives rise to considering complex signal-to-noise relations beyond additive noise models, and can be seen as a useful signal-to-noise regularizer for feature extraction and dimensionality reduction. We show that the kSNR generalizes kernel PCA (and other spectral dimensionality reduction methods), least squares SVM, and kernel ridge regression to deal with cases where signal and noise cannot be assumed inde…
A Comparative Analysis of Residual Block Alternatives for End-to-End Audio Classification
2020
Residual learning is known for being a learning framework that facilitates the training of very deep neural networks. Residual blocks or units are made up of a set of stacked layers, where the inputs are added back to their outputs with the aim of creating identity mappings. In practice, such identity mappings are accomplished by means of the so-called skip or shortcut connections. However, multiple implementation alternatives arise with respect to where such skip connections are applied within the set of stacked layers making up a residual block. While residual networks for image classification using convolutional neural networks (CNNs) have been widely discussed in the literature, their a…
Identifying the primary site of origin of MRI brain metastases from lung and breast cancer following a 2D radiomics approach
2017
Detection of brain metastases in patients with undiagnosed primary cancer is unusual but still an existing phenomenon. In these cases, identifying the cancer site of origin is non-feasible by visual examination of magnetic resonance (MR) images. Recently, radiomics has been proposed to analyze differences among classes of visually imperceptible imaging characteristics. In this study we analyzed 46 T1-weighted MR images of brain metastases from 29 patients: 29 of lung and 17 of breast origin. A total of 43 radiomics texture features were extracted from the metastatic lesions. Support vector machine (SVM) and k-nearest neighbors (k-NN) classifiers were implemented to evaluate the classificati…
Comparative Study of Face and Person Detection algorithms: Case Study of tramway in Lyon
2019
Moving object detection is one of the most important and challenging task in video surveillance and computer vision applications. Applying it in an industrial context requires taking into account parameters that are not necessarily considered in a theoretical context. We present here a brief review of numerous face and object detection algorithms and techniques that could be applied in our crowded application context. The chosen solution was embedded into the tramway.
Real-time low level feature extraction for on-board robot vision systems
2006
Robot vision systems notoriously require large computing capabilities, rarely available on physical devices. Robots have limited embedded hardware, and almost all sensory computation is delegated to remote machines. Emerging gigascale integration technologies offer the opportunity to explore alternative computing architectures that can deliver a significant boost to on-board computing when implemented in embedded, reconfigurable devices. This paper explores the mapping of low level feature extraction on one such architecture, the Georgia Tech SIMD Pixel Processor (SIMPil). The Fast Boundary Web Extraction (fBWE) algorithm is adapted and mapped on SIMPil as a fixed-point, data parallel imple…
Unsupervised deep feature extraction of hyperspectral images
2014
This paper presents an effective unsupervised sparse feature learning algorithm to train deep convolutional networks on hyperspectral images. Deep convolutional hierarchical representations are learned and then used for pixel classification. Features in lower layers present less abstract representations of data, while higher layers represent more abstract and complex characteristics. We successfully illustrate the performance of the extracted representations in a challenging AVIRIS hyperspectral image classification problem, compared to standard dimensionality reduction methods like principal component analysis (PCA) and its kernel counterpart (kPCA). The proposed method largely outperforms…
Improving SIFT-based descriptors stability to rotations
2010
Image descriptors are widely adopted structures to match image features. SIFT-based descriptors are collections of gradient orientation histograms computed on different feature regions, commonly divided by using a regular Cartesian grid or a log-polar grid. In order to achieve rotation invariance, feature patches have to be generally rotated in the direction of the dominant gradient orientation. In this paper we present a modification of the GLOH descriptor, a SIFT-based descriptor based on a log-polar grid, which avoids to rotate the feature patch before computing the descriptor since predefined discrete orientations can be easily derived by shifting the descriptor vector. The proposed des…
Meta-Tracking for Video Scene Understanding
2013
International audience; This paper presents a novel method to extract dominant motion patterns (MPs) and the main entry/exit areas from a surveillance video. The method first computes motion histograms for each pixel and then converts it into orientation distribution functions (ODFs). Given these ODFs, a novel particle meta-tracking procedure is launched which produces meta-tracks, i.e. particle trajectories. As opposed to conventional tracking which focuses on individual moving objects, meta-tracking uses particles to follow the dominant flow of the traffic. In a last step, a novel method is used to simultaneously identify the main entry/exit areas and recover the predominant MPs. The meta…
Multi-objective DSE algorithms' evaluations on processor optimization
2013
Very complex micro-architectures, like complex superscalar/SMT or multicore systems, have lots of configurations. Exploring this huge design space and trying to optimize multiple objectives, like performance, power consumption and hardware complexity is a real challenge. In this paper, using the multi-objective design space exploration tool FADSE, we tried to optimize the hardware parameters of the complex superscalar Grid ALU Processor. We compared how different heuristic algorithms handle the DSE optimization. Three of these algorithms are taken from the jMetal library (NSGAII, SPEA2 and SMPSO) while the other two, CNSGAII and MOHC were implemented by us. We show that in this huge design …