May 6, 2019

3073 words 15 mins read

Paper Group ANR 212

Template Matching Advances and Applications in Image Analysis. Matching of Images with Rotation Transformation Based on the Virtual Electromagnetic Interaction. Asymptotic Convergence in Online Learning with Unbounded Delays. Alzheimer’s Disease Diagnostics by Adaptation of 3D Convolutional Network. A new TAG Formalism for Tamil and Parser Analytic …

Template Matching Advances and Applications in Image Analysis


Title	Template Matching Advances and Applications in Image Analysis
Authors	Nazanin Sadat Hashemi, Roya Babaie Aghdam, Atieh Sadat Bayat Ghiasi, Parastoo Fatemi
Abstract	In most computer vision and image analysis problems, it is necessary to define a similarity measure between two or more different objects or images. Template matching is a classic and fundamental method used to score similarities between objects using certain mathematical algorithms. In this paper, we reviewed the basic concept of matching, as well as advances in template matching and applications such as invariant features or novel applications in medical image analysis. Additionally, deformable models and templates originating from classic template matching were discussed. These models have broad applications in image registration, and they are a fundamental aspect of novel machine vision or deep learning algorithms, such as convolutional neural networks (CNN), which perform shift and scale invariant functions followed by classification. In general, although template matching methods have restrictions which limit their application, they are recommended for use with other object recognition methods as pre- or post-processing steps. Combining a template matching technique such as normalized cross-correlation or dice coefficient with a robust decision-making algorithm yields a significant improvement in the accuracy rate for object detection and recognition.
Tasks	Decision Making, Image Registration, Object Detection, Object Recognition
Published	2016-10-23
URL	http://arxiv.org/abs/1610.07231v1
PDF	http://arxiv.org/pdf/1610.07231v1.pdf
PWC	https://paperswithcode.com/paper/template-matching-advances-and-applications
Repo
Framework

Matching of Images with Rotation Transformation Based on the Virtual Electromagnetic Interaction


Title	Matching of Images with Rotation Transformation Based on the Virtual Electromagnetic Interaction
Authors	Xiaodong Zhuang, N. E. Mastorakis
Abstract	A novel approach of image matching for rotating transformation is presented and studied. The approach is inspired by electromagnetic interaction force between physical currents. The virtual current in images is proposed based on the significant edge lines extracted as the fundamental structural feature of images. The virtual electromagnetic force and the corresponding moment is studied between two images after the extraction of the virtual currents in the images. Then image matching for rotating transformation is implemented by exploiting the interaction between the virtual currents in the two images to be matched. The experimental results prove the effectiveness of the novel idea, which indicates the promising application of the proposed method in image registration.
Tasks	Image Registration
Published	2016-10-10
URL	http://arxiv.org/abs/1610.02762v1
PDF	http://arxiv.org/pdf/1610.02762v1.pdf
PWC	https://paperswithcode.com/paper/matching-of-images-with-rotation
Repo
Framework

Asymptotic Convergence in Online Learning with Unbounded Delays


Title	Asymptotic Convergence in Online Learning with Unbounded Delays
Authors	Scott Garrabrant, Nate Soares, Jessica Taylor
Abstract	We study the problem of predicting the results of computations that are too expensive to run, via the observation of the results of smaller computations. We model this as an online learning problem with delayed feedback, where the length of the delay is unbounded, which we study mainly in a stochastic setting. We show that in this setting, consistency is not possible in general, and that optimal forecasters might not have average regret going to zero. However, it is still possible to give algorithms that converge asymptotically to Bayes-optimal predictions, by evaluating forecasters on specific sparse independent subsequences of their predictions. We give an algorithm that does this, which converges asymptotically on good behavior, and give very weak bounds on how long it takes to converge. We then relate our results back to the problem of predicting large computations in a deterministic setting.
Tasks
Published	2016-04-18
URL	http://arxiv.org/abs/1604.05280v4
PDF	http://arxiv.org/pdf/1604.05280v4.pdf
PWC	https://paperswithcode.com/paper/asymptotic-convergence-in-online-learning
Repo
Framework

Alzheimer’s Disease Diagnostics by Adaptation of 3D Convolutional Network


Title	Alzheimer’s Disease Diagnostics by Adaptation of 3D Convolutional Network
Authors	Ehsan Hosseini-Asl, Robert Keynto, Ayman El-Baz
Abstract	Early diagnosis, playing an important role in preventing progress and treating the Alzheimer{'}s disease (AD), is based on classification of features extracted from brain images. The features have to accurately capture main AD-related variations of anatomical brain structures, such as, e.g., ventricles size, hippocampus shape, cortical thickness, and brain volume. This paper proposed to predict the AD with a deep 3D convolutional neural network (3D-CNN), which can learn generic features capturing AD biomarkers and adapt to different domain datasets. The 3D-CNN is built upon a 3D convolutional autoencoder, which is pre-trained to capture anatomical shape variations in structural brain MRI scans. Fully connected upper layers of the 3D-CNN are then fine-tuned for each task-specific AD classification. Experiments on the CADDementia MRI dataset with no skull-stripping preprocessing have shown our 3D-CNN outperforms several conventional classifiers by accuracy. Abilities of the 3D-CNN to generalize the features learnt and adapt to other domains have been validated on the ADNI dataset.
Tasks	Skull Stripping
Published	2016-07-02
URL	http://arxiv.org/abs/1607.00455v1
PDF	http://arxiv.org/pdf/1607.00455v1.pdf
PWC	https://paperswithcode.com/paper/alzheimers-disease-diagnostics-by-adaptation
Repo
Framework

A new TAG Formalism for Tamil and Parser Analytics


Title	A new TAG Formalism for Tamil and Parser Analytics
Authors	Vijay Krishna Menon, S. Rajendran, M. Anand Kumar, K. P. Soman
Abstract	Tree adjoining grammar (TAG) is specifically suited for morph rich and agglutinated languages like Tamil due to its psycho linguistic features and parse time dependency and morph resolution. Though TAG and LTAG formalisms have been known for about 3 decades, efforts on designing TAG Syntax for Tamil have not been entirely successful due to the complexity of its specification and the rich morphology of Tamil language. In this paper we present a minimalistic TAG for Tamil without much morphological considerations and also introduce a parser implementation with some obvious variations from the XTAG system
Tasks
Published	2016-04-05
URL	http://arxiv.org/abs/1604.01235v1
PDF	http://arxiv.org/pdf/1604.01235v1.pdf
PWC	https://paperswithcode.com/paper/a-new-tag-formalism-for-tamil-and-parser
Repo
Framework

Fast and High-Quality Bilateral Filtering Using Gauss-Chebyshev Approximation


Title	Fast and High-Quality Bilateral Filtering Using Gauss-Chebyshev Approximation
Authors	Sanjay Ghosh, Kunal N. Chaudhury
Abstract	The bilateral filter is an edge-preserving smoother that has diverse applications in image processing, computer vision, computer graphics, and computational photography. The filter uses a spatial kernel along with a range kernel to perform edge-preserving smoothing. In this paper, we consider the Gaussian bilateral filter where both the kernels are Gaussian. A direct implementation of the Gaussian bilateral filter requires $O(\sigma_s^2)$ operations per pixel, where $\sigma_s$ is the standard deviation of the spatial Gaussian. In fact, it is well-known that the direct implementation is slow in practice. We present an approximation of the Gaussian bilateral filter, whereby we can cut down the number of operations to $O(1)$ per pixel for any arbitrary $\sigma_s$, and yet achieve very high-quality filtering that is almost indistinguishable from the output of the original filter. We demonstrate that the proposed approximation is few orders faster in practice compared to the direct implementation. We also demonstrate that the approximation is competitive with existing fast algorithms in terms of speed and accuracy.
Tasks
Published	2016-05-07
URL	http://arxiv.org/abs/1605.02178v2
PDF	http://arxiv.org/pdf/1605.02178v2.pdf
PWC	https://paperswithcode.com/paper/fast-and-high-quality-bilateral-filtering
Repo
Framework

Random Walk Graph Laplacian based Smoothness Prior for Soft Decoding of JPEG Images


Title	Random Walk Graph Laplacian based Smoothness Prior for Soft Decoding of JPEG Images
Authors	Xianming Liu, Gene Cheung, Xiaolin Wu, Debin Zhao
Abstract	Given the prevalence of JPEG compressed images, optimizing image reconstruction from the compressed format remains an important problem. Instead of simply reconstructing a pixel block from the centers of indexed DCT coefficient quantization bins (hard decoding), soft decoding reconstructs a block by selecting appropriate coefficient values within the indexed bins with the help of signal priors. The challenge thus lies in how to define suitable priors and apply them effectively. In this paper, we combine three image priors—Laplacian prior for DCT coefficients, sparsity prior and graph-signal smoothness prior for image patches—to construct an efficient JPEG soft decoding algorithm. Specifically, we first use the Laplacian prior to compute a minimum mean square error (MMSE) initial solution for each code block. Next, we show that while the sparsity prior can reduce block artifacts, limiting the size of the over-complete dictionary (to lower computation) would lead to poor recovery of high DCT frequencies. To alleviate this problem, we design a new graph-signal smoothness prior (desired signal has mainly low graph frequencies) based on the left eigenvectors of the random walk graph Laplacian matrix (LERaG). Compared to previous graph-signal smoothness priors, LERaG has desirable image filtering properties with low computation overhead. We demonstrate how LERaG can facilitate recovery of high DCT frequencies of a piecewise smooth (PWS) signal via an interpretation of low graph frequency components as relaxed solutions to normalized cut in spectral clustering. Finally, we construct a soft decoding algorithm using the three signal priors with appropriate prior weights. Experimental results show that our proposal outperforms state-of-the-art soft decoding algorithms in both objective and subjective evaluations noticeably.
Tasks	Image Reconstruction, Quantization
Published	2016-07-07
URL	http://arxiv.org/abs/1607.01895v1
PDF	http://arxiv.org/pdf/1607.01895v1.pdf
PWC	https://paperswithcode.com/paper/random-walk-graph-laplacian-based-smoothness
Repo
Framework

Exact Clustering of Weighted Graphs via Semidefinite Programming


Title	Exact Clustering of Weighted Graphs via Semidefinite Programming
Authors	Aleksis Pirinen, Brendan Ames
Abstract	As a model problem for clustering, we consider the densest k-disjoint-clique problem of partitioning a weighted complete graph into k disjoint subgraphs such that the sum of the densities of these subgraphs is maximized. We establish that such subgraphs can be recovered from the solution of a particular semidefinite relaxation with high probability if the input graph is sampled from a distribution of clusterable graphs. Specifically, the semidefinite relaxation is exact if the graph consists of k large disjoint subgraphs, corresponding to clusters, with weight concentrated within these subgraphs, plus a moderate number of outliers. Further, we establish that if noise is weakly obscuring these clusters, i.e, the between-cluster edges are assigned very small weights, then we can recover significantly smaller clusters. For example, we show that in approximately sparse graphs, where the between-cluster weights tend to zero as the size n of the graph tends to infinity, we can recover clusters of size polylogarithmic in n. Empirical evidence from numerical simulations is also provided to support these theoretical phase transitions to perfect recovery of the cluster structure.
Tasks
Published	2016-03-16
URL	http://arxiv.org/abs/1603.05296v5
PDF	http://arxiv.org/pdf/1603.05296v5.pdf
PWC	https://paperswithcode.com/paper/exact-clustering-of-weighted-graphs-via
Repo
Framework

A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method


Title	A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method
Authors	Yuzhuo Ren, Chen Chen, Shangwen Li, C. -C. Jay Kuo
Abstract	The task of estimating the spatial layout of cluttered indoor scenes from a single RGB image is addressed in this work. Existing solutions to this problems largely rely on hand-craft features and vanishing lines, and they often fail in highly cluttered indoor rooms. The proposed coarse-to-fine indoor layout estimation (CFILE) method consists of two stages: 1) coarse layout estimation; and 2) fine layout localization. In the first stage, we adopt a fully convolutional neural network (FCN) to obtain a coarse-scale room layout estimate that is close to the ground truth globally. The proposed FCN considers combines the layout contour property and the surface property so as to provide a robust estimate in the presence of cluttered objects. In the second stage, we formulate an optimization framework that enforces several constraints such as layout contour straightness, surface smoothness and geometric constraints for layout detail refinement. Our proposed system offers the state-of-the-art performance on two commonly used benchmark datasets.
Tasks
Published	2016-07-03
URL	http://arxiv.org/abs/1607.00598v1
PDF	http://arxiv.org/pdf/1607.00598v1.pdf
PWC	https://paperswithcode.com/paper/a-coarse-to-fine-indoor-layout-estimation
Repo
Framework

On a method for Rock Classification using Textural Features and Genetic Optimization


Title	On a method for Rock Classification using Textural Features and Genetic Optimization
Authors	Manuel Blanco Valentin, Clecio Roque De Bom, Marcio Portes de Albuquerque, Marcelo Portes de Albuquerque, Elisangela Faria, Maury Duarte Correia, Rodrigo Surmas
Abstract	In this work we present a method to classify a set of rock textures based on a Spectral Analysis and the extraction of the texture Features of the resulted images. Up to 520 features were tested using 4 different filters and all 31 different combinations were verified. The classification process relies on a Naive Bayes classifier. We performed two kinds of optimizations: statistical optimization with covariance-based Principal Component Analysis (PCA) and a genetic optimization, for 10,000 randomly defined samples, achieving a final maximum classification success of 91% against the original 70% success ratio (without any optimization nor filters used). After the optimization 9 types of features emerged as most relevant.
Tasks
Published	2016-07-06
URL	http://arxiv.org/abs/1607.01679v2
PDF	http://arxiv.org/pdf/1607.01679v2.pdf
PWC	https://paperswithcode.com/paper/on-a-method-for-rock-classification-using
Repo
Framework

Structured Sparse Principal Components Analysis with the TV-Elastic Net penalty


Title	Structured Sparse Principal Components Analysis with the TV-Elastic Net penalty
Authors	Amicie de Pierrefeu, Tommy Löfstedt, Fouad Hadj-Selem, Mathieu Dubois, Philippe Ciuciu, Vincent Frouin, Edouard Duchesnay
Abstract	Principal component analysis (PCA) is an exploratory tool widely used in data analysis to uncover dominant patterns of variability within a population. Despite its ability to represent a data set in a low-dimensional space, the interpretability of PCA remains limited. However, in neuroimaging, it is essential to uncover clinically interpretable phenotypic markers that would account for the main variability in the brain images of a population. Recently, some alternatives to the standard PCA approach, such as Sparse PCA, have been proposed, their aim being to limit the density of the components. Nonetheless, sparsity alone does not entirely solve the interpretability problem, since it may yield scattered and unstable components. We hypothesized that the incorporation of prior information regarding the structure of the data may lead to improved relevance and interpretability of brain patterns. We therefore present a simple extension of the popular PCA framework that adds structured sparsity penalties on the loading vectors in order to identify the few stable regions in the brain images accounting for most of the variability. Such structured sparsity can be obtained by combining l1 and total variation (TV) penalties, where the TV regularization encodes higher order information about the structure of the data. This paper presents the structured sparse PCA (denoted SPCA-TV) optimization framework and its resolution. We demonstrate the efficiency and versatility of SPCA-TV on three different data sets. The gains of SPCA-TV over unstructured approaches are significant,since SPCA-TV reveals the variability within a data set in the form of intelligible brain patterns that are easy to interpret, and are more stable across different samples.
Tasks
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01423v3
PDF	http://arxiv.org/pdf/1609.01423v3.pdf
PWC	https://paperswithcode.com/paper/structured-sparse-principal-components
Repo
Framework

A novel and automatic pectoral muscle identification algorithm for mediolateral oblique (MLO) view mammograms using ImageJ


Title	A novel and automatic pectoral muscle identification algorithm for mediolateral oblique (MLO) view mammograms using ImageJ
Authors	Chao Wang
Abstract	Pectoral muscle identification is often required for breast cancer risk analysis, such as estimating breast density. Traditional methods are overwhelmingly based on manual visual assessment or straight line fitting for the pectoral muscle boundary, which are inefficient and inaccurate since pectoral muscle in mammograms can have curved boundaries. This paper proposes a novel and automatic pectoral muscle identification algorithm for MLO view mammograms. It is suitable for both scanned film and full field digital mammograms. This algorithm is demonstrated using a public domain software ImageJ. A validation of this algorithm has been performed using real-world data and it shows promising result.
Tasks
Published	2016-03-03
URL	http://arxiv.org/abs/1603.01056v1
PDF	http://arxiv.org/pdf/1603.01056v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-and-automatic-pectoral-muscle
Repo
Framework

Multi-View Product Image Search Using Deep ConvNets Representations


Title	Multi-View Product Image Search Using Deep ConvNets Representations
Authors	Muhammet Bastan, Ozgur Yilmaz
Abstract	Multi-view product image queries can improve retrieval performance over single view queries significantly. In this paper, we investigated the performance of deep convolutional neural networks (ConvNets) on multi-view product image search. First, we trained a VGG-like network to learn deep ConvNets representations of product images. Then, we computed the deep ConvNets representations of database and query images and performed single view queries, and multi-view queries using several early and late fusion approaches. We performed extensive experiments on the publicly available Multi-View Object Image Dataset (MVOD 5K) with both clean background queries from the Internet and cluttered background queries from a mobile phone. We compared the performance of ConvNets to the classical bag-of-visual-words (BoWs). We concluded that (1) multi-view queries with deep ConvNets representations perform significantly better than single view queries, (2) ConvNets perform much better than BoWs and have room for further improvement, (3) pre-training of ConvNets on a different image dataset with background clutter is needed to obtain good performance on cluttered product image queries obtained with a mobile phone.
Tasks	Image Retrieval
Published	2016-08-11
URL	http://arxiv.org/abs/1608.03462v2
PDF	http://arxiv.org/pdf/1608.03462v2.pdf
PWC	https://paperswithcode.com/paper/multi-view-product-image-search-using-deep
Repo
Framework

Deep Learning of Robotic Tasks without a Simulator using Strong and Weak Human Supervision


Title	Deep Learning of Robotic Tasks without a Simulator using Strong and Weak Human Supervision
Authors	Bar Hilleli, Ran El-Yaniv
Abstract	We propose a scheme for training a computerized agent to perform complex human tasks such as highway steering. The scheme is designed to follow a natural learning process whereby a human instructor teaches a computerized trainee. The learning process consists of five elements: (i) unsupervised feature learning; (ii) supervised imitation learning; (iii) supervised reward induction; (iv) supervised safety module construction; and (v) reinforcement learning. We implemented the last four elements of the scheme using deep convolutional networks and applied it to successfully create a computerized agent capable of autonomous highway steering over the well-known racing game Assetto Corsa. We demonstrate that the use of the last four elements is essential to effectively carry out the steering task using vision alone, without access to a driving simulator internals, and operating in wall-clock time. This is made possible also through the introduction of a safety network, a novel way for preventing the agent from performing catastrophic mistakes during the reinforcement learning stage.
Tasks	Imitation Learning
Published	2016-12-04
URL	http://arxiv.org/abs/1612.01086v3
PDF	http://arxiv.org/pdf/1612.01086v3.pdf
PWC	https://paperswithcode.com/paper/deep-learning-of-robotic-tasks-without-a
Repo
Framework

Recursion-Free Online Multiple Incremental/Decremental Analysis Based on Ridge Support Vector Learning


Title	Recursion-Free Online Multiple Incremental/Decremental Analysis Based on Ridge Support Vector Learning
Authors	Bo-Wei Chen
Abstract	This study presents a rapid multiple incremental and decremental mechanism based on Weight-Error Curves (WECs) for support-vector analysis. Recursion-free computation is proposed for predicting the Lagrangian multipliers of new samples. This study examines Ridge Support Vector Models, subsequently devising a recursion-free function derived from WECs. With the proposed function, all the new Lagrangian multipliers can be computed at once without using any gradual step sizes. Moreover, such a function relaxes a constraint, where the increment of new multiple Lagrangian multipliers should be the same in the previous work, thereby easily satisfying the requirement of KKT conditions. The proposed mechanism no longer requires typical bookkeeping strategies, which compute the step size by checking all the training samples in each incremental round.
Tasks
Published	2016-08-01
URL	http://arxiv.org/abs/1608.00619v2
PDF	http://arxiv.org/pdf/1608.00619v2.pdf
PWC	https://paperswithcode.com/paper/recursion-free-online-multiple
Repo
Framework