arXiv research

A new method classifies color images using quaternion algebra.

Develops new methods to create imperceptible image changes that fool classifiers.

This paper presents a module of vehicle reidentification based on make/model and color classification. It could be used by the Automated Vehicular Surveillance (AVS) or by the fast analysis of video data. Many of problems, that are related to this topic, had to be addressed. In order to facilitate and accelerate the pr…

Counting and classifying blood cells is an important diagnostic tool in medicine. Support Vector Machines are increasingly popular and efficient and could replace artificial neural network systems. Here a method to classify blood cells is proposed using SVM. A set of statistics on images are implemented in C++. The MPE…

The ability to characterize the color content of natural imagery is an important application of image processing. The pixel by pixel coloring of images may be viewed naturally as points in color space, and the inherent structure and distribution of these points affords a quantization, through clustering, of the color i…

JPEG2000 (j2k) is a highly popular format for image and video compression.With the rapidly growing applications of cloud based image classification, most existing j2k-compatible schemes would stream compressed color images from the source before reconstruction at the processing center as inputs to deep CNNs. We propose…

Generative modeling over natural images is one of the most fundamental machine learning problems. However, few modern generative models, including Wasserstein Generative Adversarial Nets (WGANs), are studied on manifold-valued images that are frequently encountered in real-world applications. To fill the gap, this pape…

Recent progress on many imaging and vision tasks has been driven by the use of deep feed-forward neural networks, which are trained by propagating gradients of a loss defined on the final output, back through the network up to the first layer that operates directly on the image. We propose back-propagating one step fur…

Automates hair color digitization using imaging and deep learning.

The paper uses VGG-19 for plant species classification from leaf images.

Spectral images captured by satellites and radio-telescopes are analyzed to obtain information about geological compositions distributions, distant asters as well as undersea terrain. Spectral images usually contain tens to hundreds of continuous narrow spectral bands and are widely used in various fields. But the vast…

We determine the minimal number of colors for non-trivial $\mathbb{Z}$-colorings on the standard minimal diagrams of $\mathbb{Z}$-colorable torus links. Also included are complete classifications of such $\mathbb{Z}$-colorings and of such $\mathbb{Z}$-colorings by only four colors, which are shown by using rack colorin…

In computer vision, image datasets used for classification are naturally associated with multiple labels and comprised of multiple views, because each image may contain several objects (e.g. pedestrian, bicycle and tree) and is properly characterized by multiple visual features (e.g. color, texture and shape). Currentl…

A wearable EEG headband detects primary colors from brain activity for color perception.

Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose shock absorbing robust features such as binarization, e.g., rounding, and group extraction, e.g…

This study automates blood cell classification using computer vision.

Vision impairment due to pathological damage of the retina can largely be prevented through periodic screening using fundus color imaging. However the challenge with large scale screening is the inability to exhaustively detect fine blood vessels crucial to disease diagnosis. In this work we present a computational ima…

The main idea of this paper is to explore the possibilities of generating samples from the neural networks, mostly focusing on the colorization of the grey-scale images. I will compare the existing methods for colorization and explore the possibilities of using new generative modeling to the task of colorization. The c…

When training a deep neural network for image classification, one can broadly distinguish between two types of latent features of images that will drive the classification. We can divide latent features into (i) "core" or "conditionally invariant" features $X^\text{core}$ whose distribution $X^\text{core}\vert Y$, cond…

Adversarial perturbations are more effective in Y-channel of YCbCr color space.

Deep-learning CNN automates Cu alloy grain size evaluation.

Aicardi's invariant $F(L)$ is extended to colored singular links using graphical calculus.

Recent work shows unequal performance of commercial face classification services in the gender classification task across intersectional groups defined by skin type and gender. Accuracy on dark-skinned females is significantly worse than on any other group. In this paper, we conduct several analyses to try to uncover t…

We explore a knot invariant derived from colorings of corresponding $1$-tangles with arbitrary connected quandles. When the quandle is an abelian extension of a certain type the invariant is equivalent to the quandle $2$-cocycle invariant. We construct many such abelian extensions using generalized Alexander quandles w…

Meta Optimal Transport learns from past problems to solve similar OT problems faster.

The rapid development of computer hardware and Internet technology makes large scale data dependent models computationally tractable, and opens a bright avenue for annotating images through innovative machine learning algorithms. Semi-supervised learning (SSL) has consequently received intensive attention in recent yea…

Explains a 2D color exchange invariant correspondence to 3D linking numbers.

Study proposes deep learning techniques to diagnose and differentiate Celiac Disease and Environmental Enteropathy from biopsy images.

In recent years, the majority of works on deep-learning-based image colorization have focused on how to make a good use of the enormous datasets currently available. What about when the data at disposal are scarce? The main objective of this work is to prove that a network can be trained and can provide excellent color…

The paper classifies palettes of Dehn colorings for spatial graphs.

We present a set of 26 finite quandles that distinguish (up to reversal and mirror image) by number of colorings, all of the 2977 prime oriented knots with up to 12 crossings. We also show that 1058 of these knots can be distinguished from their mirror images by the number of colorings by quandles from a certain set of…

Classifies colored links and spatial graphs up to colored link-homotopy.

Study uses image analysis to predict MSI status in tumors.

This paper gives two new combinatorial topological proofs of the classification of rational tangles. Each proof rests on an elegant lemma showing that rational tangles are isotopic to canonical alternating rational tangles. The first proof defines the tangle fraction from the canonical form and uses flyping to prove in…

New method estimates image appearance models for segmentation.

In this paper, we confront the problem of deep learning's big labeled data requirements, offer a rule based strategy for extreme augmentation of small data sets and apply that strategy with the image to image translation model by Isola et al. (2016) to automate cel style cartoon coloring with very limited training data…

This paper introduces a method to make deep neural networks more robust to adversarial attacks.

We show that any twisted Dijkgraaf-Witten representation of a mapping class group of an orientable, compact surface with boundary has finite image. This generalizes work of Etingof, Rowell and Witherspoon showing that the braid group images are finite. In particular, our result answers their question regarding finitene…

DSGD with OAC-MAC scheme achieves better convergence in noisy wireless networks.

Paper proposes a new Wasserstein distance for mixtures of radially contoured distributions.

(ABRIDGED) In previous work, two platforms have been developed for testing computer-vision algorithms for robotic planetary exploration (McGuire et al. 2004b,2005; Bartolo et al. 2007). The wearable-computer platform has been tested at geological and astrobiological field sites in Spain (Rivas Vaciamadrid and Riba de S…

Formula for arborescent link tails using theta functions.

Convolutional neural networks (CNN) have recently achieved state-of-the-art results in various applications. In the case of image recognition, an ideal model has to learn independently of the training data, both local dependencies between the three components (R,G,B) of a pixel, and the global relations describing edge…

A representation for compact 3-manifolds with non-empty non-spherical boundary via 4-colored graphs (i.e., 4-regular graphs endowed with a proper edge-coloration with four colors) has been recently introduced by two of the authors, and an initial classification of such manifolds has been obtained up to 8 vertices of th…

In this paper, we consider biquandle colorings for knotoids in $\mathbb{R}^2$ or $S^2$ and we construct several coloring invariants for knotoids derived as enhancements of the biquandle counting invariant. We first enhance the biquandle counting invariant by using a matrix constructed by utilizing the orientation a kno…

Learning color mixing is difficult for novice painters. In order to support novice painters in learning color mixing, we propose a prediction model for semitransparent pigment mixtures and use its prediction results to create a Smart Palette system. Such a system is constructed by first building a watercolor dataset wi…

We propose a multi-wing harmonium model for mining multimedia data that extends and improves on earlier models based on two-layer random fields, which capture bidirectional dependencies between hidden topic aspects and observed inputs. This model can be viewed as an undirected counterpart of the two-layer directed mode…

We extend the notion of link colorings with values in an Alexander quandle to link colorings with values in a module $M$ over the Laurent polynomial ring $Λ_μ=\mathbb{Z}[t_1^{\pm1},\dots,t_μ^{\pm1}]$. If $D$ is a diagram of a link $L$ with $μ$ components, then the colorings of $D$ with values in $M$ form a $Λ_μ$-module…