Important Visual Attributes Research Articles

Accurate physics-based digital reproduction of effect coatings.

We built an improved 3D rendering framework to accurately visualize the complete appearance of effect coatings, including metallic effects, sparkle and iridescence. Spectral reflectance measurements and sparkle indexes from a commercially available multi-angle spectrophotometer (BYKmac-i) were used together with physics-based approaches, such as flake-based reflectance models, to implement efficiently the appearance reproduction from a small number of bidirectional measurement geometries. With this rendering framework, we rendered a series of effect coating samples on an iPad display, simulating how these samples would be viewed inside a Byko-spectra effect light booth. We validated the appearance fidelity through psychophysical methods. We asked observers to evaluate the most important visual attributes that directly affect the appearance of effect coatings, i.e., the color, the angular dependence of color (color flop) and the visual texture (sparkle and graininess). Observers were asked to directly compare the rendered samples with the real samples inside the Byko-spectra effect light booth. In this study, we first validated the accuracy of rendering the color flop of effect coatings by conducting two separate visual tests, using flat and curved samples respectively. The results show an improved accuracy when curved samples were used (acceptability of 93% vs 80%). Secondly, we validated the digital reproduction of both color and texture by using a set of 30 metallic samples, and by including texture in the rendering using a sparkle model. We optimized the model parameters based on sparkle measurement data from the BYK-mac I instrument and using a matrix-adjustment model for optimization. The results from the visual tests show that the visual acceptability of the rendering is high at 90%.

Computer Vision Method in Beer Quality Evaluation—A Review

Beers are differentiated mainly according to their visual appearance and their fermentation process. The main quality characteristics of beer are appearance, aroma, flavor, and mouthfeel. Important visual attributes of beer are foam appearance (volume and persistence), as well as the color and clarity. To replace manual inspection, automatic, objective, rapid and repeatable external quality inspection systems, such as computer vision, are becoming very important and necessary. Computer vision is a non-contact optical technique, suitable for the non-destructive evaluation of the food product quality. Currently, the main application of computer vision occurs in automated inspection and measurement, allowing manufacturers to keep control of product quality. This paper presents an overview of the applications and the latest achievements of the computer vision methods in determining the external quality attributes of beer.

Dispersing hydrophobic natural colourant β-carotene in shellac particles for enhanced stability and tunable colour.

Colour is one of the most important visual attributes of food and is directly related to the perception of food quality. The interest in natural colourants, especially β-carotene that not only imparts colour but also has well-documented health benefits, has triggered the research and development of different protocols designed to entrap these hydrophobic natural molecules to improve their stability against oxidation. Here, we report a versatile microfluidic approach that uses single emulsion droplets as templates to prepare microparticles loaded with natural colourants. The solution of β-carotene and shellac in the solvent is emulsified by microfluidics into droplets. Upon solvent diffusion, β-carotene and shellac co-precipitates, forming solid microparticles of β-carotene dispersed in the shellac polymer matrix. We substantially improve the stability of β-carotene that is protected from oxidation by the polymer matrix and achieve different colour appearances by loading particles with different β-carotene concentrations. These particles demonstrate great promise for practical use in natural food colouring.

Separate banks of information channels encode size and aspect ratio.

Size and aspect ratio are ecologically important visual attributes. Relative size confers depth, and aspect ratio is a size-invariant cue to object identity. The mechanisms of their analyses by the visual system are uncertain. In a series of three psychophysical experiments we show that adaptation causes perceptual repulsion in these properties. Experiment 1 shows that adaptation to a square causes a subsequently viewed smaller (larger) test square to appear smaller (larger) still. Experiment 2 reveals that a test rectangle with an aspect ratio (height/width) of two appears more slender after adaptation to rectangles with aspect ratios less than two, while the same test stimulus appears more squat after adaptation to a rectangle with an aspect ratio greater than two. Significantly, aftereffect magnitudes peak and then decline as the sizes or aspect ratios of adaptor and test diverge. Experiment 3 uses the results of Experiments 1 and 2 to show that the changes in perceived aspect ratio are due to adaptation to aspect ratio rather than adaptation to the height and width of the stimuli. The results are consistent with the operation of distinct banks of information channels tuned for different values of each property. The necessary channels have log-Gaussian sensitivity profiles, have equal widths when expressed as ratios, are labeled with their preferred magnitudes, and are distributed at exponentially increasing intervals. If an adapting stimulus reduces each channel's sensitivity in proportion to its activation then the displacement of the centroid of activity due to a subsequently experienced test stimulus predicts the measured size or aspect ratio aftereffect.

Efficient Color Texture Classification Using Color Monogenic Wavelet Transform

Color textures are among the most important visual attributes in image analysis. From the practical point view of color texture image analysis, this paper proposes an effective multi-scale color texture classification algorithm that is rotation and scale invariant using non-marginal color monogenic wavelet transform. The proposed algorithm exploits the color monogenic wavelet transform to obtain multi-scale representation of training samples for each texture class. The coefficients of color monogenic wavelet transform represent a magnitude and three phases: two phases encode local color information while the third contains geometric information of color texture image. The multi-scale feature vector is composed of mean value, standard deviation, energy and entropy at different scales of each of the directional sub-bands. The experimental results of average correct classification rates are 98.67, 99.08 and $$99.89\%$$ which are obtained from different color texture databases demonstrate its superior performance and robustness of the proposed classifier. The proposed color texture feature vector is also shown to be effective for color texture classification.

Color texture classification using shortest paths in graphs.

Color textures are among the most important visual attributes in image analysis. This paper presents a novel method to analyze color textures by modeling a color image as a graph in two different and complementary manners (each color channel separately and the three color channels altogether) and by obtaining statistical moments from the shortest paths between specific vertices of this graph. Such an approach allows to create a set of feature vectors, which were extracted from VisTex, USPTex, and TC00013 color texture databases. The best classification results were 99.07%, 96.85%, and 91.54% (LDA with leave-one-out), 87.62%, 66.71%, and 88.06% (1NN with holdout), and 98.62%, 96.16%, and 91.34% (LDA with holdout) of success rate (percentage of samples correctly classified) for these three databases, respectively. These results prove that the proposed approach is a powerful tool for color texture analysis to be explored.

Texture analysis using volume-radius fractal dimension

Texture plays an important role in computer vision. It is one of the most important visual attributes used in image analysis, once it provides information about pixel organization at different regions of the image. This paper presents a novel approach for texture characterization, based on complexity analysis. The proposed approach expands the idea of the Mass–radius fractal dimension, a method originally developed for shape analysis, to a set of coordinates in 3D-space that represents the texture under analysis in a signature able to characterize efficiently different texture classes in terms of complexity. An experiment using images from the Brodatz album illustrates the method performance.

A simplified gravitational model to analyze texture roughness

Textures are among the most important visual attributes in image analysis. This paper presents a novel method to analyze texture, based on representing states of a simplified gravitational collapse from an image and extracting information from each state using fractal dimension. In this approach, an image evolves in times t={1,2,...,20}, each time representing a state, which is explored by the Bouligand-Minkowski method using radius r={3,4,...,8}. These parameters allow to create a set of feature vectors, which were extracted from Brodatz's textures and leaf textures. The best classification results were 98.75% and 86.67% of success rate (percentage of samples correctly classified) for these two databases, respectively. These results prove that the proposed approach opens a promising source of research in texture analysis to be explored.

Texture analysis using graphs generated by deterministic partially self-avoiding walks

Texture is one of the most important visual attributes for image analysis. It has been widely used in image analysis and pattern recognition. A partially self-avoiding deterministic walk has recently been proposed as an approach for texture analysis with promising results. This approach uses walkers (called tourists) to exploit the gray scale image contexts in several levels. Here, we present an approach to generate graphs out of the trajectories produced by the tourist walks. The generated graphs embody important characteristics related to tourist transitivity in the image. Computed from these graphs, the statistical position (degree mean) and dispersion (entropy of two vertices with the same degree) measures are used as texture descriptors. A comparison with traditional texture analysis methods is performed to illustrate the high performance of this novel approach. ► Create a graph containing only vertices and no edges. ► For each pixel of the image, perform the deterministic partially self-avoiding walk. ► For each transition of the walk, create an edge connecting their respective nodes in the graph. ► Texture classification is performed using graph properties.

Text independent writer recognition using redundant writing patterns with contour-based orientation and curvature features

We propose an effective method for automatic writer recognition from unconstrained handwritten text images. Our method relies on two different aspects of writing: the presence of redundant patterns in the writing and its visual attributes. Analyzing small writing fragments, we seek to extract the patterns that an individual employs frequently as he writes. We also exploit two important visual attributes of writing, orientation and curvature, by computing a set of features from writing samples at different levels of observation. Finally we combine the two facets of handwriting to characterize the writer of a handwritten sample. The proposed methodology evaluated on two different data sets exhibits promising results on writer identification and verification.

Shape classification using complex network and Multi-scale Fractal Dimension

Shape provides one of the most relevant information about an object. This makes shape one of the most important visual attributes used to characterize objects. This paper introduces a novel approach for shape characterization, which combines modeling shape into a complex network and the analysis of its complexity in a dynamic evolution context. Descriptors computed through this approach show to be efficient in shape characterization, incorporating many characteristics, such as scale and rotation invariant. Experiments using two different shape databases (an artificial shapes database and a leaf shape database) are presented in order to evaluate the method, and its results are compared to traditional shape analysis methods found in literature.

Gloss measurements of raw agricultural products using image analysis

Gloss is considered one of the most important visual attributes of many foods, which is difficult to measure objectively. In this paper, a gloss imaging system (GIS) was implemented to evaluate the suitability of four indexes for measuring gloss from intensity images in flat and curved surfaces and to analyze gloss of some fruits and vegetables. Three indexes were computed from goniometric curves: maximum intensity (MI), width of the curve at 50% (WC), and area under the curve (AC). The fourth index was computed from the same intensity images as the average of the reflected luminance flux (LF) at the surface of the image. The results showed linear relationships (R-2 = 0.97) when values of MI, AC, LF for flat and curved gloss targets in the range of 4-90 units of gloss (GU) were compared with their standard gloss levels. However, the measured gloss was significantly affected by curvature and unevenness of the surface of fruits and vegetables. In spite of this, we concluded that a colour digital camera of moderate cost combined with simple image analysis procedure can yield parameters which correlate highly with the gloss appearance of fruits and vegetables and allow measurements over a very wide range of gloss with high sensitivity. (C) 2009 Elsevier Ltd. All rights reserved. (Less)

Medical image retrieval based on complexity analysis

Texture is one of the most important visual attributes used in image analysis. It is used in many content-based image retrieval systems, where it allows the identification of a larger number of images from distinct origins. This paper presents a novel approach for image analysis and retrieval based on complexity analysis. The approach consists of a texture segmentation step, performed by complexity analysis through BoxCounting fractal dimension, followed by the estimation of complexity of each computed region by multiscale fractal dimension. Experiments have been performed with MRI database in both pattern recognition and image retrieval contexts. Results show the accuracy of the method and also indicate how the performance changes as the texture segmentation process is altered.