Wood inspection with non-supervised clustering

Abstract. The appearance of sawn timber has huge natural variations that the human inspector easily compensates for mentally when determining the types of defects and the grade of each board. However, for automatic wood inspection systems these variations are a major source for complication. This makes it difficult to use textbook methodologies for visual inspection. These methodologies generally aim at systems that are trained in a supervised manner with samples of defects and good material, but selecting and labeling the samples is an error-prone process that limits the accuracy that can be achieved. We present a non-supervised clustering-based approach for detecting and recognizing defects in lumber boards. A key idea is to employ a self-organizing map (SOM) for discriminating between sound wood and defects. Human involvement needed for training is minimal. The approach has been tested with color images of lumber boards, and the achieved false detection and error escape rates are low. The approach also provides a self-intuitive visual user interface. Received: 16 December 2000 / Accepted: 8 December 2001 Correspondence to: O. Silvén     

Physicochemical and Sensory Properties of Soymilk-incorporated Bulgur

ABSTRACT Bulgur cooked in soymilk of 6% and 9% solid content had significantly ( P < 0.05) higher bulk density compared with bulgur cooked in soymilk of 3% solid content and control bulgur cooked in water. As the soymilk solid content increased, pilav bulgur yield increased whereas fine bulgur yield decreased. The SDS-extractability of bulgur proteins increases with the increase in soymilk solid content. Water absorption capacity of fine bulgur samples was affected by soymilk incorporation, and variations in oil absorption capacity were not significant ( P > 0.05). Soymilk incorporation improved color and sensory properties of pilav and fine bulgur. The results of this study suggest that soymilk can be successfully applied to bulgur production.     

彩色感光材料冲洗中隐青的产生及解决办法

在彩色感光材料冲洗过程中，经过彩色显影液处理的感光药膜中，同时生成黄、品红、青三种颜色的染料，但实际上由于青染料隐色体的电位比黄和品红染料隐色体的电位高，醌二亚胺阳离子没有足够的能力将其氧化，因此在彩色显影液中生成的是青染料的隐色体，只有在进入漂白液以后，才能形成真正的青色染料，如果由于某种原因，使得这种转变不能全部完成，就会有一部分青染料的隐色体存留在影像的青色部分，形成隐青，直接影响彩色影像的质量。本文系统地阐述了隐青的危害、产生的原因和解决的办法。     

NIST 0:45 reflectometer

The NIST 0:45 reflectometer measures the spectral reflectance factor at an influx angle of 0° and an efflux angle of 45° of colored, nonfluorescent specimens at room temperature, with widths ranging from 3 to 10 cm and heights from 3 to 20 cm and with an uncertainty of less than 0.5 in color difference units. Published in 2008 by John Wiley & Sons, Inc. Col Res Appl, 33, 94–99, 2008     

Spectral color reproduction minimizing spectral and perceptual color differences

In this article, we are combining minimization criteria in the colorant separation process for spectral color reproduction. The colorant separation is performed by inverting a spectral printer model: the spectral Yule‐Nielsen modified Neugebauer model. The inversion of the spectral printer model is an optimization operation in which a criterion is minimized at each iteration. The approach we proposed minimizes a criterion defined by the weighted sum of a spectral difference and a perceptual color difference. The weights can be tuned with a parameter α ∞ [0, 1]. Our goal is to decrease the spectral difference between the original data and its reproduction and also to consider perceptual color difference under different illuminant conditions. In order to find the best α value, we initially compare a pure colorimetric criterion and a pure spectral criterion for the reproduction, then we combine them. We perform four colorant separations: the first separation will minimize the 1976 CIELAB color difference where four illuminants are tested, the second separation will minimize an equally weighted summation of 1976 CIELAB color difference with the four illuminants tested independently, the third colorant separation will minimize a spectral difference, and the fourth colorant separation will combine a weighted sum of a spectral difference and one of the two first colorimetric differences previously introduced. This last colorant separation can be tuned with a parameter in order to emphasize on spectral or colorimetric difference. We use a six colorants printer with artificial inks for our experiments. The prints are simulated by the spectral Yule‐Nielsen modified Neugebauer model. Two groups of data are used for our experiments. The first group describes the data printed by our printing system, which is represented by a regular grid in colorant space of the printer and the second group describes the data which is not originally produced by our printing system but mapped to the spectral printer gamut. The Esser test chart and the Macbeth Color Checker test chart have been selected for the second group. Spectral gamut mapping of this data is carried out before performing colorant separation. Our results show improvement for the colorant separations combining a sum of 1976 CIELAB color difference for a set of illuminants and for the colorant separation combining a sum of 1976 CIELAB color difference and spectral difference, especially in the case of spectral data originally produced by the printer. © 2008 Wiley Periodicals, Inc. Col Res Appl, 33, 494–504, 2008     

Chromatic induction: Opponent color or complementary color process?

In present convention, chromatic induction (simultaneous and successive contrast) is usually held to be an opponent color process. Fifty years ago, it was an accepted complementary color process. The latter was never disputed yet apparently overlooked, and is here shown to be the more accurate account by inspecting afterimages and published data on simultaneous and successive hue induction. © 2007 Wiley Periodicals, Inc. Col Res Appl, 33, 77–81, 2008     

Uncertainty analysis for the NIST 0:45 Reflectometer

Sets of color tiles are available from the National Institute of Standards and Technology calibrated using the NIST 0:45 Reflectometer. The uncertainties associated with the measured values for the color tiles are an indispensable component of the calibration report that accompanies these tiles. A systematic, analytical approach developed previously was applied to the particular case of the reference instrument and color tile set, taking into account the operation and characteristics of the instrument and the spectral properties of the set. The primary sources of uncertainty were identified, and the resulting uncertainties in the color space values L*, a*, and b* were determined. In general, the uncertainties are lowest for those color tiles whose reflectance factors are nearly constant with wavelength. Published in 2008 by John Wiley & Sons, Inc. Col Res Appl, 33, 100–107, 2008     

Detection and modification of confusing color combinations for red‐green dichromats to achieve a color universal design

Color‐vision deficiency is a relatively common genetic condition, which often leads to the obstruction of necessary information in colored images. It is important to minimize such inconvenient effects in communication using colored images from a universal design perspective. The universal design principle stipulates that all environments and products should be usable by all people, regardless of age, physical attributes, and ability. This article proposes a method to detect color combinations in a given image that would confuse color dichromats, and suggests a way in which to modify them to make the image easily distinguishable for both normal and dichromatic observers. Confusing color combinations were detected based on a color‐difference calculation using simulations of how the color would appear to dichromats. The confusing colors were then modified based on the minimization of an evaluation function, which was defined as the sum of the degree of confusion and the degree of color change from the original image. Several colored images obtained by the proposed method were compared with the originals by red–green dichromatic observers who judged them to be clearer, thereby confirming that the proposed method was effective for color rendering for universal design. © 2008 Wiley Periodicals, Inc. Col Res Appl, 33, 203–211, 2008     

Perceptual evaluation of color gamut mapping algorithms

The recommendation of the CIE has been followed as closely as possible to evaluate the accuracy of five color gamut mapping algorithms (GMAs)—two nonspatial and three spatial algorithms—by psychophysical experiments with 20 test images, 20 observers, one test done on paper and a second one on display. Even though the results do not show any overall “winner,” one GMA is definitely perceived as not accurate. The importance of a high number of test images to obtain robust evaluation is underlined by the high variability of the results depending on the test images. Significant correlations between the percentage of out‐of‐gamut pixels, the number of distinguishable pairs of GMAs, and the perceived difficulty to distinguish them have been found. The type of observers is also important. The experts, who prefer a spatial GMA, show a stronger consensus and look especially for a good rendering of details, whereas the nonexperts hardly make a difference between the GMAs. © 2008 Wiley Periodicals, Inc. Col Res Appl, 33, 470–476, 2008