Colour constancy based on texture similarity for natural images

Colour constancy is a classical problem in computer vision. Although there are a number of colour constancy algorithms based on different assumptions, none of them can be considered as universal. How to select or combine these available methods for different natural image characteristics is an important problem. Recent studies have shown that the texture feature is an important factor to consider when selecting the best colour constancy algorithm for a certain image. In this paper, Weibull parameterisation is used to identify the texture characteristics of colour images. According to the texture similarity, the best colour constancy method (or best combination of methods) is selected out for a specific image. The experiments were carried out on a large data set and the results show that this new approach outperforms current state‐of‐the‐art single algorithms, as well as some combined algorithms.     

Spectrophotometric error in colour coordinates introduced by fluorescence of white calibration tile

Fluorescence has been detected in some white standard tiles intended for the calibration of spectrophotometers for colour measurements. The problem is that usually no warning is given to the user about it, giving raise to errors if they are calibrated using conventional spectrophotometric techniques. This work analyzes the differences on the colour coordinates of one of these standards measured with a polychromatic illumination spectrophotometer and with a monochromatic illumination one. This work also analyzes the colour coordinates error obtained when other coloured standards are calibrated against one of these white fluorescent standards, when reflectance measurement is done with a polychromatic illumination spectrophotometer as well as with a monochromatic illumination instrument. These are the two most typical situations found in practice where the use of fluorescent standards may produce errors. © 2004 Wiley Periodicals, Inc. Col Res Appl, 29, 111–114, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/col.10233     

The effect of texture on the pass/fail colour tolerances of injection‐molded plastics

The effect of surface texture on the pass/fail colour tolerance region was estimated using acrylonitrile–butadiene–styrene injection‐molded plaques in three different colours and with different surface textures. Variations in the measured colour coordinates due to differences in texture for three selected colours were observed using the specular component excluded mode (SCE) of the spectrophotometer. Such variations could not, however, be clearly distinguished in the specular component included mode. The colour tolerance regions were assessed through a combination of colour measurement and a psychometric study involving 35 observers. The limits of acceptance of colour differences varied substantially with the surface texture. In some cases, the observers accepted a larger colour difference for the textured than for the smooth surface, whereas in other cases, the reverse situation was noted. Thus, no general conclusion regarding the influence of texture on the tolerance region can be drawn, since the acceptable differences were colour‐ and/or surface texture‐dependent. In the case of textured surfaces, measurements made in the SCE mode of the spectrophotometer appear to be more meaningful for assessing perceived colour differences and tolerance regions. © 2006 Wiley Periodicals, Inc. Col Res Appl, 32, 47–54, 2007; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/col.20284     

Computer simulation study of images in contact and near-contact printing

Versatile computer programs capable of simulating near-contact images from arbitrary objects and illumination were reported. Their capability was demonstrated in examples of combinations of different types of object and illumination. From the specific examples, we were able to derive certain general rules: (1) Polychromatic illumination is always better than monochromatic illumination. (Besides observing the examples given above, polychromatic illumination also helps when standing waves in photoresist are considered.) (2) Negative masks are easier to print than positive ones. Note that a negative mask in the sense of optical diffraction means smaller dimension for transparent parts of the mask. (3) Some well designed irregularities in the mask pattern improves the image. (4) The effective depth tolerance is between the limits set by the focussing effect and the image spreading effect. (5) Holographic mask should relax flatness and exposure tolerance.     

基于灰度形态重构的颗粒图像分割方法

提出了一种基于距离变换、形态重构和分水岭算法的图像分割算法。将一幅图像通过距离变换得到距离灰度图,与形态重构算法结合,得到颗粒图像的标识点图,用标识点图对距离灰度图进行分割,再用分水岭变换对分割后的距离灰度图进行变换。试验表明,该算法能有效合理地解决粘连或者重叠颗粒等物体的分割。     

Colour combination effects in experimental rooms*

This article deals with the way colours in a room affect each other through contrast effects and reflections. The study presented is based on the visual observations of the colour appearance of three inherent colours in a sequence of experimental situations. My point of departure was a yellow, blue, and red room. The room had distinctly different colour appearances of the same inherent colours when observed at different locations. The effects of both contrasts and reflections were evident. However, reflection effects seemed to dominate the situation. In a study of small experimental rooms, different combinations of the same three inherent colours were systematically tested. Comparisons were made to examine the differences in colour appearance between monochromatic rooms and multicoloured rooms with varying colour schemes. The illumination was kept stable. In the cases studied, it was obvious how the colours in the two‐coloured rooms became more alike or “neutralized each other.” The contrast strengthening between abutting areas on the same level had distinct significance for colour appearance and perception of space. However, not in such a way that the perceived colour differences became larger in the two‐coloured room than between each monochromatic rooms. © 1999 John Wiley & Sons, Inc. Col Res Appl, 24, 230–242, 1999     

医学图像分割方法研究

分析了医学图像处理的基本流程,对医学图像的分割进行了数学描述。探讨了医学图像分析中的三类主要方法,包括基于区域的图像分割,基于边缘的图像分割,基于特定理论的图像分割。详细阐述了阈值法,边缘检测法及分水岭算法的主要思想。     

Evaluating colour image difference metrics for gamut-mapped images

The quality of several colour image difference metrics, pixelwise CIELAB Δ E _ab , S-CIELAB, iCAM, Structural Similarity Index, Universal Image Quality and the hue-angle algorithm, have been investigated. These results were compared with the results from a psychophysical experiment in which the perceptual image difference was evaluated. Six original images were reproduced using six different colour gamut-mapping algorithms. The results of our experiment indicate that perceptual image difference cannot be directly related to colour image difference calculated by current metrics. Therefore, it is currently not possible to evaluate colour gamut mapping quality using colour image difference metrics.     

Colour dependency of textile samples on the surface texture

In this paper, the perceptual and instrumental effects of texture on colour is investigated, using 63 textile samples, in nine colour centres and seven texture structures. The effectiveness of texture is evaluated by assessing colour differences between six texture samples and a standard texture in each colour group. Experimental results show that the sample texture has a significant effect on the measured and perceived colour and its influence depends on the colour centre of the sample. The magnitude of texture effect is more dependent on the texture type than on its coarseness. A new term to evaluate texture difference of a pair of textile samples was defined using a Gabor filter (Gabor texture difference). The visual colour changes gave a good correlation with Gabor texture difference values; however, the colour of the samples affected this correlation. So the colour change, as a result of texture differences, depends on two independent variables consisting of the Gabor texture difference and the colour centre of samples.     

An unsupervised method for dominant colour region segmentation in yarn‐dyed fabrics

This paper presents a novel unsupervised approach to detect dominant colour regions standing out conspicuously in yarn‐dyed fabric images. For a dominant colour region of a yarn‐dyed fabric, measured by an imaging system, its individual yarn has an irregular three‐dimensional shape resulting in significant colour difference among pixels of the yarn. This difference leads to difficulty in segmenting yarns into dominant colour regions. A probabilistic model is proposed in this study to associate the colour of a dominant colour region with the colours of its yarns. Based on this model, the colour histograms of a dominant colour region are first estimated from those of yarns in a yarn‐dyed fabric image. Then, a hierarchical segmentation structure is devised to detect dominant colour regions in the image. Experimental results show that the proposed approach achieves satisfactory performance for dominant colour region segmentation in yarn‐dyed fabric images, with high computational efficiency.     

Control of optics in random access analysers

The technology behind random access analysers involves flexible optical systems which can measure absorbances for one reaction at different scheduled times, and for several reactions performed simultaneously at different wavelengths. Optics control involves light sources (continuous and flash mode), indexing of monochromatic filters, injection-moulded plastic cuvettes, optical fibres, and polychromatic analysis.     

Investigation of texture effect on visual colour difference evaluation

The texture effect on visual colour difference evaluation was investigated in this study. Five colour centers were selected and textured colour pairs were generated using scanned textile woven fabrics and colour‐mapping technique. The textured and solid colour pairs were then displayed on a characterized cathode ray tube (CRT) monitor for colour difference evaluation. The colour difference values for the pairs with texture patterns are equal to 5.0 CIELAB units in lightness direction. The texture level was represented by the half‐width of histogram, which is called texture strength in this study. High correlation was found between texture strength and visual colour difference for textured colour pairs, which indicates that an increasing of 10 units of texture strength in luminance would cause a decreasing of 0.25 units visual difference for the five colour centers. The ratio of visual difference between textured and solid colour pairs also indicates a high parametric effect of texture. © 2005 Wiley Periodicals, Inc. Col Res Appl, 30, 341–347, 2005; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/col.     

Colour and proportion of grains measurement in through-body porcelain tiles by means of image processing

A common demand in the production of through-body porcelain tiles is the visual uniformity of the produced tiles. We assume that their visual appearance can be controlled by properly acting over the process control. This paper presents an image processing method for obtaining a feedback for it. The method estimates two important properties, which are colour and proportion of each kind of grains forming the tile. It consists of two steps: a colour segmentation by applying the clustering algorithm ‘Fuzzy C-Means’, and the centres refinement of the former segmentation, proposed by us. The centres refinement proposal is based on the colour information and the colour mixing process. The experimental results show that the measurements of the colour and the proportion of grains obtained with the centres refinement, are more accurate compared to the ones obtained with ‘Fuzzy C-Means’.     

Determination of steel quality based on discriminating textural feature selection

Image data can be acquired from a product surface in real time by image sensor systems in chemical plants. For quality determination based on these image datasets, effective texture classification methodology is essential to handle highly dimensional images and to extract quality-related information from these product surface images.Wavelet texture analysis is useful for reducing the dimension and extracting textural information from images. Although wavelet texture analysis extracts only textural characteristics from images, the extracted features still contain unnecessary information for classification. The texture analysis method can be improved by retaining only class-dependent features and removing common features. In previous works, best basis and local discriminant basis are the most popular techniques for selecting an important basis from the wavelet packet basis. However, feature selection based on wavelet texture analysis has been studied for texture classification. Because previous methods are designed for wavelet coefficients with features for analysis, their performance is poor with wavelet texture analysis.We propose a novel texture classification methodology for quality determination based on feature selection using wavelet texture analysis. The proposed methodology applies the sequential forward floating selection (SFFS) algorithm as a feature selection strategy to select discriminating wavelet signatures using wavelet texture analysis. The proposed methodology is validated through quality determination for industrial steel surfaces. The results show that the proposed method has fewer classification errors with fewer number of features than previous methods.     

基于图像的皮肤纹理评价算法研究

皮肤表面纹理或微轮廓的量化评价对抗皱宣称的化妆品功效评价有重要意义。基于皮肤美容领域的应用需求和日常生活的实际需要,结合图像处理领域的相关算法,对皮肤的基础纹理特征展开了研究。首先,将实验实测的皮肤图像转为灰度图像,再通过对比度受限的自适应直方图均衡化对图像进行增强,之后通过高斯滤波去除图像的噪声,再采用维纳滤波对纹理的细节信息进行增强,得到纹理清晰的皮肤图像。通过实验确定适合于皮肤纹理评价的灰度共生矩阵的灰度级数和距离,基于灰度共生矩阵算法对皮肤纹理进行统计分析,提出了基于4个纹理特征参数的综合指标数学模型,并应用该模型对全部皮肤图像进行了纹理特征定量评价,同时也由专家对这些皮肤图像进行视觉盲评,2种评价方法一致性良好。     

A computer‐assisted colour selection system based on aesthetic measure for colour harmony and fuzzy logic theory

An aesthetic measure based approach for constructing a colour design/selection system is proposed in this article. In this model, an image data base for the relationships between the psychological preference of customers and clothing colour tones is built using the membership functions of a fuzzy set, and an aesthetic measure calculation method based on colour harmony is also proposed. In addition, a skin colour detection theory is proposed to construct a skin colour detection program to detect the skin colour of a customer, which is then taken as the major colour in matching the skin, polo shirt, and(or) pant colours to select the best colour combination. Integrating the skin colour detection theory, colour harmony theory, aesthetic measure method, and fuzzy set theory, a program is constructed to build an aesthetic measure based colour design/selection system. With the aid of this system, one can get proper cloth colours to match his/her skin colour and image requirement by starting with inputting one's colour photo, catching image with a camera, or inputting R, G, B values of his/her skin. The theoretical results for the ranks of clothing colours proposed by the system are examined with the experimental results and the result shows they are very close, suggesting that the proposed colour selection system is acceptable. Although the selection of clothing colours is taken as an example to specify the methodology, it can also be used to develop a system for other products. © 2008 Wiley Periodicals, Inc. Col Res Appl, 33, 411–423, 2008     

Evaluation of texture distribution during the industrial polishing process of porcelain stoneware tiles

The present work addresses the distribution of texture over the surface of porcelain stoneware tiles due to kinematics imposed by industrial polishing process. The scratching process was simulated using a computational algorithm, which was based on the kinematic equations for the whole myriad of abrasive particles. Different scratching patterns were identified over the polished surface and their corresponding positions were mapped. The experimental results showed that regions in the tile centre present smaller tendencies for exhibiting preferential textures than those of the lateral ones. The final texture was slightly asymmetric and different from those simply left by the last scratches. The definition of three polishing domains was then suggested according to different phenomenological criteria. Results from both experiments and simulations made evident the influence of the kinematic parameters adopted by the industries on the polishing quality of porcelain stoneware tiles.     

基于图像傅里叶变换纹理特征和概率神经网络的气固流化床流型识别

提出一种基于图像傅里叶变换纹理特征和概率神经网络相结合的气固流化床流型识别的新方法。该方法利用高速摄影系统获取流型图像。首先对流型图像进行组合滤波去噪,然后运用长方环傅里叶周向谱能量百分比法来计算图像频率分布特征,从而建立流型图像的纹理特征向量,并结合概率神经网络进行训练,实现流型的识别。实验结果表明,该方法能有效地识别气固流化床中鼓泡床、节涌床、湍动床、快速流化床、稀相输送五种典型流型,整体识别率达到98%,为流型识别开辟一条新途径。     

Estimation of fuzzy sets for computational colour categorization

Colour is an important visual cue for computer vision applications. However, until recently, the automatic assignment of names to image regions has not been widely used due to the nonexistence of a general computational model for colour categorization. In this article we present a model for colour naming based on fuzzy‐set theory, in which each of the 11 basic colour terms defined by Berlin and Kay 1 is modeled as a fuzzy set with a characteristic function that assigns a membership value to the category to any colour sample. The model is based on combining two well‐known functions, a sigmoid and a Gaussian, to define a membership function for colour categories. It is denoted here as the sigmoid–Gaussian function and it fulfills a set of properties that make it adequate to this purpose. The characteristic functions for each colour category have been fitted to data obtained from a psychophysical experiment and the model has been tested on the Munsell colour array to show its validity. The results obtained indicate that our approach can be very useful as a first step to expand the use of colour‐naming information in computer vision applications. © 2004 Wiley Periodicals, Inc. Col Res Appl, 29, 342–353, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/col.20042