Spatial Color Research Articles

Developing Forecasting Model in Thailand Fashion Market Based on Statistical Analysis and Content-Based Image Retrieval

Traditional trend forecasting process in Thailand fashion industry was challenged by a fast fashion. In this paper, the Content-Based Image Retrieval (CBIR) technique is utilized for retrieval of a fashion trendsetter in fast fashion influence. Firstly, six fashion theories were implemented as 12 variables affecting the trendsetter. Cluster analysis, and factor analysis approach were used to find out the source of a fashion trendsetter as well. Cluster analysis separated all samples into three groups with different fashion ways. Moreover, factor analysis technique grouped all variables into three important factors. From such techniques, Internet media clearly is the best source of a fashion trendsetter. In the authors' model, traditional forecasting sources were added up with a fast fashion influence from CBIR. Then, the CBIR was evaluated in terms of efficiency compared with a real fashion expert in the Thai fashion industry. From statistical test, spatial color distribution yields high efficiency in selecting similar fashion style as a fashion expert.

Metro 스타일 GUI의 가시화 효율 최적화

Graphical user interfaces (GUI) in modern software deliver information visually, and a well-designed interface can provide information to the use in an organized and intuitive manner while poorly-designed interfaces can cause visual inconvenience and confusion. In order to effectively deliver information to the user, visual attention should be placed on a prominent location in the image. This paper introduces a method based on a human visual system (HVS) that can improve Metro-style GUIs by reducing a user's workload to visually find information. Our method is designed with spatial mapping and color mapping for buttons in the Metro-style GUI. Also we define a metric for Metro-style GUI effectiveness, including an optimization algorithm. The results show that our method improves the performance of visual search tasks in a Metro-style GUI.

Self-Adaptive Structure of Remote Phosphor for Phosphor-Converted White LEDs

High-efficiency white light-emitting diodes (LEDS) with superior spatial color homogeneity (SCH) have been investigated. In this paper, a new method of packaging of phosphor-converted white LEDs (pc-WLEDs) that employs a self-exposure technique as well as a remote phosphor configuration is presented. It is suggested that this remote phosphor configuration reduces the backscattering of emission light of LEDs as well as the operating temperature of the phosphor, which improve the luminous efficiency and reliability of pc-WLEDs. The slurry method with self-exposure process was applied to achieve a self-adaptive remote phosphor coating layer surrounding the LED chips which could map the angular intensity distribution of blue light emitted from LED chips every direction and therefore improve the spatial color homogeneity. The experimental results show that pc-WLEDs with self-adaptive remote phosphor coating has remarkable advantages over conventional dispensing coating and conformal coating in terms of efficiency and color homogeneity.

A modified fuzzy color histogram using vision perception variation of pixels at different location

The fuzzy linking color histogram considers not only the similarity of different colors from different bins but also the dissimilarity of those colors assigned to the same bin. Moreover, it projects the three-dimension histogram onto the one single-dimension histogram, which reduces the complexity of computation. Spatial fuzzy linking color histogram (SFLCH) combines fuzzy linking color histogram with spatial information that describes the color distribution of pixels in different regions. Meanwhile, the concept "color complexity" is defined in histogram similarity measure in order to add the influence of human vision perception to image retrieval. Compared with other methods, the modified fuzzy color histogram is proved to be more accurate and effective for the content-based image retrieval from the experimental results.

Frequential versus spatial colour textons for breast TMA classification

Advances in digital pathology are generating huge volumes of whole slide (WSI) and tissue microarray images (TMA) which are providing new insights into the causes of cancer. The challenge is to extract and process effectively all the information in order to characterize all the heterogeneous tissue-derived data. This study aims to identify an optimal set of features that best separates different classes in breast TMA. These classes are: stroma, adipose tissue, benign and benign anomalous structures and ductal and lobular carcinomas. To this end, we propose an exhaustive assessment on the utility of textons and colour for automatic classification of breast TMA. Frequential and spatial texton maps from eight different colour models were extracted and compared. Then, in a novel way, the TMA is characterized by the 1st and 2nd order Haralick statistical descriptors obtained from the texton maps with a total of 241×8 features for each original RGB image. Subsequently, a feature selection process is performed to remove redundant information and therefore to reduce the dimensionality of the feature vector. Three methods were evaluated: linear discriminant analysis, correlation and sequential forward search. Finally, an extended bank of classifiers composed of six techniques was compared, but only three of them could significantly improve accuracy rates: Fisher, Bagging Trees and AdaBoost. Our results reveal that the combination of different colour models applied to spatial texton maps provides the most efficient representation of the breast TMA. Specifically, we found that the best colour model combination is Hb, Luv and SCT for all classifiers and the classifier that performs best for all colour model combinations is the AdaBoost. On a database comprising 628 TMA images, classification yields an accuracy of 98.1% and a precision of 96.2% with a total of 316 features on spatial textons maps.

The effects of spatial proximity and colour similarity on competition between targets and distractors on visual working memory.

The effects of spatial proximity and colour similarity on competition between targets and distractors on visual working memory.

What does visual suffix interference tell us about spatial location in working memory?

A visual object can be conceived of as comprising a number of features bound together by their joint spatial location. We investigate the question of whether the spatial location is automatically bound to the features or whether the two are separable, using a previously developed paradigm whereby memory is disrupted by a visual suffix. Participants were shown a sample array of four colored shapes, followed by a postcue indicating the target for recall. On randomly intermixed trials, a to-be-ignored suffix array consisting of two different colored shapes was presented between the sample and the postcue. In a random half of suffix trials, one of the suffix items overlaid the location of the target. If location was automatically encoded, one might expect the colocation of target and suffix to differentially impair performance. We carried out three experiments, cuing for recall by spatial location (Experiment 1), color or shape (Experiment 2), or both randomly intermixed (Experiment 3). All three studies showed clear suffix effects, but the colocation of target and suffix was differentially disruptive only when a spatial cue was used. The results suggest that purely visual shape-color binding can be retained and accessed without requiring information about spatial location, even when task demands encourage the encoding of location, consistent with the idea of an abstract and flexible visual working memory system.

Development of 15 MHz 2-2 piezo-composite ultrasound linear array transducers for ophthalmic imaging

High frequency (>15MHz) ultrasound imaging is capable of producing high spatial resolution B-mode and color Doppler images for the efficient diagnosis of ocular diseases. However, commercial high frequency ultrasound imaging systems cannot currently provide its full capability for ophthalmic applications because either single element or annular array transducers are used in conjunction with mechanical scanning. To overcome the current limitations, 15MHz 128-element linear array transducers were developed, which are suitable to cover the whole eye from the eyelid in anterior segment to orbital fundus in posterior segment. To achieve the highest electromechanical coupling coefficient, 2-2 piezo-composite was designed and fabricated as an active layer. For the design, the simple model of the thickness-mode oscillation was derived and used in the 1-D model simulator such as PiezoCAD. Also, the usability of the simple model was verified by comparing its simulation results with those by finite element model-based PZFlex. In addition, easy fabrication procedure for the high frequency 2-2 piezo-composite arrays was proposed. In performance evaluation, the pulse-echo response of a representative composite element showed the center frequency of 14.4MHz and the −6dB fractional bandwidth of 69.4%. Measured insertion loss was achieved higher than −33.9dB and crosstalk level between elements less than −30dB. From the evaluation results, it is expected that the linear array transducer developed using the proposed design and fabrication methods can provide a potential alternative for high frequency ophthalmic imaging with the desired capability.

Visual Tracking Via Kernel Sparse Representation With Multikernel Fusion

It remains a challenging task to track an object robustly due to factors such as pose variation, illumination change, occlusion, and background clutter. In the past decades, a number of researchers have been attracted to tackling these difficulties, and they proposed many effective methods. Among them, sparse representation-based tracking method is a promising. While much success has been demonstrated, there are several issues that still need to be addressed. First, the introduction to trivial occlusion templates brings a high computational cost of this method. Second, the utilization of raw template object representation makes this method difficult to adopt sophisticated object features. To solve these problems, we consider the sparse representation problem in a kernel space and propose a kernel sparse representation (KSR)-based tracking algorithm. Under the kernel representation, it is not necessary to introduce trivial occlusion templates in order to reduce the computational cost. Furthermore, multikernel fusion allows our method to use multiple sophisticated object features, such as spatial color histogram and spatial gradient-orientation histogram, and let these features complement each other during the tracking process. Comparative experiments on challenging scenes demonstrate that our KSR-based tracking algorithm outperforms the state-of-the-art approaches in tracking accuracy.

GM-PHD-Based Multi-Target Visual Tracking Using Entropy Distribution and Game Theory

Tracking multiple moving targets in a video is a challenge because of several factors, including noisy video data, varying number of targets, and mutual occlusion problems. The Gaussian mixture probability hypothesis density (GM-PHD) filter, which aims to recursively propagate the intensity associated with the multi-target posterior density, can overcome the difficulty caused by the data association. This paper develops a multi-target visual tracking system that combines the GM-PHD filter with object detection. First, a new birth intensity estimation algorithm based on entropy distribution and coverage rate is proposed to automatically and accurately track the newborn targets in a noisy video. Then, a robust game-theoretical mutual occlusion handling algorithm with an improved spatial color appearance model is proposed to effectively track the targets in mutual occlusion. The spatial color appearance model is improved by incorporating interferences of other targets within the occlusion region. Finally, the experiments conducted on publicly available videos demonstrate the good performance of the proposed visual tracking system.

Optimization of a merit function for the visual perception of color uniformity in spot lights

AbstractThe objective of the present study is the development of an optimized evaluation method which describes color uniformity in the far field of light‐emitting diode (LED) spot lights related to visual perception of color and pattern. The merit function is requested to evaluate measurements and optical simulations of spot light systems. A human factor experiment was performed as a two‐alternative forced choice (2AFC) test. During the experiment, a pairs of spot lights with various spatial color distributions were shown successively to the subject. The subjects had to select the more even spot light of the pair shown.The perceived rank order of spot lights was calculated afterwards. It was compared with five different mathematical functions describing several aspects of spatial color uniformity based on the CIELAB color space. These are the widely used color difference ΔE, gradient, difference of color average, circular symmetry description, and linear smoothness. No single basic function fits the perception in a sufficient way because none of the function considers all visual aspects. For a better correlation between the visual perception and the merit function, a linear combination of four basic functions is proposed. The designed merit function for the color uniformity of spot lights USL is more effective for the prediction of the visual perception. A correlation value of 0.91 is reached. It enables a quantitative evaluation of those LED lighting systems and protects against individual subjective judgments. © 2014 Wiley Periodicals, Inc. Col Res Appl, 40, 287–296, 2015

Salient object detection based on multi‐scale super‐pixels and saliency propagation

A novel method to detect the most salient object from an image is proposed. Saliency cues such as spatial colour distribution and the saliency prior are extended to super-pixels and are integrated to compute the final saliency. The super-pixels are generated in multiple scales so that the proposed method is adaptive to objects of different sizes. Moreover, to solve the problem that many saliency detection algorithms rely on local evidences, it is proposed to propagate the saliency information based on the spectral affinities of super-pixels. Experimental results have proven that the proposed method achieves discriminative saliency maps and outperforms the state-of-the-art methods.

Detailed experimental characterization of reflectance spectra ofSasakia charondabutterfly using multispectral optical imaging

A multispectral acquisition system to examine the bidirectional reflectance distribution function of structurally colored biological materials in the visible range is presented. We focus on the purple-blue and white-pearl wing scales of the male butterfly Sasakia charonda. Multispectral imaging was done by changing the illumination angular position around the sample as well as that of the specimen around the multispectral sensor axis. Reflectance spectra were transformed to color coordinates and visualized in different color spaces. Spectral analysis shows distinct iridescent patterns in purple-blue and white-pearl scales. Colorimetric analysis indicates that purple-blue scales enhance blue coloring and exhibit higher color saturation. Principal component analysis reveals that the number of principal components that account for more than 99% of reflectance vari- ability was higher in white-pearl scales. This suggests a higher spectral complexity in their spatial color pattern formation. Reconstruction of reflectance spectra from the principal components is discussed. We conclude that multispectral imaging provides new insights into spatial reflectance mapping that result from the combination of structural colorations and variable amounts of absorption pigments. © 2014 Society of Photo-Optical Instrumentation Engineers

Termite Retinex: a new implementation based on a colony of intelligent agents

The original presentation of Retinex, a spatial color correction and image enhancement algorithm modeling the human vision system, as proposed by Land and McCann in 1964, uses paths to explore the image in search of a local reference white point. The interesting results of this algorithm have led to the development of many versions of Retinex. They follow the same principle but differ in the way they explore the image, with, for example, random paths, random samples, convolution masks, and variational formulations. We propose an alternative way to explore local properties of Retinex, replacing random paths by traces of a specialized swarm of termites. In presenting the spatial characteristics of the proposed method, we discuss differences in path exploration with other Retinex implementations. Experiments, results, and comparisons are presented to test the efficacy of the proposed Retinex implementation.

An Improved White-RGB Color Filter Array Based CMOS Imaging System for Cell Phones in Low-Light Environments

In this paper, a novel White-RGB (WRGB) color filter array-based imaging system for cell phone is presented to reduce noise and reproduce color in low illumination. The core process is based on adaptive diagonal color separation to recover color components from a white signal using diagonal reference blocks and location-based color ratio estimation in the luminance space. The experiments, which are compared with the RGB and state-of-the-art WRGB approaches, show that our imaging system performs well for various spatial frequency images and color restoration in low-light environments.

Visual Fingerprints: Identifying, Summarizing and Comparing Music

The paper presents a research project that aims at visually summarizing Western classical and popular music in a way that acts as a track’s unique identifier, provides an immediate overview of its acoustic content, and facilitates meaningful comparisons of music. The project focuses on casual music listeners, and provides extensive analysis and visualization facilities for high-quality MP3 audio files. The system has been built using diverse technologies, including Python, JavaScript, PHP, and third-party libraries, and can be extended for further research purposes. To test various aural-to-visual mapping options and expressiveness of key music features, timbre, rhythm, melody, harmony, and loudness have been visualized. The final music visualization setup employs timbre, harmony, and note intensity development over time expressed as spatial organization and color variation cues. The resulting visual fingerprints are capable of conveying important information about music, including its genre, instrumental diversity, and melodic complexity. While currently at its prototype stage, the project has been shown to satisfy its initial goals, with several further research opportunities available, including testing more advanced statistical approaches and conducting user studies.

Performance Analysis of Spatial Color Information for Object Detection Using Background Subtraction

Object detection, which is a primary yet important step in applications including video surveillance, gets difficult when the video of outdoor environment is influenced by illumination and weather changes. Background Subtraction is the method frequently used for in such cases. In this paper, enhanced BS method namely Extended Frame Differencing Method (EFDM) and Extended Histogram Differencing Method (EHDM) using spatial color information are proposed to improve the accuracy and computational efficiency of object detection in real time and outdoor environment. The effects of different spatial color information for the proposed methods are compared and analyzed. The spatial information used in the analysis includes RGB, HSV, CIELab, CIELuv, YCrCb color models. The results show that EFDM and EHDM present better results with HSV spatial color information.

From Pixels to Region: A Salient Region Detection Algorithm for Location-Quantification Image

Image saliency detection has become increasingly important with the development of intelligent identification and machine vision technology. This process is essential for many image processing algorithms such as image retrieval, image segmentation, image recognition, and adaptive image compression. We propose a salient region detection algorithm for full-resolution images. This algorithm analyzes the randomness and correlation of image pixels and pixel-to-region saliency computation mechanism. The algorithm first obtains points with more saliency probability by using the improved smallest univalue segment assimilating nucleus operator. It then reconstructs the entire saliency region detection by taking these points as reference and combining them with image spatial color distribution, as well as regional and global contrasts. The results for subjective and objective image saliency detection show that the proposed algorithm exhibits outstanding performance in terms of technology indices such as precision and recall rates.

CHARACTERIZING THE DUST COMA OF COMET C/2012 S1 (ISON) AT 4.15 AU FROM THE SUN

We report results from broadband visible images of comet C/2012 S1 (ISON) obtained with the Hubble Space Telescope Wide Field Camera 3 on 2013 April 10. C/ISON's coma brightness follows a 1/{\rho} (where {\rho} is the projected distance from the nucleus) profile out to 5000 km, consistent with a constant speed dust outflow model. The turnaround distance in the sunward direction suggests that the dust coma is composed of sub-micron-sized particles emitted at speeds of tens of meters s$^{-1}$. A({\theta})f{\rho}, which is commonly used to characterize the dust production rate, was 1340 and 1240 cm in the F606W and F438W filters, respectively, in apertures <1.6" in radius. The dust colors are slightly redder than solar, with a slope of 5.0$\pm$0.2% per 100 nm, increasing to >10% per 100 nm 10,000 km down the tail. The colors are similar to those of comet C/1995 O1 (Hale-Bopp) and other long-period comets, but somewhat bluer than typical values for short-period comets. The spatial color variations are also reminiscent of C/Hale-Bopp. A sunward jet is visible in enhanced images, curving to the north and then tailward in the outer coma. The 1.6"-long jet is centered at a position angle of 291$^\circ$, with an opening angle of about 45$^\circ$. The jet morphology remains unchanged over 19 hours of our observations, suggesting that it is near the rotational pole of the nucleus, and implying that the pole points to within 30 deg of (RA, Dec) = (330$^\circ$, 0$^\circ$). This pole orientation indicates a high obliquity of 50$^\circ$-80$^\circ$.

A New Colorimetrically-Calibrated Automated Video-Imaging Protocol for Day-Night Fish Counting at the OBSEA Coastal Cabled Observatory

Field measurements of the swimming activity rhythms of fishes are scant due to the difficulty of counting individuals at a high frequency over a long period of time. Cabled observatory video monitoring allows such a sampling at a high frequency over unlimited periods of time. Unfortunately, automation for the extraction of biological information (i.e., animals' visual counts per unit of time) is still a major bottleneck. In this study, we describe a new automated video-imaging protocol for the 24-h continuous counting of fishes in colorimetrically calibrated time-lapse photographic outputs, taken by a shallow water (20 m depth) cabled video-platform, the OBSEA. The spectral reflectance value for each patch was measured between 400 to 700 nm and then converted into standard RGB, used as a reference for all subsequent calibrations. All the images were acquired within a standardized Region Of Interest (ROI), represented by a 2 × 2 m methacrylate panel, endowed with a 9-colour calibration chart, and calibrated using the recently implemented “3D Thin-Plate Spline” warping approach in order to numerically define color by its coordinates in n-dimensional space. That operation was repeated on a subset of images, 500 images as a training set, manually selected since acquired under optimum visibility conditions. All images plus those for the training set were ordered together through Principal Component Analysis allowing the selection of 614 images (67.6%) out of 908 as a total corresponding to 18 days (at 30 min frequency). The Roberts operator (used in image processing and computer vision for edge detection) was used to highlights regions of high spatial colour gradient corresponding to fishes' bodies. Time series in manual and visual counts were compared together for efficiency evaluation. Periodogram and waveform analysis outputs provided very similar results, although quantified parameters in relation to the strength of respective rhythms were different. Results indicate that automation efficiency is limited by optimum visibility conditions. Data sets from manual counting present the larger day-night fluctuations in comparison to those derived from automation. This comparison indicates that the automation protocol subestimate fish numbers but it is anyway suitable for the study of community activity rhythms.