Fully automatic image colorization based on semantic segmentation technology

Aiming at these problems of image colorization algorithms based on deep learning, such as color bleeding and insufficient color, this paper converts the study of image colorization to the optimization of image semantic segmentation, and proposes a fully automatic image colorization model based on semantic segmentation technology. Firstly, we use the encoder as the local feature extraction network and use VGG-16 as the global feature extraction network. These two parts do not interfere with each other, but they share the low-level feature. Then, the first fusion module is constructed to merge local features and global features, and the fusion results are input into semantic segmentation network and color prediction network respectively. Finally, the color prediction network obtains the semantic segmentation information of the image through the second fusion module, and predicts the chrominance of the image based on it. Through several sets of experiments, it is proved that the performance of our model becomes stronger and stronger under the nourishment of the data. Even in some complex scenes, our model can predict reasonable colors and color correctly, and the output effect is very real and natural.

Further insight into the global variability of the OCA2-HERC2 locus for human pigmentation from multiallelic markers

The OCA2-HERC2 locus is responsible for the greatest proportion of eye color variation in humans. Numerous studies extensively described both functional SNPs and associated patterns of variation over this region. The goal of our study is to examine how these haplotype structures and allelic associations vary when highly variable markers such as microsatellites are used. Eleven microsatellites spanning 357 Kb of OCA2-HERC2 genes are analyzed in 3029 individuals from worldwide populations. We found that several markers display large differences in allele frequency (10% to 35% difference) among Europeans, East Asians and Africans. In Europe, the alleles showing increased frequency can also discriminate individuals with (IrisPlex) predicted blue and brown eyes. Distinct haplotypes are identified around the variants C and T of the functional SNP rs12913832 (associated to blue eyes), with linkage disequilibrium r2 values significant up to 237 Kb. The haplotype carrying the allele rs12913832 C has high frequency (76%) in blue eye predicted individuals (30% in brown eye predicted individuals), while the haplotype associated to the allele rs12913832 T is restricted to brown eye predicted individuals. Finally, homozygosity values reach levels of 91% near rs12913832. Odds ratios show values of 4.2, 7.4 and 10.4 for four markers around rs12913832 and 7.1 for their core haplotype. Hence, this study provides an example on the informativeness of multiallelic markers that, despite their current limited potential contribution to forensic eye color prediction, supports the use of microsatellites for identifying causing variants showing similar genetic features and history.

Color prediction model for hybrid multifilament fabric

In order to facilitate the design of a hybrid filament before spinning, a k-m (Kubelka-Munk) iteration model was proposed, which was based on the calculation method for reflectance of a translucent object and needed to be used in conjunction with a fabric model that can reflect the arrangement order of monofilaments. Therefore, the model can not only calculate the color of each point on the fabric surface, but also the mixed color of the fabric. Twenty fabrics with five different blending ratios of black monofilaments and white monofilaments, four multifilament fineness and three fabric weave types were woven. The relationship between the gray distribution of all points on the fabric surface captured by the camera in a DigiEye colorimeter and calculated by the k-m iteration model was analyzed, and the color difference between the mixed color of the fabric tested by the Datacolor spectrophotometer and that calculated by the k-m iteration model was calculated. The results show that the intersection distance and Pearson correlation coefficient between the gray histogram of the photographed fabric image and that of the calculated fabric image were 0.79 and 0.89, respectively. The average color difference obtained by the k-m iteration model was 0.92 Color Measurement Committee (2:1) units, which was best compared with the calculation results of other models. By discussing the fabric structure parameters causing the lightness difference, it was concluded that the calculated lightness was smaller than the measured lightness difference for fabric with a longer float length, smaller multifilament fineness and a larger black monofilament blending ratio.

Intelligent manufacturing of color blended yarn: Color matching algorithm and manufacturing process through computer numerically controlled ring spinning system

Yarn-dyed textiles complement digital printing textiles, which hold promise for high production and environmentally friendly energy efficiencies. However, the complicated structures of color-blended yarns lead to unpredictable colors in textile products and become a roadblock to developing nonpollution textile products. In the present work, we propose a framework of intelligent manufacturing of color blended yarn by combining the color prediction algorithm with a self-developed computer numerically controlled (CNC) ring spinning system. The S-N model is used for the prediction of the color blending effect of the ring-spun yarn. The optimized blending ratios of ring-spun yarn are obtained based on the proposed linear model of parameter W. Subsequently, the CNC ring-spinning frame is used to manufacture color-blended yarns, which can configure the constituent fibers in such a way that different sections of yarn exhibit different colors.