偏度和峰度的图像色彩和谐变化

Image color harmonization algorithm using skewness and kurtosis

目的当图像颜色较多时,使用Cohen-Or方法进行和谐变化之后的图像颜色丢失严重,和原图像相差较远,并且该方法在计算图像最优和谐模版类型时时间开销大。方法鉴于此,本文引入用于描述变量所有取值分布形态偏向和陡缓程度的偏度和峰度来计算图像的和谐模版灰色区域H值范围,将七种和谐模版分类合并到X、T两大类,按照灰色区域损失最少为最优模版的原则,调整计算出来的和谐模版灰色区域H值到X或者T和谐模版的灰色区域中,采用标准高斯函数将颜色正态迁移到调整后的色彩和谐模版灰色区域中,最终实现图像色彩和谐变化。结果实验结果表明,本文的图像和谐变化结果能和原图像保持较高的相似度,颜色损失较少,并大大降低了和谐变化所需的时间,一幅450×423图像和谐处理的时间开销由原来的2 549.78 s降低为13.869 3 s。结论使用本文方法和谐变化之后的图像最大限度地保持了原有图像的颜色风格,可以为灰度图像着色、图像之间的色彩迁移、工业产品风格转移等应用提供帮助。

Objective Using Cohen-Or method to harmonize a color-rich image leads to severe alterations in the original col- ors of an image and thus creates a processed image that is different from the original one. Furthermore, deciding on the type of optimal color harmonization template is time consuming. Method This study introduces skewness and kurtosis, which are used to describe all variant values in the form of deviation and steep degree, to calculate the scope of the value H of a har- monization template gray area and categorize seven harmonization templates into X and T types. According to the gray area loss of at least the principle of the optimal template, the result of value H is applied to the gray area in the X or T harmoni- zation template. Normalized Gaussian function is commonly used to migrate color into the gray area of the adjusted color harmonization template. Harmonization of the original image is then achieved. Result Experimental resuhs show that the harmonized image using the proposed method exhibits great similarity to the original one, retains the original colors, and considerably reduces the time needed in the process of harmonization. The harmonious processing time of a 450 × 423 image is reduced from 2 549. 78 s to 13. 869 3 s. Conclusion The harmonized image using the proposed method retains its color style similarity to the original image. The proposed method facilitates grayscale image colorization, image color transfer,and industrial product style transfer.