A new method for determining the levelness of colored textiles is presented based on the application of principal component analysis and a color levelness index is also introduced. Color levelness is actually a description of the uniformity of color shade in different places of the fabric. Generally levelness is a very important parameter of the quality of textile coloration. The main process affects color levelness is dyeing. An initial level sorption will lead to a level dyeing and the whole process affected by some important factors like dyebath pH, liquor ratio, flow rate and temperature. A common example of unlevel dyeing is nylon with acid dyes that most of the time, cause difficulties for dyers. An acceptably dyed fabric must be a match to a target and is visually even in appearance. In addition to the requirement of piece colored textiles, the demand for unevenly colored textiles has greatly increased. One example is the popularity and large consumption garments which are water-washed, stone-washed and sand-washed. The evaluation and control of the quality of these different appearances require colorists to develop an objective method to measure color levelness. But a visual assessment does not produce quantitative levelness data. Also visual assessments are highly dependent on the judgment of the observer and it is influenced by many factors. On the other hand some researches consist of the study of image processing techniques, characterization of fabric appearance and software development. The objective of this research is to establish a quantitative method to determine the levelness by using PCA. Principal component analysis abbreviated PCA. It has been an important and useful mathematical tool in color technology since the 1960s. Its uses have included defining tolerance intervals and ellipsoidal regions, estimating colorant spectral properties from mixtures, deriving CIE daylight, data reduction for large ensembles of spectra and spectral imaging. It is a common technique for finding pattern in data of high dimension. Principal component analysis explores the variance-covariance or correlation structure of a sample set in vector form. It uses mainly for two purposes of data reduction and principle direction determination. Data reduction is accomplished by neglecting the unimportant directions in which samples variances are insignificant. Because dominate sample variations are along several significant directions, the numbers of these directions approximates the dimensionality of the sample set. The optimal number of eigenvectors which indicate directions depends on the application and accuracy requirement. In this method the principal component analysis technique is employed on K/S function of the reflectance data sets for nylon and acrylic samples and the principal directions and the corresponding eigenvalues of each set have been determined. The term percentage variance can be used as a gauge to estimate the dimensionality of a sample set. The percentage of cumulative variance of the first direction have been computed and introduced as a criterion for evaluation of color levelness which is ideally 100% for level samples. The accuracy and efficiency of the suggested index is evaluated by comparing with the visual observation and the other indexes. Key Words: Levelness, PCA , K/S, Reflectance.