I was wondering whether the numerical representations of individual faces were PCA numerical series. Principal Component Analysis (PCA) is the most common method for image-based recognition, image preprocessing, lossless compression, signal-noise analysis, and high resolution spectrum analysis.
PCA can transform an image into a set of unique components, where each component has a numerical degree of distance and relatedness from an agreed on centered component. The first component has the largest possible variance (it accounts for most of the variability in the group). Each succeeding component has the highest variance that is orthogonal to the preceding components. The transformation of the group proceeds linearly from a group with a high degree of dimensionality to a group with a low degree of dimensionality of which the components of the group with a low degree of dimensionality are uncorrelated.
PCA reduces the dimensionality of a complex group of possibly unrelated activities into a smaller group of principal components that accurately represent the entire group with minimum information loss and no loss of essential intrinsic information. PCA also reveals the internal structure of a group of possibly unrelated activities, it can be used to discover meaningful relationships based on commonalities the internal structure of the group shares with other activities that happened in the past. PCA is well known for forcasting with time-series analysis and regression analysis. In most cases the predictability of specific activities can be calculated with high percentages of certainity, by focusing the reconstruction of projected outcomes on the optimization/maximization of the variances of specific activities.
In addition by categorizing the images into age groups and gender groups that information would be very valuable beyond marketing in longer list of industries world-wide.
PCA can transform an image into a set of unique components, where each component has a numerical degree of distance and relatedness from an agreed on centered component. The first component has the largest possible variance (it accounts for most of the variability in the group). Each succeeding component has the highest variance that is orthogonal to the preceding components. The transformation of the group proceeds linearly from a group with a high degree of dimensionality to a group with a low degree of dimensionality of which the components of the group with a low degree of dimensionality are uncorrelated.
PCA reduces the dimensionality of a complex group of possibly unrelated activities into a smaller group of principal components that accurately represent the entire group with minimum information loss and no loss of essential intrinsic information. PCA also reveals the internal structure of a group of possibly unrelated activities, it can be used to discover meaningful relationships based on commonalities the internal structure of the group shares with other activities that happened in the past. PCA is well known for forcasting with time-series analysis and regression analysis. In most cases the predictability of specific activities can be calculated with high percentages of certainity, by focusing the reconstruction of projected outcomes on the optimization/maximization of the variances of specific activities.
In addition by categorizing the images into age groups and gender groups that information would be very valuable beyond marketing in longer list of industries world-wide.