Colorizing the Prokudin-Gorskii Collection

CS 194-26 Project 1

cs194-26-ahc

Overview

We produce color images from digitized Prokudin-Gorskii glass plate images using image processing techniques, ensuring minimal visual artifacts.

Pre-Cropping

We split the LoC scans in thirds and remove borders based on the blue channel.

cathedral

Alignment

Multiscale Image Pyramid

We downsample the channels by succesive factors of two then, starting at the smallest scale, perform a partial normalized correlation within a certain window, then use offset from the smaller scale as the starting point for the next level.

FFT Method

The multiscale method may have issues when the window sizes are chosen suboptimally. To search a far larger window, the whole image, we align based on the maximum normalized cross-correlation of the image gradient norms of the red and green channels w.r.t. the blue channel using the FFT method for runtime efficiency. We then use the maximum translation to remove areas where no overlap occurs.

Image Gradient Norm

Since some surfaces may not have similar profiles between colors channels, we use the image gradient norm of each channel for the cross correlation.

cathedral

Contrast Enhancement

For contrast enhacement, we convert to YUV space, linearize the Y channel, then convert back to RGB.

emir1 emir2

Color Balance

We use a simple color balancing technique from Adobe Photoshop's "auto levels" command: we scale the histograms of each of the R, G, and B channels such that they span the complete [0, 255] scale.

emir1 emir2