Peter Majewicz

Correcting Specular Noise in Multiple Images of Photographed Documents

Portable digital cameras have become omnipresent. Their low-lost, simplicity to use, flexibility, and good quality images have widened their applicability far beyond their original purpose of taking personal photos. Every day people discover new uses for them from photographing teaching boards to documents. One of the difficulties of using cameras is the occurrence of specular noise whenever the photographed object is glossy. This paper presents an efficient algorithm for removing the specular noise of photographed documents by taking multiple images with different illumination sources.

Document page classification algorithms in low-end copy pipeline

We develop real-time, low-complexity image classification algorithms suitable for a copy mode selector embedded in a low-end copier. The algorithms classify scanned images represented in RGB or in an opponent color space. Classes are the eight combinations of mono/color and text/mix/picture/photo. Classification is 30–98% accurate with misclassifications tending to be benign. The algorithms provide for improved copy quality, a simplified user interface, and increased copy rate.

Removing Shade and Specular Noise in Images of Objects and Documents Acquired with a 3D-Scanner

This paper presents an efficient algorithm for removing the specular noise and undesired shades in images of objects and documents acquired with a 3D-Scanner. The basic principle of such device is to photograph objects by taking multiple images with different illumination sources.

AM/FM halftoning: improved cost function and training framework

FM halftoning generates good tone rendition but it is not appropriate for electrophotographic (EP) printers due to the inherent instability of the EP process. Although AM halftoning yields stable dots, it is susceptible to moire and contouring artifacts. To combine the strengths of AM and FM halftoning, the AM/FM halftoning algorithm exploits each advantage of AM and FM halftoning. The resulting halftone textures have green noise spectral characteristics. In this paper, we present an improved training procedure for the AM/FM halftoning algorithm. Since most of the green noise energy is concentrated in the middle frequencies, the tone dependent error diffusion (TDED) parameters (weights and thresholds) are optimized using a new cost function with normalization to distribute the cost evenly over all frequencies. With the new cost function, we can obtain image quality that is very close to the direct binary search (DBS) search-based dispersed-dot halftoning algorithm. The cost function for training the AM part is also modified by penalizing variation in measured tone value across the multiple printer conditions for each combination of dot size and dot density.

Color-to-grayscale conversion with color clustering and significance criteria

An image processing algorithm is presented that adaptively converts color images to grayscale. The intent of the conversion is to preserve color information that is traditionally lost by the conversion process. The conversion produces high-contrast grayscale representations with enhanced color discriminability. A web-based psychometric study confirms that the algorithm is mostly preferred over traditional algorithms. The algorithm employs a multi-stepped approach that includes color clustering, 3-dimensional partitioning, and simulated annealing.

Hardware-friendly mixed content compression algorithm

The mixed content compression (MCC) algorithm developed in this research provides a hardware efficient solution for compression of scanned compound document images. MCC allows for an easy implementation in imaging pipeline hardware by using only an 8 row buffer of pixels. MCC uses the JPEG encoder to effectively compress the background and picture content of a document image. The remaining text and line graphics in the image, which require high spatial resolution, but can tolerate low color resolution, are compressed using a JBIG1 encoder and color quantization. To separate the text and graphics from the image, MCC uses a simple mean square error (MSE) block classification algorithm to allow a hardware efficient implementation. Results show that for our comprehensive training suite, the compression ratio average achieved by MCC was 60:1, but JPEG only achieved 35:1. In particular, MCC compression ratios become very high on average (82:1 versus 44:1) for mono text documents, which are very common documents being copied and scanned with all-in-ones. In addition, MCC has an edge sharpening side-effect that is very desirable for the target application.

A Document Page Classification Algorithm in Copy Pipeline

This paper describes a real-time, strip-based, low-complexity document page classification algorithm, which can be used as a copy mode selector in the copy pipeline. The benefits of such a copy mode selector include improving copy quality, simplifying user interaction, and increasing copy rate.