An image taken under the backlight condition shows that a main object or foreground appears very dark, but
a background appears relatively bright since the exposure time of the main object or foreground is relatively
shorter than the one of the background due to high luminance from the background. The determination of
the backlight image is generally done by luminance histogram analysis since it is believed that the distinct
characteristic of the backlight image is a large luminance difference between the foreground and background.
However, this conventional detection method may not be adequate for video images since it generally targets
on still images. Furthermore, the detection of the backlight image would not be performed well if there are
abrupt changes in light, motion, or scenes. Inaccurate detection leads to unnecessary compensation that makes
images over-highlighted or flickered, especially when consecutive frames of video have different illumination
modes. Since an image taken under normal light conditions may also have the similar luminance characteristics
of the backlight image, it would not be sufficient to discriminate between the normal light and backlight image
using only luminance information. Therefore, the analysis of chrominance of images is introduced to detect the
backlight image more accurately.
In this paper, we propose a new algorithm for color/mono classification of scanned images. During the scanning process,
various artifacts were produced by scanner sensors. These artifacts made it difficult to design a classifier for color/mono
classification. The proposed algorithm utilized a pixel color index that reflected pixel colorfulness. For each pixel in the
scanned image, its neighboring block was extracted and the pixel color index was computed using the neighboring block
in the RGB space. To compute the pixel color index, we determined whether the center pixel had homogeneous
neighbors or not. If the center pixel had homogeneous neighbors, the pixel color index was calculated by averaging the
achromatic distances of the homogeneous neighbors. If the maximum value of the pixel color indexes in an image was
larger than the given threshold, the image was classified as a color document.
With the rapid advances of the internet and other multimedia technologies, the digital document market has been
growing steadily. Since most digital images use halftone technologies, quality degradation occurs when one tries to scan
and reprint them. Therefore, it is necessary to extract the halftone areas to produce high quality printing. In this paper, we
propose a low complexity pixel-based halftone detection algorithm. For each pixel, we considered a surrounding block.
If the block contained any flat background regions, text, thin lines, or continuous or non-homogeneous regions, the pixel
was classified as a non-halftone pixel. After excluding those non-halftone pixels, the remaining pixels were considered to
be halftone pixels. Finally, documents were classified as pictures or photo documents by calculating the halftone pixel
ratio. The proposed algorithm proved to be memory-efficient and required low computation costs. The proposed
algorithm was easily implemented using GPU.
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.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.