MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

Color image segmentation: advances and prospects

One of the challenging issues for Orthogonal Frequency Division Multiplexing (OFDM) system is its high Peak-to-Average Power Ratio (PAPR). In this paper, we review and analysis different OFDM PAPR reduction techniques, based on computational complexity, bandwidth expansion, spectral spillage and performance. We also discuss some methods of PAPR reduction for multiuser OFDM broadband communication systems.

https://engold.ui.ac.ir/~sabahi/Advanced%20digital%20communication/An%20Overview%20Peak-to-Average%20Power%20Ratio%20Reduction%20Reduction%20Techniques%20for%20OFDM%20Signals.pdf

An Overview: Peak-to-Average Power Ratio Reduction Techniques for OFDM Signals

Computer and Robot Vision Vol. 1, by R.M. Haralick and Linda G. Shapiro, Addison-Wesley, 1992, ISBN 0-201-10887-1.

Computer and Robot Vision

This paper presents a new reflectance model for rendering computer synthesized images. The model accounts for the relative brightness of different materials and light sources in the same scene. It describes the directional distribution of the reflected light and a color shift that occurs as the reflectance changes with incidence angle. The paper presents a method for obtaining the spectral energy distribution of the light reflected from an object made of a specific real material and discusses a procedure for accurately reproducing the color associated with the spectral energy distribution. The model is applied to the simulation of a metal and a plastic.

A reflectance model for computer graphics

The paper proposes a tone reproduction method using neural network and sigmoid function to perceptually compensate for the characteristics of an output device. The printer was used as an output device and its characteristics were analyzed by colorimetric measurement. The measured device characteristics were used in the learning process of a neural network which modeled the I/O characteristics of the device and the sigmoid function was exploited for optimal tone reproduction curves for the printer. In the application of real images, the mapping function between the proposed tone-curve and input signal of each device was built as a LUT (look-up table) between sigmoid function input to the neural network and output of the neural network. As a result, the proposed algorithms showed detailed color reproduction and enhanced image contrast on the printer.

Tone reproduction technique using neural network in inkjet printers

With the rapid development of display technology as well as the diversity of display, image quality assessment plays an important role in display color reproduction. The image quality has described by objective evaluation based on the physical measured data, such as contrast ratio, color reproduction range, color temperature, and gamma characteristics, etc., however, the final judgement is achieved by perceptual quality assessment of observers. Therefore, it is necessary to investigate the relationship between physical performance of display and perceptual image quality. Thus, in order to evaluate objectively the color reproduction characteristics of two mobile displays, TFT-LCD and AMOLED, we measured the darkroom contrast ratio of full screen, luminance and color temperature of full-screen white, full-screen gray and color linearity, tone reproduction of color scales for each RGB primary, and color reproduction range. Then the pair-wise comparison is implemented for image experts and naive observers not only to judge their preference on principal evaluation attributes but also to subjectively describe perceived image quality. Through two evaluation processes, we derived the objective bases that can prove the results of subjective image quality assessment by interconnecting physical factors that have influence on observers' preference judgements. Finally, this paper provided important information for improving the image quality and increasing preference from an observer's point of view.

Evaluation of Color Reproduction Characteristics of TFT-LCD and AMOLED for Mobile Phone

Texture Classification Using Morphological Pattern Spectrum Based on Morphological Subband Decomposition

To acquire a high dynamic range (HDR) image of a scene, several low dynamic range (LDR) images acquired from a digital camera with different exposure times are generally fused into one HDR image to cover the entire dynamic range of the scene. However, when capturing a scene, the scene dynamic range (SDR) is unknown. Consequently, the exposure times for the LDR images need to be as varied as possible to cover the unknown SDR. This paper proposes a method to estimate the SDR using two LDR im- ages. Using the SDR information, SDR-adaptive exposure times can then be selected to achieve the optimal HDR image. The SDR is defined as two exposure times when captured LDR images are mar- ginally clipped to black and white, indicating the lower and upper limits of the SDR, respectively. To identify these times, two LDR images, an overexposed and an underexposed image, are cap- tured. Using the opto-electronic conversion function of the camera used, the minimum gray level in the overexposed image is then used to estimate the exposure time to make the minimum gray level of the image just black, while the maximum gray level in the under- exposed image is used to estimate the exposure time to make the maximum gray level of the image just white. By evaluating the ac- quired HDR image error according to the exposure times of fused LDR images for various scenes, SDR-adaptive exposure times to acquire an optimal HDR image with the minimal error are selected. Experiments confirm that the quality of an HDR image based on fusing LDR images with the proposed SDR-adaptive exposure times is similar to that of an HDR image based on fusing LDR images with conventionally chosen exposure times, even though the number of LDR images used to acquire the HDR image with the proposed method is much smaller than that used by the conventional method. © 2009 Society for Imaging Science and Technology. DOI: 10.2352/J.ImagingSci.Technol.2009.53.2.020505

High Dynamic Range Image Acquisition from Multiple Low Dynamic Range Images Based on Estimation of Scene Dynamic Range

This paper proposes an adaptive error diffusion algorithm for text enhancement followed by an efficient text segmentation that uses the maximum gradient difference (MGD). The gradients are calculated along with scan lines, then the MGD values are filled within a local window to merge text segments. If the value is above a threshold, the pixel is considered as potential text. Isolated segments are then eliminated in a non-text region filtering process. After the text segmentation, a conventional error diffusion method is applied to the background, while edge enhancement error diffusion is used for the text. Since it is inevitable that visually objectionable artifacts are generated when using two different halftoning algorithms, gradual dilation is proposed to minimize the boundary artifacts in the segmented text blocks before halftoning. Sharpening based on the gradually dilated text region (GDTR) then prevents the printing of successive dots around the text region boundaries. The method is extended to halftone color images to sharpen the text regions. The proposed adaptive error diffusion algorithm involves color halftoning that controls the amount of edge enhancement using a general error filter. However, edge enhancement unfortunately produces color distortion, as edge enhancement and color difference are trade-offs. The multiplicative edge enhancement parameters are selected based on the amount of edge sharpening and color difference. Plus, an additional error factor is introduced to reduce the dot elimination artifact generated by the edge enhancement error diffusion. In experiments, the text of a scanned image was sharper when using the proposed algorithm than with conventional error diffusion without changing the background.

Yeong-Ho Ha

Papers

Tone reproduction technique using neural network in inkjet printers

Evaluation of Color Reproduction Characteristics of TFT-LCD and AMOLED for Mobile Phone

Texture Classification Using Morphological Pattern Spectrum Based on Morphological Subband Decomposition

High Dynamic Range Image Acquisition from Multiple Low Dynamic Range Images Based on Estimation of Scene Dynamic Range

Efficient text segmentation and adaptive color error diffusion for text enhancement