Histogram equalization

About: Histogram equalization is a research topic. Over the lifetime, 5755 publications have been published within this topic receiving 89313 citations.

PaletteNet: Image Recolorization with Given Color Palette

Abstract: Image recolorization enhances the visual perception of an image for design and artistic purposes. In this work, we present a deep neural network, referred to as PaletteNet, which recolors an image according to a given target color palette that is useful to express the color concept of an image. PaletteNet takes two inputs: a source image to be recolored and a target palette. PaletteNet is then designed to change the color concept of a source image so that the palette of the output image is close to the target palette. To train PaletteNet, the proposed multi-task loss is composed of Euclidean loss and adversarial loss. The experimental results show that the proposed method outperforms the existing recolorization methods. Human experts with a commercial software take on average 18 minutes to recolor an image, while PaletteNet automatically recolors plausible results in less than a second.

Fingerprint classification using a deep convolutional neural network

Abstract: Biometric systems detect authenticity based on users' distinct physiological or behavioral characteristics for purposes of identification and access control. These pattern recognition systems are difficult to bypass when compared to traditional token or password based systems. This paper is proposing a new deep learning architecture for fingerprint recognition. The proposed architecture comprises of a pre-processing stage for extracting texture features from fingerprints, and this stage is performed by using histogram equalization, Gabor enhancement and fingerprint thinning. The pre-processed fingerprints are input into a Deep Convolutional Neural Network classifier. The proposed approach has achieved 98.21% classification accuracy with 0.9 loss. The obtained accuracy is significantly higher than previously reported results on the same dataset, 77%.

A new approach for real-timehistogram equalization usingfpga

Abstract: Thispaper presents anovel design forreal-time histogram equalization basedonfield programmable gatearrays (FPGAs).The designisimplemented usingnonconventional schemes tocompute thehistogram statistics andequalization inparallel. Counters areusedin conjunction withadedicated decoder specially designed forthis purpose. Thehardware isfast, simple, andflexible withreasonable development cost. Theproposed system isimplemented usingStratix IIfamilychiptype EP2S15F484C3. Themaximumclockfrequency can reach upto250MHz.Inthis case, thetotal timerequired toperform histogram equalization foranimageofsize 256X256 is0.262ms.

Development of short-wavelength near-infrared spectral imaging for grain color classification

Abstract: Color class of wheat is an important attribute for the identification of cultivars and the marketing of wheat, but is not always easy to measure in the visible spectral range because of variation in vitreosity and surface structure of the kernels. This work examines whether short-wavelength near IR imaging in the range 632-1098 nm can be used to distinguish different cultivars. The spectral characteristics of six hard white winter and hard red spring wheats were first studied by bulk-sample SW-NIR reflectance spectroscopy using regression analysis to select appropriate wavelengths and sets of wavelengths. Prediction of percent red wheat was better if C-H or O-H vibrational overtones were included in the models in addition to the tail from the visible chromophore absorbance, apparently because the vibrational bands make it possible to normalize the color measurement to the dry matter content of the samples. Next, a reflectance spectral image of 640 X 480 spatial pixels and 11 wavelengths was acquired for a mixture of the two contrasting wheat samples using a CCD camera and a liquid crystal tunable filter. The cultivars were distinguished in the image of principal component (PC) score number two that was calculated from the spectral image. The discrimination is due to the tail from the absorbance band that peaks in the visible. PC images 3 and 6 seem to arise mainly from O-H and C-H bands, respectively, and it is speculated that these spectral features will be important for generating multivariate models to predict the color class of grain. It is shown that the contrast between the red-wheat, white- wheat and background can be increased by applying histogram equalization and segmentation of the kernels in the images.© (1999) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

LBP histogram selection for supervised color texture classification

Abstract: In this paper, we propose a Local Binary Pattern (LBP) histogram selection approach. It consists in assigning to each histogram a score which measures its efficiency to characterize the similarity of the textures within the different classes. The histograms are then ranked according to the proposed score and the most discriminant ones are selected. Experiments, which have been carried out on benchmark color texture image databases, show that the proposed histogram selection approach is able to improve the classification performances.