An image captured in dark environment usually has ambient illumination, but the image looks dark and noisy. However, the use of flash can introduce unwanted artifacts such as sharp shadows at silhouettes, red eyes, an...
详细信息
ISBN:
(纸本)9781467385640
An image captured in dark environment usually has ambient illumination, but the image looks dark and noisy. However, the use of flash can introduce unwanted artifacts such as sharp shadows at silhouettes, red eyes, and non-uniform brightness in the image. We propose a new framework to enhance photographs captured in dark environments by combining the best features from a flash and a no-flash image. We use sparse and redundant dictionary learning based approach to denoise the no-flash image. A weighted least squares framework is used to transfer sharp details from the flash image into the no-flash image. We show that our approach is simple and able to generate better images than that of the state-of-the-art flash/no-flash fusion method.
the spread of global smartphone market in the past decade has resulted in exponential growth of unstructured data, particularly in the form of multimedia, in the domain of social networking. Consequently, it has made ...
详细信息
ISBN:
(纸本)9781467385640
the spread of global smartphone market in the past decade has resulted in exponential growth of unstructured data, particularly in the form of multimedia, in the domain of social networking. Consequently, it has made data retrieval cumbersome, specially for the users. this has also posed as a major challenge in the development of new algorithms and technologies. this paper presents a context based search technique for personalized image retrieval, based on Logical Item-set Mining on image Hash-Tags given by the users. the tests were performed on Instagram image datasets of two different users, collected through a crawler and show promising results.
In this work we propose a new formulation for hyperspectral denoising based on the Blind Compressed Sensing (BCS) framework. BCS learns the sparsifying basis during signal recovery combining the advantages of standard...
详细信息
ISBN:
(纸本)9781467385640
In this work we propose a new formulation for hyperspectral denoising based on the Blind Compressed Sensing (BCS) framework. BCS learns the sparsifying basis during signal recovery combining the advantages of standard sparse recovery with dictionary learning. We show that our proposed formulation yields better results than a state-of-the-art technique hyperspectral denoising both in terms of PSNR (more than 1dB improvement) and visual quality.
images taken in bad weather conditions like haze and fog suffer from loss of contrast and color shift. the object radiance is attenuated in the atmosphere and the atmospheric light is added to the scene radiance creat...
详细信息
ISBN:
(纸本)9781467385640
images taken in bad weather conditions like haze and fog suffer from loss of contrast and color shift. the object radiance is attenuated in the atmosphere and the atmospheric light is added to the scene radiance creating a veil like semi-transparent layer called airlight. the methods proposed till now assumes that the atmospheric light is constant throughout the image domain, which may not be true always. Here we propose a method that works under the relaxed assumption that the color of atmospheric light is constant but its intensity may vary in the image. We use the color line model to estimate the contribution of airlight in each patch and interpolate at places where the estimate is not reliable. We apply reverse operation to recover the haze free image.
the presence of both caption/graphics/superimposed and scene texts in video frames is the major cause for the poor accuracy of text recognition methods. this paper proposes an approach for identifying tampered informa...
详细信息
ISBN:
(纸本)9781509009824
the presence of both caption/graphics/superimposed and scene texts in video frames is the major cause for the poor accuracy of text recognition methods. this paper proposes an approach for identifying tampered information by analyzing the spatial distribution of DCT coefficients in a new way for classifying caption and scene text. Since caption text is edited/superimposed, which results in artificially created texts comparing to scene texts that exist naturally in frames. We exploit this fact to identify the presence of caption and scene texts in video frames based on the advantage of DCT coefficients. the proposed method analyzes the distributions of both zero and non-zero coefficients (only positive values) locally by moving a window, and studies histogram operations over each input text line image. this generates line graphs for respective zero and non-zero coefficient coordinates. We further study the behavior of text lines, namely, linearity and smoothness based on centroid location analysis, and the principal axis direction of each text line for classification. Experimental results on standard datasets, namely, ICDAR 2013 video, 2015 video, YVT video and our own data, show that the performances of text recognition methods are improved significantly after-classification compared to before-classification.
this paper presents a camera model to deal with underwater scene reconstruction from multiple images. Effects due to change in path of light ray at the medium interface is modelled for a general medium with unknown re...
详细信息
ISBN:
(纸本)9781467385640
this paper presents a camera model to deal with underwater scene reconstruction from multiple images. Effects due to change in path of light ray at the medium interface is modelled for a general medium with unknown refractive index. Our model calculates the refractive index of the medium and simultaneously removes the geometric refraction effects in images using point correspondences in image pairs. With known internal parameters of the camera we find the external parameters of the camera and then 3-D reconstruction is obtained.
We have developed a novel method for image abstraction which preserves more details present in the salient regions and removes details present in the non- salient regions from the given image of a natural scene. We de...
详细信息
ISBN:
(纸本)9781467385640
We have developed a novel method for image abstraction which preserves more details present in the salient regions and removes details present in the non- salient regions from the given image of a natural scene. We define a region to be salient based on the saliency measure estimated in the region. We propose to preserve details in salient regions by dividing them into smaller groups of pixels and remove details from non- salient regions by dividing them in larger group of pixels. We achieve this kind of grouping by guiding an over- segmentation algorithm with spatially varying block size depending on the saliency measure. the adaptive image abstraction goal is finally achieved using a novel brush called point spread brush which is used to reproduce the action of brush with a varying spatial spread.
In this paper, a compressed domain blind watermarking scheme is proposed which embeds the watermark by altering the number of nonzero transform co-efficients (NNZ) of 4 x 4 transform blocks of the HEVC video sequence....
详细信息
ISBN:
(纸本)9781467385640
In this paper, a compressed domain blind watermarking scheme is proposed which embeds the watermark by altering the number of nonzero transform co-efficients (NNZ) of 4 x 4 transform blocks of the HEVC video sequence. To embed the watermark, firstly, temporally homogeneous blocks having relatively less motion are selected. In this work, watermark is inserted in the Intra (I) frame and the motion characteristics of the I frame has been determined using the motion information of the Inter (P or B) predicted frames of its close neighborhood. the watermark is embedded by altering the NNZ difference of 4 x 4 transform blocks in the consecutive intra predicted frames. A comprehensive set of experiments is carried out to show that the scheme is robust against re-compression attacks while maintaining a descent visual quality (PSNR), the bit increase rate (BIR) of the watermarked video.
We target the problem of image Denoising using Gaussian Processes Regression (GPR). Being a non- parametric regression technique, GPR has received much attention in the recent past and here we further explore its vers...
详细信息
ISBN:
(纸本)9781467385640
We target the problem of image Denoising using Gaussian Processes Regression (GPR). Being a non- parametric regression technique, GPR has received much attention in the recent past and here we further explore its versatility by applying it to a denoising problem. the focus is primarily on the design of a local gradient sensitive kernel that captures pixel similarity in the context of image denoising. this novel kernel formulation is used to shape the smoothness of the joint GP prior. We apply the GPR denoising technique to small patches and then stitch back these patches, this allows the priors to be local and relevant, also this helps us in dealing with GPR complexity. We demonstrate that our GPR based technique gives better PSNR values in comparison to existing popular denoising techniques.
Accurate detection of optic disk and macula are of interest in automated analysis of retinal images as they are landmarks in retina and their detection aids in assessing the severity of diseases based on the locations...
详细信息
ISBN:
(纸本)9781467385640
Accurate detection of optic disk and macula are of interest in automated analysis of retinal images as they are landmarks in retina and their detection aids in assessing the severity of diseases based on the locations of abnormalities relative to these landmarks. the general strategy is to design different methods to these landmarks. In contrast, we propose a novel and unified approach for Optic disk and macula detection in this paper using the Generalized Motion Pattern (GMP) [10] [19] which is derived by inducing motion to an image to smooth out unwanted information. the proposed method is unsupervised, parallelizable and handles illumination differences efficiently but assumes a fixed protocol in image acquisition. the proposed method has been tested on five public datasets and obtained results indicate comparable performance to supervised approaches for the same problem.
暂无评论