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

FusionGAN: A generative adversarial network for infrared and visible image fusion

Infrared and visible image fusion methods and applications: A survey

In this paper, we proposed a new end-to-end model, termed as dual-discriminator conditional generative adversarial network (DDcGAN), for fusing infrared and visible images of different resolutions. Our method establishes an adversarial game between a generator and two discriminators. The generator aims to generate a real-like fused image based on a specifically designed content loss to fool the two discriminators, while the two discriminators aim to distinguish the structure differences between the fused image and two source images, respectively, in addition to the content loss. Consequently, the fused image is forced to simultaneously keep the thermal radiation in the infrared image and the texture details in the visible image. Moreover, to fuse source images of different resolutions, e.g. , a low-resolution infrared image and a high-resolution visible image, our DDcGAN constrains the downsampled fused image to have similar property with the infrared image. This can avoid causing thermal radiation information blurring or visible texture detail loss, which typically happens in traditional methods. In addition, we also apply our DDcGAN to fusing multi-modality medical images of different resolutions, e.g. , a low-resolution positron emission tomography image and a high-resolution magnetic resonance image. The qualitative and quantitative experiments on publicly available datasets demonstrate the superiority of our DDcGAN over the state-of-the-art, in terms of both visual effect and quantitative metrics. Our code is publicly available at https://github.com/jiayi-ma/DDcGAN .

DDcGAN: A Dual-Discriminator Conditional Generative Adversarial Network for Multi-Resolution Image Fusion

Image denoising review: From classical to state-of-the-art approaches

Image fusion is a well-recognized and a conventional field of image processing. Image fusion provides an efficient way of enhancing and combining pixel-level data resulting in highly informative data for human perception as compared with individual input source data. In this paper, we have demonstrated a comprehensive survey of multi-scale and non-multi-scale decomposition-based image fusion methods in detail. The reference-based and non-reference-based image quality evaluation metrics are summarized together with recent trends in image fusion. Several image fusion applications in various fields have also been reported. It has been stated that though a lot of singular fusion techniques seemed to have given optimum results, the focus of researchers is shifting toward amalgamated or hybrid fusion techniques, which could harness the attributes of both multi-scale and non-multi-scale decomposition methods. Toward the end, the review is concluded with various open challenges for researchers. Thus, the descriptive study in this paper would form basis for stimulating and nurturing advanced research ideas in image fusion.

From Multi-Scale Decomposition to Non-Multi-Scale Decomposition Methods: A Comprehensive Survey of Image Fusion Techniques and Its Applications

The current literature documents a plethora of image denoising techniques in the fields of medical imaging, remote sensing, biometrics, surveillance and vegetation mapping. Therefore it is important to have brief insight into various types of noises in different type of images, for instance medical images, remote sensing images and natural images. This article encompasses the basic definition, history, usage and type of noise affecting some of the major types of imaging modalities. Besides this a brief discussion on the type of noise prevailing in remote sensing and natural images is also given. While designing an effective image denoising algorithm, one needs to be acquainted with the prior information about the noise prevalent in various types of images. Further, a brief idea about the basic principle, outlook, contrast levels and application of medical imaging modalities has also been presented in the context of this article.­­­­­­

Noise Issues Prevailing in Various Types of Medical Images

Many significant images contains some extent of noise, that is unexplained variation in data disturbances in image intensity which are either uninterpretable or out of interest. Image analysis is often simplified if this unwanted noise is filtered. For this image simplification, filtering in frequency domain is done. In this paper we will demonstrate the image sharpening by Gaussian & Butterworth high pass filter and jot some points revealing their differences.

Ayush Dogra

Papers

Image denoising review: From classical to state-of-the-art approaches

From Multi-Scale Decomposition to Non-Multi-Scale Decomposition Methods: A Comprehensive Survey of Image Fusion Techniques and Its Applications

Noise Issues Prevailing in Various Types of Medical Images

Image Sharpening By Gaussian And Butterworth High Pass Filter

Two-dimensional gray scale image denoising via morphological operations in NSST domain & bitonic filtering