In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

Low-light is an inescapable element of our daily surroundings that greatly affects the efficiency of our vision. Research works on low-light has seen a steady growth, particularly in the field of image enhancement, but there is still a lack of a go-to database as benchmark. Besides, research fields that may assist us in low-light environments, such as object detection, has glossed over this aspect even though breakthroughs-after-breakthroughs had been achieved in recent years, most noticeably from the lack of low-light data (less than 2% of the total images) in successful public benchmark dataset such as PASCAL VOC, ImageNet, and Microsoft COCO. Thus, we propose the Exclusively Dark dataset to elevate this data drought, consisting exclusively of ten different types of low-light images (i.e. low, ambient, object, single, weak, strong, screen, window, shadow and twilight) captured in visible light only with image and object level annotations. Moreover, we share insightful findings in regards to the effects of low-light on the object detection task by analyzing visualizations of both hand-crafted and learned features. Most importantly, we found that the effects of low-light reaches far deeper into the features than can be solved by simple "illumination invariance'". It is our hope that this analysis and the Exclusively Dark dataset can encourage the growth in low-light domain researches on different fields. The Exclusively Dark dataset with its annotation is available at this https URL

Getting to Know Low-light Images with The Exclusively Dark Dataset

Palmprint processes a number of unique features for reliable personal recognition. However, different types of palmprint images contain different dominant features. Instead, only some features of the palmprint are visible in a palmprint image, whereas the other features may not be notable. For example, the low-resolution palmprint image has visible principal lines and wrinkles. By contrast, the high-resolution palmprint image contains clear ridge patterns and minutiae points. In addition, the three dimensional (3-D) palmprint image possesses curvatures of the palmprint surface. So far, there is no work to summarize the feature extraction of different types of palmprint images. In this paper, we have an aim to completely study the feature extraction and recognition of palmprint. We propose to use a unified framework to classify palmprint images into four categories: 1) the contact-based; 2) contactless; 3) high-resolution; and 4) 3-D palmprint images. Then, we analyze the motivations and theories of the representative extraction and matching methods for different types of palmprint images. Finally, we compare and test the state-of-the-art methods via the widely used palmprint databases, and point out some potential directions for future research.

Feature Extraction Methods for Palmprint Recognition: A Survey and Evaluation

Images captured under poor illumination conditions often exhibit characteristics such as low brightness, low contrast, a narrow gray range, and color distortion, as well as considerable noise, which seriously affect the subjective visual effect on human eyes and greatly limit the performance of various machine vision systems. The role of low-light image enhancement is to improve the visual effect of such images for the benefit of subsequent processing. This paper reviews the main techniques of low-light image enhancement developed over the past decades. First, we present a new classification of these algorithms, dividing them into seven categories: gray transformation methods, histogram equalization methods, Retinex methods, frequency-domain methods, image fusion methods, defogging model methods and machine learning methods. Then, all the categories of methods, including subcategories, are introduced in accordance with their principles and characteristics. In addition, various quality evaluation methods for enhanced images are detailed, and comparisons of different algorithms are discussed. Finally, the current research progress is summarized, and future research directions are suggested.

/pdf/an-experiment-based-review-of-low-light-image-enhancement-5dhscyutxx.pdf

An Experiment-Based Review of Low-Light Image Enhancement Methods

A hybrid optimization algorithm based on cuckoo search and differential evolution for solving constrained engineering problems

Multiview video summarization using video partitioning and clustering

Video frame interpolation is an important area in the computer vision research activities for video post-processing, surveillance, and video restoration tasks. It aims toward increasing the frame rate of a video sequence by calculating intermittent frames between consecutive input frames. This ensures extra smooth, clear motion in order to make animation fluid enough and reduce display motion blur. Advanced deep learning algorithms have the potential to discover knowledge from large-scale diverse video data. These algorithms gain insights about intermediate motion and provide new opportunities to further improve video interpolation technologies. This survey demonstrates a comprehensive overview of about a good number of contributions over past decade pertinent to the latest developments in this domain. The survey paper highlights common challenges in the area of video frame interpolation based on three key aspects: high visual quality, low complexity, and high efficiency of interpolated output from regular videos with the standard frame rate. We scrutinize the architectures, workflows, performance, advantages, and disadvantages and generate a broad categorization along with an overview of experimental results of various state-of-the-art methods executed on benchmark datasets. This survey discusses applications of diverse interpolation frameworks. It provides a backbone reference that inspires future researchers to optimize current techniques on academic and industrial grounds.

A comprehensive survey on video frame interpolation techniques

This paper presents an optimal fuzzy system for image contrast enhancement using differential evolution. The algorithm uses different fuzzification functions for underexposed and overexposed regions of the image. After fuzzification, both of these regions namely underexposed and overexposed are modified using a fuzzy intensification (FINT) operator and power-law, respectively. The fuzzy values are defuzzified using inverse of the membership functions to get enhanced image. An objective function based on histograms of the input and enhanced image is formulated and used in differential evolution algorithm to get the optimized enhancement. The evaluation of the proposed algorithm is evaluated visually as well as quantitatively. The comparison with existing algorithms establishes the supremacy of the proposed algorithm.

Image Contrast Enhancement Using Differential Evolution

In this paper, we proposed a new low-light image enhancementapproach to overcome the above limitations. Theproposed algorithm is named as Nature Preserving LowlightImage Enhancement (NPLIE). NPLIE estimates initialillumination and performs optimal refinement. The proposedalgorithm computes the reflectance component through anelement-wise division of input image by illumination. The enhanced image is obtained as a product of adjusted illumination and reflectance component. In this work, we estimate initialilluminance from structure-aware smoothening of a low-lightimage using guided filters of variable box sizes. We computerefined illumination by solving the proposed multi-objective

/pdf/illumination-estimation-for-nature-preserving-low-light-ovsz0pgzda.pdf

Illumination Estimation for Nature Preserving low-light image enhancement

A novel technique is presented to detect and remove the salt and pepper noise in digital color images. The algorithm is proposed for detection of noisy pixel, edges and noise free pixels by utilizing basic property of salt and pepper noise. Each pixel is treated according whether it is edge pixel, noisy pixel or pixel from smooth region etc. Noisy pixel are replaced with median of neighborhood of noise free pixel. The edge pixel are given special attention so that we do not loose them during the process of noise reduction because of similar nature of intensity difference for impulse noise and edge pixels. For removing noisy pixel from an edge, the median of noise free each pixels are used which led to appreciable reduction of impulse noise and almost no effect on edges. This algorithm gives noticeable better results than most of the existing filters.

Anil Singh Parihar

Papers

Multiview video summarization using video partitioning and clustering

A comprehensive survey on video frame interpolation techniques

Image Contrast Enhancement Using Differential Evolution

Illumination Estimation for Nature Preserving low-light image enhancement

Edge Preserving Fuzzy Filter for Color Images