Efficient image colorization based on seed pixel selection

Colorization is a technique to automatically produce color components for monochrome images and videos based on a few input colors. Generally, image colorization is initialized from a number of seed pixels whose colors are specified by users, and then the colors are gradually prorogating to the monochrome surroundings under a given optimization constraint. So, the performance of colorization is highly dependent on the selection of seed pixels. However, little attention has been paid to the selection of seed pixels, and how to improve the effectiveness of manual input remains a challenging task. To address this, an improved colorization method using seed pixel selection is proposed to assist the users in determining which pixels are highly required to be colorized for a high-quality colorized image. Specifically, the gray-scale image is first divided into non-overlapped blocks, and then, for each block, two pixels that approximate the average luminance of block are selected as the seeds. After the seed pixels are colored by users, an optimization that minimizes the difference between the seeds and their adjacent pixels is employed to propagate the colors to the other pixels. The experimental results demonstrate that, for a given amount of inputs, the proposed method can achieve a higher PSNR than the conventional colorization methods.     

A heuristic approach to discovering user correlations from organized social stream data

Multimedia Tools and Applications - Recently, with the widespread popularity of SNS (Social Network Service), such as Twitter, Facebook, people are increasingly accustomed to sharing feeling,...     

Social recommendation based on trust and influence in SNS environments

The development of social media provides convenience to people’s lives. People’s social relationship and influence on each other is an important factor in a variety of social activities. It is obviously important for the recommendation, while social relationship and user influence are rarely taken into account in traditional recommendation algorithms. In this paper, we propose a new approach to personalized recommendation on social media in order to make use of such a kind of information, and introduce and define a set of new measures to evaluate trust and influence based on users’ social relationship and rating information. We develop a social recommendation algorithm based on modeling of users’ social trust and influence combined with collaborative filtering. The optimal linear relation between them will be reached by the proposed method, because the importance of users’ social trust and influence varies with the data. Our experimental results show that the proposed algorithm outperforms traditional recommendation in terms of recommendation accuracy and stability.

     

A content-adaptive video quality assessment method for online media service

Multimedia Tools and Applications - Video quality assessment is an important issue for Internet Content Providers (ICPs) to improve their service. Some research has been done on objective video...     

Illumination robust single sample face recognition based on ESRC

Multimedia Tools and Applications - The extended sparse representation classifier (ESRC) is one of the state-of-the-art solutions for single sample face recognition, but it performs...     

An auto-encoder-based summarization algorithm for unstructured videos

Multimedia Tools and Applications - Video summarization is an effective way to quick view videos and relieve the pressure of videos storage. However the traditional algorithms are hardly adapted to...     

Reversible data hiding in encrypted images based on multi-level encryption and block histogram modification

Multimedia Tools and Applications - In recent years there has been significant interest in reversible data hiding, and also in particular, reversible data hiding in encrypted images (RDH-EI). This...     

Multi-window based ensemble learning for classification of imbalanced streaming data

Imbalanced streaming data is commonly encountered in real-world data mining and machine learning applications, and has attracted much attention in recent years. Both imbalanced data and streaming data in practice are normally encountered together; however, little research work has been studied on the two types of data together. In this paper, we propose a multi-window based ensemble learning method for the classification of imbalanced streaming data. Three types of windows are defined to store the current batch of instances, the latest minority instances, and the ensemble classifier. The ensemble classifier consists of a set of latest sub-classifiers, and the instances employed to train each sub-classifier. All sub-classifiers are weighted prior to predicting the class labels of newly arriving instances, and new sub-classifiers are trained only when the precision is below a predefined threshold. Extensive experiments on synthetic datasets and real-world datasets demonstrate that the new approach can efficiently and effectively classify imbalanced streaming data, and generally outperforms existing approaches.     

Analysis and improvement of the quantum image matching

We investigate the quantum image matching algorithm proposed by Jiang et al. (Quantum Inf Process 15(9):3543–3572, 2016). Although the complexity of this algorithm is much better than the classical exhaustive algorithm, there may be an error in it: After matching the area between two images, only the pixel at the upper left corner of the matched area played part in following steps. That is to say, the paper only matched one pixel, instead of an area. If more than one pixels in the big image are the same as the one at the upper left corner of the small image, the algorithm will randomly measure one of them, which causes the error. In this paper, an improved version is presented which takes full advantage of the whole matched area to locate a small image in a big image. The theoretical analysis indicates that the network complexity is higher than the previous algorithm, but it is still far lower than the classical algorithm. Hence, this algorithm is still efficient.     

Simultaneous assay of platelet adhesion at multiple shear rates within a single microfluidic channel

Cardiovascular diseases are currently the major causes of mortality in the world, especially in developed nations. As a predominant one, thrombosis is the platelet aggregation induced by a high shear rate. Platelet aggregation assay can clarify the occurrence mechanism of thrombosis, as well as be used as an important tool in the clinical diagnosis, personalized treatment, and screening of anticoagulants. Thus, relevant studies attracted considerable attention. As an important step in platelet aggregation, platelet adhesion and its detection also attract intensive concern. Thus, some analytical methods have been developed for platelet adhesion assay, and the impact of shear rate is one of the focuses. Compared with other devices, biosensors can give a more accurate result within a shorter time. Furthermore, some biosensors can achieve real-time analysis. However, only one or several shear rates can be tested at the same time, which may decrease the analytical efficiency. Meanwhile, in most cases, only the average platelet adhesion effect within a reactor is detected, and the impact of the distribution of shear rates is improperly neglected. In this study, a microfluidic device with a single channel is designed and fabricated for platelet adhesion assay. When the platelet-rich plasma flows through the collagen-modified sensing surface of the channel bottom, the interaction between platelets and collagen molecules on the entire surface can be simultaneously monitored by using a surface plasmon resonance imaging (SPRi) system. A gradient of the shear rate (0–546 s^-1) could be formed within the channel by choosing a suitable depth-to-width ratio (1:5), so platelet adhesion at multiple shear rates could be monitored simultaneously. This method enables the measurement of the adhesion process of unlabeled platelets on the entire sensing surface, in vitro, at multiple shear rates. Such a system can obtain more accurate platelet adhesion result at a given shear rate than traditional methods. Furthermore, in an individual operation, platelet adhesion can be repeatedly tested at multiple points with an equal shear rate, so a much higher analytical efficiency can also be achieved.