Photographs taken by mobile device usually suffer from loss of details and low visual attraction due to the poor light condition. The enhancement of the underexposed image can effectively solve this problem. However, previous work may inevitably wash out some weak edges and lose details when handling several underexposed images. To deal with these problems, this paper presents a detail-preserving underexposed image enhancement method based on a new optimal weighted multi-exposure fusion mechanism. Providing an input underexposed image, we propose a novel multi-exposure image enhancement method which can generate a multi-exposure image sequence. However, none of these images are good enough, as images with high exposure have good brightness and color information, whereas sharp details are better preserved in the images with lower exposure. In order to preserve details and enhance the blurred edges, we propose to solve an energy function to compute the optimal weight of the three measurements: 1) local contrast; 2) saturation; and 3) exposedness. Then a weighted multi-exposed fusion method is used to generate the final image. Since the proposed approach is computationally light-weight, it is possible to implement it on mobile devices, such as smart phones and compact cameras. Various experiment results validate our new method.

Human pose estimation from image or video is a basic issue in computer graphics and computer vision. The challenge of human pose estimation in video lies in the temporal coherency issue. The temporal consistency in video is the contents similarity shown in the video frames. In video, temporal consistency maintenance of human pose estimation is to obtain better long-term consistency. Great major methods for the long-term consistency are using the whole video optimization method, which makes very large computation and absence of consistency before and after articulated limbs. In this paper, a novel method for maintenance of temporal consistency is proposed. We maintain the temporal consistency of the video by the structured space learning and halfway temporal evaluation methods. We adopt a three-stage multi-feature deep convolution network framework to generate the initial posture joints position data, and a long-term temporal coherence is propagated to the overall video at each stage. The long-term consistency is more appealing since it produces stable results over larger periods of time. Our method can achieve good temporal consistency, and get accurate and stable human pose estimation results. Various experimental results demonstrated the superiority of our method.

Content-based image copy detection has become one of the important technologies in copyright protection, where two major processes, content-based feature extraction and matching are included. However, it is certainly true that enough storage space is required to establish a feature database for matching, which greatly increases time and storage consumption, as well as lacks flexibility. Fortunately, perceptual image hashing is a good strategy to address these problems, in which content-based features are extracted and further encoded to hash codes. On the one hand, content-based features provide and ensure higher copy detection accuracy, while on the other hand, hash codes instead of feature database reduce storage space and improve time efficiency. Meanwhile, a better balance between robustness and discrimination is one of the most objectives of image hashing, which is conducive to its application in multimedia management and security. Consequently, we present an effective image hashing method for copy detection. Specifically, to obtain perceptual robustness against to copy attacks, we extract the global statistical characteristics in the gray-level co-occurrence matrix (GLCM) to reveal texture changes. Then, to make up the discrimination limitation, we leverage the local dominant DCT coefficients from the first row/column in each sub-image to calculate vector distance. Finally, two kinds of complementary information (global feature via texture and local feature via vector distance) are simultaneously preserved to generate hash codes. Various experiments performed on benchmark database indicate that our proposed perceptual image hashing provides higher detection accuracy and a better balance between robustness and discrimination than the state-of-the-art algorithms.

Numerous screen content images (SCIs) have been produced to meet the needs of virtual desktop and remote display, which put forward a very urgent requirement for security and management of SCIs. Perceptual hashing is an effective way to deal with this issue. However, since SCIs are generally composed of pictures, graphics and texts, their intrinsic characteristics are different from those of natural images. Thus the previous hashing methods for natural images are not suitable for SCIs. In this paper, we propose a perceptual hashing method for SCIs from the perspective of visual content understanding. Specifically, considering that the visual content understanding of SCIs mainly comes from textual regions, while the contours of text always have thinner width and higher contrast, it is decided to generate hash in the gradient field. An input screen image is first performed by some joint preprocessing operations. Then the maximum gradient magnitude and corresponding orientation information are extracted from three color channels R, G and B. Normalized histogram and local frequency coefficient features are further obtained from the maximum gradient magnitude. Finally, a hash sequence is constructed by statistics that are derived from extracted features. Experiments validated on three SCIs databases were conducted to evaluate classification between robustness and discrimination. Receiver operating characteristics (ROC) results demonstrate that the proposed method is superior to the state-of-the-art algorithms. Besides, SIQAD and SCID databases were leveraged to present the application in reduced-reference screen content image quality assessment, and comparisons show that our hashing could provide accurate predictions than other metrics.

Recently, neural style transfer has become a popular task in both academic research and industrial applications. Although the existing methods made great progress in terms of quality and efficiency, most of them mainly focus on extracting high-level features. Therefore, it is still challenging to display the hierarchical structure of the content image due to lack of texture information, which causes blurred boundaries and distortion of the stylized image. In this paper, a novel neural image and video style transfer scheme is proposed to suppress distortion and preserve the semantic content of the content image, which is capable of yielding satisfactory stylized images and videos of a variety of scenarios. We first propose to assemble a refine network into an auto-encoder framework to guide style transfer, which can ensure that the stylized image have diverse levels of details. Then, we introduce the global content loss and the local region structure loss to train the model and enhance the robustness of the model. In addition, in order to produce a high-quality stylized video, our method not only preserves the image structure, but also introduces a temporal consistency loss and a cycle-temporal loss to avoid temporal incoherence and motion blur as far as possible. Our approach is also friendly for photographic and exposed image and video style transfer. Both quantitative and qualitative evaluation demonstrated the effectiveness of our method.