Automatic segmentation of curvilinear objects in medical images plays an important role in the diagnosis and evaluation of human diseases, yet it is a challenging uncertainty in the complex segmentation tasks due to different issues such as various image appearances, low contrast between curvilinear objects and their surrounding backgrounds, thin and uneven curvilinear structures, and improper background illumination conditions. To overcome these challenges, we present a unique curvilinear structure segmentation framework based on an oriented derivative of stick (ODoS) filter and a deep learning network for curvilinear object segmentation in medical images. Currently, a large number of deep learning models emphasize developing deep architectures and ignore capturing the structural features of curvilinear objects, which may lead to unsatisfactory results. Consequently, a new approach that incorporates an ODoS filter as part of a deep learning network is presented to improve the spatial attention of curvilinear objects. Specifically, the input image is transfered into four-channel image constructed by the ODoS filter. In which, the original image is considered the principal part to describe various image appearance and complex background illumination conditions, a multi-step strategy is used to enhance the contrast between curvilinear objects and their surrounding backgrounds, and a vector field is applied to discriminate thin and uneven curvilinear structures. Subsequently, a deep learning framework is employed to extract various structural features for curvilinear object segmentation in medical images. The performance of the computational model is validated in experiments conducted on the publicly available DRIVE, STARE and CHASEDB1 datasets. The experimental results indicate that the presented model yields surprising results compared with those of some state-of-the-art methods.

Curvilinear object segmentation in medical images based on ODoS filter and deep learning network

Abstract Aiming at solving the problems of low success rate and weak robustness of object tracking algorithms based on siamese network in complex scenes with occlusion, deformation, and rotation, a siamese network object tracking algorithm with attention network and adaptive loss function (SiamANAL) is proposed. Firstly, the multi-layer feature fusion module for template branch (MFFMT) and the multi-layer feature fusion module for search branch (MFFMS) are designed. The modified convolutional neural networks (CNN) are used for feature extraction through the fusion module to solve the problem of features loss caused by too deep network. Secondly, an attention network is introduced into the SiamANAL algorithm to calculate the attention of template map features and search map features, which enhances the features of object region, reduces the interference of background region, and improves the accuracy of the algorithm. Finally, an adaptive loss function combined with pairwise Gaussian loss function and cross entropy loss function is designed to increase inter-class separation and intra-class compactness of classification branches and improve the accuracy rate of classification and the success rate of regression. The effectiveness of the proposed algorithm is verified by comparing it with other popular algorithms on two popular benchmarks, the visual object tracking 2018 (VOT2018) and the object tracking benchmark 100 (OTB100). Extensive experiments demonstrate that the proposed tracker achieves competitive performance against state-of-the-art trackers. The success rate and precision rate of the proposed algorithm SiamANAL on OTB100 are 0.709 and 0.883, respectively. With the help of cloud computing services and data storage, the processing performance of the proposed algorithm can be further improved. 

/pdf/a-cloud-oriented-siamese-network-object-tracking-algorithm-1d2jgg8k.pdf

A cloud-oriented siamese network object tracking algorithm with attention network and adaptive loss function

Welcome to Heshan: An Installation to Create Immersive and Entertaining Experiences with Local Art Through Interactive Media Technologies

The invention relates to the field of video copyright protection, and discloses a video to-be-retrieved positioning method applied to video copyright protection, which comprises the following steps: acquiring a plurality of key frame images of each video copyright data in a video copyright data set and a plurality of key frame images of to-be-retrieved video data; extracting a feature vector of the key frame image by using a deep convolutional neural network model; calculating perceptual hash values of a plurality of key frame images of the to-be-retrieved video data and perceptual hash valuesof a plurality of key frame images of each video copyright data; constructing a to-be-retrieved system added with a clustering algorithm and an inverted index; and performing quick retrieval and positioning on the to-be-retrieved video data. According to the method, the infringement fragment or the infringement picture can be accurately positioned, the identification of possible attack resistingmeans of the infringement video is enhanced, the robustness of the model is enhanced, the retrieval efficiency under mass data is improved, and the high accuracy and recall rate of video infringementretrieval are ensured.

Video to-be-retrieved positioning method applied to video copyright protection

The invention relates to a data processing method and device, electronic equipment and a storage medium, and the method comprises the steps of obtaining a plurality of pieces of first feature data ofa target face, and enabling the plurality of pieces of first feature data to be obtained through the extraction of the target face based on different algorithms; and based on a preset feature mappingrelationship, converting the plurality of pieces of first feature data into a plurality of pieces of corresponding second feature data, the plurality of pieces of second feature data having the same feature representation mode. According to the embodiment of the invention, the feature conversion efficiency can be improved.

Data processing method and device, electronic equipment and storage medium

An improved image segmentation model was established to achieve accurate detection of target contours under high noise, low resolution, and uneven illumination environments. The new model is based on the variational level set algorithm, which improves the C–V (Chan and Vese) model and GAC (Geodesic Active Contour) model, fuses the contour and area models to segment the image information, that is, the edge information and region information of the image are fused into the same "energy" functional. According to the geometric characteristics of the curve, GAC model can effectively avoid re parameterization and light insensitivity in the evolution process, and CV model can effectively distinguish the fuzzy boundary of the image by maximizing the gray difference between the target and the background, it has strong anti-noise performance. By solving the steady-state solution of the partial differential equation, the optimal solution of the energy model is solved. New method can improve the calculation accuracy, topological structure adaptability, anti-noise ability, and reduce the light sensitivity effectively. Experiment shows that the new model has good robustness, high real-time performance, and it can effectively improve detection accuracy.

Image contour detection based on improved level set in complex environment

The invention discloses a video parallel retrieval method based on Spark and deep hash, and the method comprises the steps: carrying out the CNN-based video key frame image depth feature extraction ofan original video data set, and obtaining a video abstract image depth feature set; secondly, performing distributed hash-based video key frame image feature quantification on the video abstract image depth feature set to obtain an image distributed coding feature set and a coding lookup book; and finally, performing Spark-based video parallel retrieval on the to-be-retrieved image, searching thebook through Spark-based distributed calculation in combination with encoding, and finally returning the retrieved video of the most approximate image. On the premise of ensuring the accuracy of video retrieval, the calculation efficiency of retrieval can be effectively improved, and then the speed of video retrieval is increased.

Huang Kai

Papers

Image contour detection based on improved level set in complex environment

Video parallel retrieval method based on Spark and deep hash