Focused on the problem that Affinity Propagation (AP) clustering algorithm is sensitive to parameter Preference, which is not suitable for sparse data, and has the incorrectly clustered sample points in the clustering results, an algorithm named Adaptive Affinity Propagation clustering based on universal gravitation (GA-AP) was proposed. Firstly, the gravitational search mechanism was introduced into the traditional AP algorithm in order to perform the global optimization to the sample points. Secondly, on the basis of global optimization, the correctly clustered and incorrectly clustered sample points in each cluster were found through the information entropy and Adaptive Boosting (AdaBoost) algorithm, the weights of the sample points were calculated. Each sample point was updated by the corresponding weight, so that the similarity, Preference value, attractiveness and membership degree were updated, and the re-clustering was performed. The above steps were continuously operated until the maximum number of iterations was reached. Through simulation experiments on nine datasets, it can be seen that compared to Affinity Propagation clustering based on Adaptive Attribute Weighting (AFW_AP) algorithm, AP algorithm, K-means clustering (K-means) algorithm and Fuzzy C-Means (FCM) algorithm, the proposed algorithm has the average values of Purity, F-measure and Accuracy (ACC) increased by 0.69, 71.74% and 98.5% respectively at most. Experimental results show that the proposed algorithm reduces the dependence on Preference and improves the clustering effect, especially the accuracy of clustering results for sparse datasets.

Focused on the potential safety hazard of leakage of fingerprint and other biometrics in the cloud environment, as well as the lack of security or convenience of the existing biometric authentication schemes, a terminal APP of trusted fingerprint authentication based on orthogonal decomposition and TrustZone was designed and implemented. The sensitive operations such as fingerprint feature extraction, fingerprint template generation were executed in the trusted execution environment provided by the hardware isolation mechanism of TrustZone, making these operations isolated from the applications in the general execution environment to resist the attacks of malicious programs and ensure the security of the authentication process. The fingerprint template generated on the basis of orthogonal decomposition algorithm integrate the random noise while remaining the matching ability, so that it was able to resist the attack against the feature template to a certain extent. As a result, the fingerprint template was able to be stored and transmitted in the cloud environment, so that the user and the device were unbound, which improved the convenience of biometric authentication. Experiments and theoretical analysis show that the correlation and randomness of the fingerprint template of the proposed algorithm is higher than those of original feature and random projection algorithms, so that the algorithm has stronger security. In addition, the experimental results of time and storage overheads as well as recognition accuracy show that, both convenience and security are considered in this APP, meeting the requirements of security authentication in mobile cloud environment.

In order to solve the problem that Clustering by Fast Search and Find of Density Peaks (CFSFDP) needs to manually select the center on the decision graph, an Integrated Algorithm Based on Density Peaks and Density-based Clustering (IABDPDC) was proposed. Firstly, learning from the principle of CFSFDP, the data with the largest local density was selected as the first center. Then, from the first center, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm improved by Warshall algorithm was used to cluster to obtain the first category. Finally, from the data that has not been clustered, the maximum local density data was found out as the center of the next category and was clustered again by the above algorithm, until all the data was clustered or some data was considered as noise. The proposed algorithm not only solves the problem of manual center selection in CFSFDP, but also optimizes the DBSCAN algorithm, in which, every iteration starts from the current best point (the point with the largest local density). By comparing with the classical algorithms (such as CFSFDP, DBSCAN, fuzzy C-means (FCM) and K-means) on visual datasets and non-visualized datasets, the experimental results show that the proposed algorithm has better clustering effect with higher accuracy.

Concerning the problem that it is difficult to estimate the shape characteristics of irregular objects, a new automatic detection method for irregular jewelry images was put forward by introducing the concept of Principal Component Analysis (PCA) to realize the automatic measurement for jewelry. First, the principal axis of target image was extracted by PCA. Then, four vertices of the external rectangle of jewelry were computed according to the optimization direction of the principal axis. Last, the best-fitted rectangle of irregular contour was positioned to detect the irregular shape of the jewelry. The proposed method was applied to real jewelry images, experimental results illustrate that this algorithm can accurately locate the target in the image. Compared with the linear spectral frequency method and the projection rotation translation method, the subjective and objective evaluation results prove the superiority of the proposed algorithm.

A new corner detection algorithm based on the autocorrelation matrix of Multi-channel Odd Gabor grAdient (MOGA) was proposed to suppress the decrease of corner positioning accuracy caused by the smoothed edge. The input image was transformed by 8-channel odd Gabor filter, and then autocorrelation matrices were constructed for each pixel by Gabor gradient correlation of the pixel and its surrounding pixels. If the sum of the normalized eigenvalues of the pixel was local maxima, the pixel was labeled as a corner. Compared with the classical algorithms, such as Harris and Curvature Scale Space (CSS), the proposed algorithm increased the average rate of correct detection by 17.74%, and decreased the average rate of positioning error by 18.15%. The experimental results show that the proposed algorithm has very good detection performance, and gets higher corner detection rate and better corner positioning accuracy.

The traditional data stream clustering algorithms are mostly based on distance or density, so their clustering quality and processing efficiency are weak. To address the above problems, this paper proposed a data stream clustering algorithm based on dependent function. Firstly, the data points were modeled in the form of matter-element and dependent function was established to solve the problem. Secondly, the value of the dependent function was calculated. According to this value, the degree that data point belongs to a certain cluster was judged. Then, the proposed method was applied to online-offline framework of the data stream clustering. Finally, the proposed algorithm was tested by using the real data set KDD-CUP99 and randomly generated artificial data sets. The experimental results show that clustering purity of the proposed method is over 92%, and it can deal with about 6300 records per second. Compared with the traditional algorithm, the processing efficiency of the algorithm is greatly improved. In the aspects of dimension and the number of cluster, the algorithm shows stronger scalability, and it is suitable for processing large dynamic data set.