30results about How to "Guaranteed time and efficiency" patented technology

The invention discloses a multi-view image bidirectional matching strategy with constrained object information. The multi-view image bidirectional matching strategy comprises the following steps: performing multi-view image forward matching of the constrained object information according to an imaging model of the image and the input ground object information so as to improve the reliability of matching similarity measurement and calculation by utilizing the information redundancy between the multi-view images; and performing backward matching of multiple independent stereoscopic images on the multi-view image forward matching result so as to effectively eliminate multiple matching points in the forward matching result, and improve the accuracy of the multi-view image matching result. The matching process of each point to be matched is not influenced in the matching strategy, the matching strategy is a parallel matching strategy, and high-efficiency parallel matching of multiple points to be matched is promoted. According to the method, the operating efficiency and the result reliability of multi-view image dense matching can be effectively improved, and the problems that the efficiency is low and multiple mismatching points exist in a traditional multi-view image matching method for matching single stereoscopic image and fusing multiple matching results are solved.

The invention discloses an information hiding method of a 3-dimensional reference matrix based on a mini sudoku matrix. Firstly, construct a 3D Cubic reference matrix model; secondly, according to the difference table, secret information value and pixel value characteristics, the addressing modification is carried out in the external hidden layer, and the secret information is hidden, and the corresponding space search area is obtained; after that, in The default value of the corresponding space search area is modified, and the secret information is hidden in the inner hidden layer; finally, the value of the pixel group is modified according to the coding coordinates of the inner and outer hidden layers, and the hidden image embedded with the secret information is obtained. Experimental results show that the present invention not only can achieve better image quality and higher embedding capacity, but also has very considerable embedding efficiency and can realize real-time embedding. In addition, according to the algorithm proposed by the present invention, the 3-dimensional reference matrix can still be deduced into an N-dimensional reference matrix, and the time efficiency of information embedding is still guaranteed.

The invention discloses a method for constructing a multi-layer morphological brain network, an intelligent terminal and a storage medium, comprising: acquiring human brain image data, preprocessing the human brain image data, and extracting several brain image data from the human brain image data. Morphological features; divide several morphological features according to brain regions based on the preset cortical atlas, and determine the brain regions to which each morphological feature belongs; according to several morphological features and each morphological feature brain regions, and construct a multi-layer morphological brain network. The construction method of the present invention is simple, and the multi-layer morphological brain network constructed combines various morphological features, taking into account the correlation and specificity between different morphological features, provides rich and comprehensive cerebral cortex morphological information, and ensures the practical Time efficiency and economic benefits in the research and analysis process.

The invention relates to a fast image filtering method based on space filling curves and extreme points. The fast image filtering method based on the space filling curves and the extreme points comprises the following steps: a first step is that a source image to be filtered is input; a second step is that a Hilbert curve is generated; a third step is that pixel points in a two-dimensional image domain are subjected to sequencing according to an order indicated by the Hilbert curve, and a one-dimensional pixel point sequence is generated; a fourth step is that a maximum envelope and a minimum envelope of the one-dimensional pixel point sequence are calculated, and the obtained envelopes are subjected to fine processing; a fifth step is that the maximum envelope and the minimum envelope after the fine processing are used as input values, and an image base and image details after a smoothing filtering process are obtained through calculation of a mean value; and a sixth step is that one-dimensional filtering results of the image base and the image details are subjected to counter-Hilbert sequencing, an original two-dimensional image is divided into a smooth part and a detail part, and therefore filtering is finished. The fast image filtering method based on the space filling curves and the extreme points can extremely reduce interpolation errors and lower the complexity of the filtering, and can achieve a quasi-real-time effect.

The invention relates to an image segmentation method based on a color sample and an electric field model. In the invention, an electric field theory in physics is introduced to color sample learning, model training and pixel classification. The method comprises the steps of: selecting positive sample pixel data and negative sample pixel data of a target area from sample pictures, taking color space as a 3D electric field model and calculating field intensity of each coordinate point, deducing each color value probability belonging to an object area in the space based on a Bayesian criterion, searching an optimal segmentation threshold of an object in the space through an ROC curve describing classification effect, determining related parameters of the field model and a suitable electric field spatial resolution, and building indexes through a mapping table method to further achieve rapid pixel classification and image segmentation. Compared with the histogram model in the prior art, according to the invention, the non-sample point probability can be estimated under the circumstance of a small sample; compared with the kernel density estimation method in the prior art, according to the invention, image segmentation with high precision and high time-efficiency can be realized by using more kernels to describe color distribution of the target area.

The invention discloses an electronic dictionary words retrieval method based on a self-adaptive dictionary tree and relates to a words retrieval technology in an electronic dictionary. The method defines a retrieval structure with two levels which includes a prefix matching level of the self-adaptive dictionary and a complete words matching level for a piecewise dichotomy search. The retrieval method is that the matching of words prefixes is firstly implemented in the self-adaptive dictionary tree, and if the words prefixes are hit, the information of the words is returned. Otherwise, the piecewise dichotomy search level is started for the search, and the words to be searched for or the information of the words which is nearest to the words to be searched for is found out and returned. The electronic dictionary words retrieval method can be used for effectively improving the efficiency of the words search and ensuring the balance of time efficiency and space occupation.

The invention discloses a novel multi-image plumb line track matching method capable of returning multiple elevation values. The method comprises the following steps of: confirming m to-be-matched points of a ground space element (X0, Y0) on a benchmark image by using an image imaging model; matching multiple images restrained by space information to m to-be-matched points; calculating space three-dimensional coordinates (Xi, Yi, Zi) corresponding to the to-be-matched points and an absolute difference (deltaXi and deltaYi) between each coordinate (Xi, Yi) and the space element (X0, Y0) by adopting a multi-image adjustment bundle method, and deciding the returned elevation values according to whether the absolute difference is less than a set threshold. In the multi-image plumb line track matching method, multi-image matching and accuracy test of matching result are together fused to effectively eliminate wrong matching, so that the method can solve the disadvantage that only one elevation value can be returned by the traditional ground image matching method.