33results about How to "Identification helps" patented technology

The invention relates to a brake control method based on driver brake intension recognition. The brake control method comprises the following steps: (1) judging the current brake intension of a driver through fuzzy reasoning according to a brake pedal opening value obtained by a brake pedal opening degree sensor and a vehicle running speed obtained by a vehicle speed sensor, and thus obtaining the representation value of the current brake intension; (2) obtaining a brake control command corresponding to the current brake intension according to the representation value of the current brake intension and the current brake pedal opening value and the vehicle speed of the vehicle, and carrying out corresponding brake actions. Compared with the prior art, the brake control method has the advantages of rapid response, high reliability and the like, the brake potential is developed, and the driving safety is improved.

The invention provides a fingerprint and finger vein bimodal recognition decision level fusion method. Two modules, namely a fingerprint module and a vein module are included. The fingerprint module and the vein module read fingerprint images and vein images; the read fingerprint images and vein images are subjected to image quality evaluation according to respective image characteristics to acquire quality scores; the fingerprint images and vein images are preprocessed and recognized, wherein the fingerprint recognition adopts a minutiae-based matching method and the vein recognition adopts an improved Hausdorff distance mode, and respective recognition results are obtained; and finally, a weight is designed according to image quality scores of the two modes, and the recognition results are subjected to decision level fusion according to the weight and a final recognition result is obtained. Based on the fact that the performance of the system after fusion is superior to that of a single fingerprint recognition or finger vein recognition system, the method has strong practicability.

The invention provides a secondary classification fusion identification method for fingerprint and finger vein bimodal identification. A fingerprint module and a vein module are used as primary classifiers, and a secondary decision module is used as a secondary classifier. The method comprises the following steps of: reading a fingerprint image and a vein image through the fingerprint module and the vein module; pre-processing the read images respectively and extracting characteristic point sets of the both; performing identification on the images respectively to obtain respective identification results, wherein the fingerprint identification adopts a detail point match-based method, and the vein identification uses an improved Hausdorff distance mode to perform identification; forming a new characteristic vector by using the extracted fingerprint and vein characteristic point sets in a characteristic series mode through the secondary decision module so as to form the secondary classifier and obtain an identification result; and finally, performing decision-level fusion on the three identification results. The method has the advantages of making full use of identification information of fingerprints and finger veins, and effectively improving the accuracy of an identification system, along with high identification rate.

The invention discloses a system and method for automatic text extraction and recognition of low-resolution medical bill images. The system includes four modules: an image preprocessing module, a field segmentation module, a single character segmentation module, and a character recognition module. The method described includes four steps: image preprocessing, field area recognition, character string segmentation, and character recognition and verification. The present invention can be better applicable to automatic text extraction and recognition of low-resolution medical bill images. By analyzing the layout of the bills, this information can be fully utilized. For images with low image quality, noise and image resolution have a great impact, using the semantics of each field area helps to divide the string into individual characters, which can be converted into single-character recognition. For example, for an invoice number composed of pure numbers, you can use a method specially designed to process images with only numbers; when recognizing, limit the recognition range to ten numbers from 0 to 9, and the recognition rate can be greatly improved.

The invention provides a method and device for a phase shift attribute based on geosteering, and relates to the technical field of oil and gas seismic exploration interpretation. The method comprisesthe steps that according to a normalized complex seismic channel of a post-stack seismic data body and multiple pieces of preset information of a direction perpendicular to the geologic structure trend, complex value correlation corresponding to various directions is calculated to determine an adjacent model track along each direction; then a complex correlation coefficient matrix corresponding tothe various directions is determined; then an instantaneous phase shift attribute of a point in the complex correlation coefficient matrix corresponding to the various directions is determined as thephase shift of the point; a maximum value of the phase shift of the point corresponding to the various directions as an identification result of the phase shift attribute of the point. The method anddevice for the phase shift attribute based on the geosteering have the advantages that the ancient geomorphological structure illusion with an inclination angle can be identified by using the calculation result of the phase shift, the information of the direction perpendicular to the geologic structure trend is introduced, the weak discontinuous anomalous body border can be better identified, thereby being conductive to determining a weak reflective structure and a minute structure.

The invention provides a front face human body automatic identity recognition method under a long-distance video. The method comprises a gait module and a human face module, and the method comprises the steps of firstly reading a video file, using the Adaboost method for detecting pedestrians, automatically opening the human face module and the gait module for respectively adopting the kernel principal component analysis on gait and human face for carrying out feature extraction if detecting the pedestrians, and finally adopting the decision-making level fusion method which adopts the human face features to assist the gait features for carrying out recognition. The method proposes a new solution concept for long-distance identity recognition and adopts the decision-making level fusion method which uses the human face features to assist the gait features. The human face features are assisted in the single-sample gait recognition, and the method has the advantages that even the gait training sample is the single sample and human face images are multiple, the number of the training samples can be expanded from another point of view, thereby being beneficial to the identity recognition, and improving the recognition precision by 2.4% by the fusion with the human face features.

The invention relates to a radiation scanning and detecting device for small and medium size vehicles. The radiation scanning and detecting device for the small and medium size vehicles comprises a door frame, a radiation source, a detector, a supporting platform, a conveyer support, a circulation drag unit, a vehicle wheel guide unit and a hanging bridge unit. The method of the radiation scanning and detecting device for the small and medium size vehicles has the advantages that a top illuminate radiation source U-type detector arrangement mode is adopted, the flattening radiation detection relative to the vehicles is achieved, and image quality is improved effectively; detectors with high sensitivity are adopted, image resolution can achieve the level of package detection, and a security check inspector can identify guns, knives, explosive assemblies and other forbidden objects conveniently; a double-energy detection technology is adopted to detect the material characteristics of the articles inside the vehicles, the fact that the security check inspector can identify flammable and combustible dangerous goods is facilitated; trundles and foot margins are designed and mounted on vehicle conveying devices and check channels, equipment is convenient to mount, debug and move, non-fixed type mounting with the ground is achieved, and the floor of a site cannot be damaged.

The present invention provides a method for identifying defective products in e-commerce based on transfer learning, comprising the following steps: S30 Encoding text information, encoding the text information into vector form to obtain encoded data, and using words in the text information in the current paragraph The co-occurrence in , to obtain a distributed representation; S40 feature extraction, input the encoded data into the algorithm module, and generate domain-independent features through the migration learning algorithm based on confrontational domain adaptation; and S50 defective product identification, domain-independent The feature is used as input, through a multi-channel convolutional neural network, and then connected to multiple layers of fully connected layers to identify defective products. A method for identifying defective products in e-commerce based on transfer learning of the present invention aims at the difference between product data distributions on different e-commerce platforms, uses the transfer learning method to greatly reduce the cost of identifying defective products on different e-commerce platforms, and improves The accuracy of defective product identification is improved.