31results about How to "Improve the accuracy of discrimination" patented technology

The invention provides a method for discriminating adulterated raw and fresh milk by using near infrared spectrum, which comprises the following steps of: (1) collecting the near infrared spectra of various raw and fresh milk samples and adulterated milk samples, and correspondingly establishing a raw and fresh milk spectrum library and an adulterated milk spectrum library; (2) establishing a discrimination model by using the near infrared spectra in the raw and fresh milk spectrum library and the adulterated milk spectrum library, and correcting the discrimination model so as to obtain an optimal discrimination model; (3) collecting the near infrared spectrum of an unknown milk sample which is adulterated or not adulterated, and discriminating the near infrared spectrum of the unknown milk sample by using the optimal discrimination model so as to obtain the discrimination result of the unknown milk sample, wherein the discrimination model is established by using the SVM (Support Vector Machine) method in the step (2). With the method, the discrimination accuracy on adulterated milk containing various unknown adulterants is greatly increased, and the optimal discrimination model is updated and maintained by expanding and updating the near infrared spectra in the raw and fresh milk spectrum library and the adulterated milk spectrum library.

The invention discloses a sitting posture real-time detection method based on double cameras. The method comprises the following steps of calibrating internal and external parameters of cameras; acquiring a human body sitting posture stereo image through a binocular camera; performing stereo matching for the acquired stereo image, keeping a point cloud in a set range as a potential human body part point cloud; projecting the segmented human body part point cloud in the acquired image to perform image-based human face and human eye detection; judging whether the human faces are detected; judging whether an image rotation angle is greater than a set threshold value; judging whether the human eyes are detected; calling rotation transformation R2 of a calibrated camera coordinate system relative to a vertical plane, and calculating out vertical distance between the human eyes and the cameras through a three-dimensional point cloud nearby the human eyes; adding the set distance between the binocular camera and a desk surface and the distance between the human eyes and the cameras together to obtain the vertical distance between the human eyes and the desk surface; and judging whether the vertical distance between the human eyes and the desk surface is greater than a set vertical distance threshold value. The sitting posture real-time detection method based on double cameras automatically detects human body sitting posture in real time and judges whether the sitting posture is correct or not.

This method combines the real-time filter with the call-bill analysis to filter the garbage notes (GN). It raises the intercepting rate of the GN supervision center and lowers the error judgment rate. Its advantages: 1) The Chinese key words adopt the blur-pinyin / keyword matching mould-board technique to effectively clear the interfere info in GN. 2) According to the behavior character of GN, this method regulates dynamically the user trust levels, integrates the Garbage Degree Value of notes to judge the note genus. 3) The parallel real-time filter programs run on the multi-core hardware platform to reduce the influence of the note supervision center on the processing ability of the note business center. 4) The new strategy of note sorting and processing is: letting legal notes pass, intercepting GN, attaching runner's prompt on the question note, then letting it pass. 5) This system adopts Beyes method to learn off-line the note specimen and generates the GN keyword dictionary.

The invention relates to an intermediate infrared-near infrared correlation spectrum discriminating method for melamine-doped milk. The method comprises the following steps: (1) preparing pure milk for experiment and melamine-doped milk; (2) scanning intermediate infrared spectrums and near infrared spectrums of the pure milk for experiment and the melamine-doped milk; (3) calculating two-dimensional intermediate infrared-near infrared correlation synchronous spectrum matrixes of the pure milk for experiment and the melamine-doped milk respectively; (4) establishing a discriminating model by adopting a multi-dimensional partial least squares method; (5) scanning an unknown sample and calculating to obtain a two-dimensional intermediate infrared-near infrared correlation synchronous spectrum matrix of the unknown sample, and substituting the matrix into the discriminating model, thus judging whether the milk is doped with melamine. According to the invention, the capability of extracting feature information of dopant in milk through the two-dimensional intermediate infrared-near infrared correlation synchronous spectrums is fully utilized, the subjectivity of a direct comparison method for discriminating the doped sample based on the two-dimensional correlation spectrum is overcome, and the method is simple, easy and scientific, and is high in analyzing efficiency and discriminating accuracy.

The invention discloses a Poa pratensis variety identification method based on a hyper-spectral image. The method comprises the following steps of: 1, placing Poa pratensis samples which are prepared in a hyper-spectral imaging device, and acquiring the hyper-spectral image; 2, extracting the information of the hyper-spectral image, which comprises spectral information and / or external characteristic information; 3, calculating total difference between different Poa pratensis varieties at different wave bands according to the spectral information which is extracted; 4, establishing a function model for determining different varieties of Poa pratensis according to the total difference at each wave band or according to the total difference and the external characteristic information; and 5, determining the samples according to the function model which is established in the step 4 to identify different varieties of Poa pratensis. The method provided by the invention is easy and convenient to operate, and has large technical advantages. The acquired information is accurate and reliable, and batch quick identification can be performed.

The present invention provides an FFT-based distributed optical fiber vibration sensing positioning method. By collecting the Rayleigh backscattering signals of multiple pulses, FFT is performed on the signals accumulated at each position. According to the amplitude-frequency characteristics at the position, Determine the frequency of the vibration signal at this position, use the frequency as the judgment condition to screen, and process the frequency results that meet the judgment conditions with the difference at the corresponding position at adjacent times, and accurately identify the real and effective vibration position when the optical cable is affected by the external environment. The present invention also provides an FFT-based distributed optical fiber vibration sensing and positioning device, which is used to implement the aforementioned positioning method. The invention judges the vibration position by combining the vibration frequency characteristics of different vibration forms and the real vibration suddenness characteristics, the algorithm is simple to realize, and has good engineering practicability.