Objective To study the conversion model of RGB color space to CIE1976 L*a*b* color space with higher accuracy, which provides some value for the fields of computer color matching, color detection, and color reproduction. Methods The method of three-dimensional look-up table method and back propagation (BP) neural network are proposed, and the effect of the model built under the two methods is evaluated under the calculation of CIE1976 L*a*b* and CIE2000 color difference by NCS color card data. Results Under the calculation of CIE1976 L*a*b* color difference, the average color difference under the four interpolation methods of the three-dimensional look-up table is within 3, and the average color difference of the BP neural network algorithm is 1.8720. Under the calculation of CIE2000 color difference, the average color difference of the four interpolation methods of the three-dimensional look-up table drops within 1, and the average color difference of the BP neural network also shows a downward trend, and the specific value is 1.3449. Conclusions According to the result obtained by the research method, the color difference of the tetrahedral interpolation method is the smallest among the four interpolation methods of the three-dimensional look-up table method under both color difference formulas. Whether it is the three-dimensional look-up table method or the BP neural network, the model obtained by the CIE2000 color difference formula is the best. In general, for the two methods, the BP neural network method is more convenient and faster, and the color difference effect is also desirable.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Voice disorders are one of the incipient symptoms of Parkinson's disease (PD). Recent studies have shown that approximately 90% of PD patients suffer from vocal disorders. Therefore, it is significant to extract pathological information on the voice signals to detect PD. In this paper, a feature, named energy direction features based on empirical mode decomposition (EDF-EMD), is proposed to show the different characteristics of voice signals between PD patients and healthy subjects. Firstly, the intrinsic mode functions (IMFs) were obtained through the decomposition of voice signals by EMD. Then, the EDF is obtained by calculating the directional derivatives of the energy spectrum of each IMFs. Finally, the performance of the proposed feature is verified on two different datasets: dataset-Sakar and dataset-CPPDD. The proposed approach shows the best average resulting accuracy of 96.54% on dataset-Sakar and 92.59% on dataset-CPPDD. The results demonstrate that the method proposed in this paper is promising in the field of PD detection.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.